View All Items

Title: Environmental Physical(-)Virtual Interaction to Improve Social Presence with a Virtual Human in Mixed Reality.
Creator: Kim, Kangsoo, Welch, Gregory, Gonzalez, Avelino, Sukthankar, Gita, Bruder, Gerd, Fiore, Stephen, University of Central Florida
Abstract / Description: Interactive Virtual Humans (VHs) are increasingly used to replace or assist real humans in various applications, e.g., military and medical training, education, or entertainment. In most VH research, the perceived social presence with a VH, which denotes the user's sense of being socially connected or co-located with the VH, is the decisive factor in evaluating the social influence of the VH(-)a phenomenon where human users' emotions, opinions, or behaviors are affected by the VH. The purpose...
Show moreInteractive Virtual Humans (VHs) are increasingly used to replace or assist real humans in various applications, e.g., military and medical training, education, or entertainment. In most VH research, the perceived social presence with a VH, which denotes the user's sense of being socially connected or co-located with the VH, is the decisive factor in evaluating the social influence of the VH(-)a phenomenon where human users' emotions, opinions, or behaviors are affected by the VH. The purpose of this dissertation is to develop new knowledge about how characteristics and behaviors of a VH in a Mixed Reality (MR) environment can affect the perception of and resulting behavior with the VH, and to find effective and efficient ways to improve the quality and performance of social interactions with VHs. Important issues and challenges in real(-)virtual human interactions in MR, e.g., lack of physical(-)virtual interaction, are identified and discussed through several user studies incorporating interactions with VH systems. In the studies, different features of VHs are prototyped and evaluated, such as a VH's ability to be aware of and influence the surrounding physical environment, while measuring objective behavioral data as well as collecting subjective responses from the participants. The results from the studies support the idea that the VH's awareness and influence of the physical environment can improve not only the perceived social presence with the VH, but also the trustworthiness of the VH within a social context. The findings will contribute towards designing more influential VHs that can benefit a wide range of simulation and training applications for which a high level of social realism is important, and that can be more easily incorporated into our daily lives as social companions, providing reliable relationships and convenience in assisting with daily tasks.
Show less
Date Issued: 2018
Identifier: CFE0007340, ucf:52115
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007340

Title: Interactive Perception in Robotics.
Creator: Baghbahari Baghdadabad, Masoud, Behal, Aman, Haralambous, Michael, Lin, Mingjie, Sukthankar, Gita, Xu, Yunjun, University of Central Florida
Abstract / Description: Interactive perception is a significant and unique characteristic of embodied agents. An agent can discover plenty of knowledge through active interaction with its surrounding environment. Recently, deep learning structures introduced new possibilities to interactive perception in robotics. The advantage of deep learning is in acquiring self-organizing features from gathered data; however,it is computationally impractical to implement in real-time interaction applications. Moreover, it can be...
Show moreInteractive perception is a significant and unique characteristic of embodied agents. An agent can discover plenty of knowledge through active interaction with its surrounding environment. Recently, deep learning structures introduced new possibilities to interactive perception in robotics. The advantage of deep learning is in acquiring self-organizing features from gathered data; however,it is computationally impractical to implement in real-time interaction applications. Moreover, it can be difficult to attach a physical interpretation. An alternative suggested framework in such cases is integrated perception-action.In this dissertation, we propose two integrated interactive perception-action algorithms for real-time automated grasping of novel objects using pure tactile sensing. While visual sensing andprocessing is necessary for gross reaching movements, it can slow down the grasping process if it is the only sensing modality utilized. To overcome this issue, humans primarily utilize tactile perceptiononce the hand is in contact with the object. Inspired by this, we first propose an algorithm to define similar ability for a robot by formulating the required grasping steps.Next, we develop the algorithm to achieve force closure constraint via suggesting a human-like behavior for the robot to interactively identify the object. During this process, the robot adjuststhe hand through an interactive exploration of the object's local surface normal vector. After the robot finds the surface normal vector, it then tries to find the object edges to have a graspable finalrendezvous with the object. Such achievement is very important in order to find the objects edges for rectangular objects before fully grasping the object. We implement the proposed approacheson an assistive robot to demonstrate the performance of interactive perception-action strategies to accomplish grasping task in an automatic manner.
Show less
Date Issued: 2019
Identifier: CFE0007780, ucf:52361
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007780

Title: Guided Autonomy for Quadcopter Photography.
Creator: Alabachi, Saif, Sukthankar, Gita, Behal, Aman, Lin, Mingjie, Boloni, Ladislau, Laviola II, Joseph, University of Central Florida
Abstract / Description: Photographing small objects with a quadcopter is non-trivial to perform with many common user interfaces, especially when it requires maneuvering an Unmanned Aerial Vehicle (C) to difficult angles in order to shoot high perspectives. The aim of this research is to employ machine learning to support better user interfaces for quadcopter photography. Human Robot Interaction (HRI) is supported by visual servoing, a specialized vision system for real-time object detection, and control policies...
Show morePhotographing small objects with a quadcopter is non-trivial to perform with many common user interfaces, especially when it requires maneuvering an Unmanned Aerial Vehicle (C) to difficult angles in order to shoot high perspectives. The aim of this research is to employ machine learning to support better user interfaces for quadcopter photography. Human Robot Interaction (HRI) is supported by visual servoing, a specialized vision system for real-time object detection, and control policies acquired through reinforcement learning (RL). Two investigations of guided autonomy were conducted. In the first, the user directed the quadcopter with a sketch based interface, and periods of user direction were interspersed with periods of autonomous flight. In the second, the user directs the quadcopter by taking a single photo with a handheld mobile device, and the quadcopter autonomously flies to the requested vantage point.This dissertation focuses on the following problems: 1) evaluating different user interface paradigms for dynamic photography in a GPS-denied environment; 2) learning better Convolutional Neural Network (CNN) object detection models to assure a higher precision in detecting human subjects than the currently available state-of-the-art fast models; 3) transferring learning from the Gazebo simulation into the real world; 4) learning robust control policies using deep reinforcement learning to maneuver the quadcopter to multiple shooting positions with minimal human interaction.
Show less
Date Issued: 2019
Identifier: CFE0007774, ucf:52369
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007774

Title: Game-Theoretic Frameworks and Strategies for Defense Against Network Jamming and Collocation Attacks.
Creator: Hemida, Ahmed, Atia, George, Simaan, Marwan, Vosoughi, Azadeh, Sukthankar, Gita, Guirguis, Mina, University of Central Florida
Abstract / Description: Modern networks are becoming increasingly more complex, heterogeneous, and densely connected. While more diverse services are enabled to an ever-increasing number of users through ubiquitous networking and pervasive computing, several important challenges have emerged. For example, densely connected networks are prone to higher levels of interference, which makes them more vulnerable to jamming attacks. Also, the utilization of software-based protocols to perform routing, load balancing and...
Show moreModern networks are becoming increasingly more complex, heterogeneous, and densely connected. While more diverse services are enabled to an ever-increasing number of users through ubiquitous networking and pervasive computing, several important challenges have emerged. For example, densely connected networks are prone to higher levels of interference, which makes them more vulnerable to jamming attacks. Also, the utilization of software-based protocols to perform routing, load balancing and power management functions in Software-Defined Networks gives rise to more vulnerabilities that could be exploited by malicious users and adversaries. Moreover, the increased reliance on cloud computing services due to a growing demand for communication and computation resources poses formidable security challenges due to the shared nature and virtualization of cloud computing. In this thesis, we study two types of attacks: jamming attacks on wireless networks and side-channel attacks on cloud computing servers. The former attacks disrupt the natural network operation by exploiting the static topology and dynamic channel assignment in wireless networks, while the latter attacks seek to gain access to unauthorized data by co-residing with target virtual machines (VMs) on the same physical node in a cloud server. In both attacks, the adversary faces a static attack surface and achieves her illegitimate goal by exploiting a stationary aspect of the network functionality. Hence, this dissertation proposes and develops counter approaches to both attacks using moving target defense strategies. We study the strategic interactions between the adversary and the network administrator within a game-theoretic framework.First, in the context of jamming attacks, we present and analyze a game-theoretic formulation between the adversary and the network defender. In this problem, the attack surface is the network connectivity (the static topology) as the adversary jams a subset of nodes to increase the level of interference in the network. On the other side, the defender makes judicious adjustments of the transmission footprint of the various nodes, thereby continuously adapting the underlying network topology to reduce the impact of the attack. The defender's strategy is based on playing Nash equilibrium strategies securing a worst-case network utility. Moreover, scalable decomposition-based approaches are developed yielding a scalable defense strategy whose performance closely approaches that of the non-decomposed game for large-scale and dense networks. We study a class of games considering discrete as well as continuous power levels.In the second problem, we consider multi-tenant clouds, where a number of VMs are typically collocated on the same physical machine to optimize performance and power consumption and maximize profit. This increases the risk of a malicious virtual machine performing side-channel attacks and leaking sensitive information from neighboring VMs. The attack surface, in this case, is the static residency of VMs on a set of physical nodes, hence we develop a timed migration defense approach. Specifically, we analyze a timing game in which the cloud provider decides when to migrate a VM to a different physical machine to mitigate the risk of being compromised by a collocated malicious VM. The adversary decides the rate at which she launches new VMs to collocate with the victim VMs. Our formulation captures a data leakage model in which the cost incurred by the cloud provider depends on the duration of collocation with malicious VMs. It also captures costs incurred by the adversary in launching new VMs and by the defender in migrating VMs. We establish sufficient conditions for the existence of Nash equilibria for general cost functions, as well as for specific instantiations, and characterize the best response for both players. Furthermore, we extend our model to characterize its impact on the attacker's payoff when the cloud utilizes intrusion detection systems that detect side-channel attacks. Our theoretical findings are corroborated with extensive numerical results in various settings as well as a proof-of-concept implementation in a realistic cloud setting.
Show less
Date Issued: 2019
Identifier: CFE0007468, ucf:52677
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007468

Title: Context-Centric Affect Recognition From Paralinguistic Features of Speech.
Creator: Marpaung, Andreas, Gonzalez, Avelino, DeMara, Ronald, Sukthankar, Gita, Wu, Annie, Lisetti, Christine, University of Central Florida
Abstract / Description: As the field of affect recognition has progressed, many researchers have shifted from having unimodal approaches to multimodal ones. In particular, the trends in paralinguistic speech affect recognition domain have been to integrate other modalities such as facial expression, body posture, gait, and linguistic speech. Our work focuses on integrating contextual knowledge into paralinguistic speech affect recognition. We hypothesize that a framework to recognize affect through paralinguistic...
Show moreAs the field of affect recognition has progressed, many researchers have shifted from having unimodal approaches to multimodal ones. In particular, the trends in paralinguistic speech affect recognition domain have been to integrate other modalities such as facial expression, body posture, gait, and linguistic speech. Our work focuses on integrating contextual knowledge into paralinguistic speech affect recognition. We hypothesize that a framework to recognize affect through paralinguistic features of speech can improve its performance by integrating relevant contextual knowledge. This dissertation describes our research to integrate contextual knowledge into the paralinguistic affect recognition process from acoustic features of speech. We conceived, built, and tested a two-phased system called the Context-Based Paralinguistic Affect Recognition System (CxBPARS). The first phase of this system is context-free and uses the AdaBoost classifier that applies data on the acoustic pitch, jitter, shimmer, Harmonics-to-Noise Ratio (HNR), and the Noise-to-Harmonics Ratio (NHR) to make an initial judgment about the emotion most likely exhibited by the human elicitor. The second phase then adds context modeling to improve upon the context-free classifications from phase I. CxBPARS was inspired by a human subject study performed as part of this work where test subjects were asked to classify an elicitor's emotion strictly from paralinguistic sounds, and then subsequently provided with contextual information to improve their selections. CxBPARS was rigorously tested and found to, at the worst case, improve the success rate from the state-of-the-art's 42% to 53%.
Show less
Date Issued: 2019
Identifier: CFE0007836, ucf:52831
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007836

Title: Bootstrapping Cognitive Radio Networks.
Creator: Horine, Brent, Turgut, Damla, Wei, Lei, Boloni, Ladislau, Sukthankar, Gita, Garibay, Ivan, University of Central Florida
Abstract / Description: Cognitive radio networks promise more efficient spectrum utilization by leveraging degrees of freedom and distributing data collection. The actual realization of these promises is challenged by distributed control, and incomplete, uncertain and possibly conflicting knowledge bases. We consider two problems in bootstrapping, evolving, and managing cognitive radio networks. The first is Link Rendezvous, or how separate radio nodes initially find each other in a spectrum band with many degrees...
Show moreCognitive radio networks promise more efficient spectrum utilization by leveraging degrees of freedom and distributing data collection. The actual realization of these promises is challenged by distributed control, and incomplete, uncertain and possibly conflicting knowledge bases. We consider two problems in bootstrapping, evolving, and managing cognitive radio networks. The first is Link Rendezvous, or how separate radio nodes initially find each other in a spectrum band with many degrees of freedom, and little shared knowledge. The second is how radio nodes can negotiate for spectrum access with incomplete information.To address the first problem, we present our Frequency Parallel Blind Link Rendezvous algorithm. This approach, designed for recent generations of digital front-ends, implicitly shares vague information about spectrum occupancy early in the process, speeding the progress towards a solution. Furthermore, it operates in the frequency domain, facilitating a parallel channel rendezvous. Finally, it operates without a control channel and can rendezvous anywhere in the operating band. We present simulations and analysis on the false alarm rate for both a feature detector and a cross-correlation detector. We compare our results to the conventional frequency hopping sequence rendezvous techniques.To address the second problem, we model the network as a multi-agent system and negotiate by exchanging proposals, augmented with arguments. These arguments include information about priority status and the existence of other nodes. We show in a variety of network topologies that this process leads to solutions not otherwise apparent to individual nodes, and achieves superior network throughput, request satisfaction, and total number of connections, compared to our baselines. The agents independently formulate proposals based upon communication desires, evaluate these proposals based upon capacity constraints, create arguments in response to proposal rejections, and re-evaluate proposals based upon received arguments. We present our negotiation rules, messages, and protocol and demonstrate how they interoperate in a simulation environment.
Show less
Date Issued: 2012
Identifier: CFE0004546, ucf:49240
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004546

Title: Human Group Behavior Modeling for Virtual Worlds.
Creator: Shah, Syed Fahad Allam, Sukthankar, Gita, Georgiopoulos, Michael, Foroosh, Hassan, Anagnostopoulos, Georgios, University of Central Florida
Abstract / Description: Virtual worlds and massively-multiplayer online games are rich sources of information about large-scale teams and groups, offering the tantalizing possibility of harvesting data about group formation, social networks, and network evolution. They provide new outlets for human social interaction that differ from both face-to-face interactions and non-physically-embodied social networking tools such as Facebook and Twitter. We aim to study group dynamics in these virtual worlds by collecting and...
Show moreVirtual worlds and massively-multiplayer online games are rich sources of information about large-scale teams and groups, offering the tantalizing possibility of harvesting data about group formation, social networks, and network evolution. They provide new outlets for human social interaction that differ from both face-to-face interactions and non-physically-embodied social networking tools such as Facebook and Twitter. We aim to study group dynamics in these virtual worlds by collecting and analyzing public conversational patterns of users grouped in close physical proximity. To do this, we created a set of tools for monitoring, partitioning, and analyzing unstructured conversations between changing groups of participants in Second Life, a massively multi-player online user-constructed environment that allows users to construct and inhabit their own 3D world. Although there are some cues in the dialog, determining social interactions from unstructured chat data alone is a difficult problem, since these environments lack many of the cues that facilitate natural language processing in other conversational settings and different types of social media. Public chat data often features players who speak simultaneously, use jargon and emoticons, and only erratically adhere to conversational norms.Humans are adept social animals capable of identifying friendship groups from a combination of linguistic cues and social network patterns. But what is more important, the content of what people say or their history of social interactions? Moreover, is it possible to identify whether people are part of a group with changing membership merely from general network properties, such as measures of centrality and latent communities? These are the questions that we aim to answer in this thesis. The contributions of this thesis include: 1) a link prediction algorithm for identifying friendship relationships from unstructured chat data 2) a method for identifying social groups based on the results of community detection and topic analysis.The output of these two algorithms (links and group membership) are useful for studying a variety of research questions about human behavior in virtual worlds. To demonstrate this we have performed a longitudinal analysis of human groups in different regions of the Second Life virtual world. We believe that studies performed with our tools in virtual worlds will be a useful stepping stone toward creating a rich computational model of human group dynamics.
Show less
Date Issued: 2011
Identifier: CFE0004164, ucf:49074
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004164

Title: Leveraging Help Requests in POMDP Intelligent Tutors.
Creator: Folsom-Kovarik, Jeremiah, Sukthankar, Gita, Schatz, Sarah, Gonzalez, Avelino, Shumaker, Randall, Schatz, Sarah, University of Central Florida
Abstract / Description: Intelligent tutoring systems (ITSs) are computer programs that model individual learners and adapt instruction to help each learner differently. One way ITSs differ from human tutors is that few ITSs give learners a way to ask questions. When learners can ask for help, their questions have the potential to improve learning directly and also act as a new source of model data to help the ITS personalize instruction. Inquiry modeling gives ITSs the ability to answer learner questions and refine...
Show moreIntelligent tutoring systems (ITSs) are computer programs that model individual learners and adapt instruction to help each learner differently. One way ITSs differ from human tutors is that few ITSs give learners a way to ask questions. When learners can ask for help, their questions have the potential to improve learning directly and also act as a new source of model data to help the ITS personalize instruction. Inquiry modeling gives ITSs the ability to answer learner questions and refine their learner models with an inexpensive new input channel.In order to support inquiry modeling, an advanced planning formalism is applied to ITS learner modeling. Partially observable Markov decision processes (POMDPs) differ from more widely used ITS architectures because they can plan complex action sequences in uncertain situations with machine learning. Tractability issues have previously precluded POMDP use in ITS models. This dissertation introduces two improvements, priority queues and observation chains, to make POMDPs scale well and encompass the large problem sizes that real-world ITSs must confront. A new ITS was created to support trainees practicing a military task in a virtual environment. The development of the Inquiry Modeling POMDP Adaptive Trainer (IMP) began with multiple formative studies on human and simulated learners that explored inquiry modeling and POMDPs in intelligent tutoring. The studies suggest the new POMDP representations will be effective in ITS domains having certain common characteristics.Finally, a summative study evaluated IMP's ability to train volunteers in specific practice scenarios. IMP users achieved post-training scores averaging up to 4.5 times higher than users who practiced without support and up to twice as high as trainees who used an ablated version of IMP with no inquiry modeling. IMP's implementation and evaluation helped explore questions about how inquiry modeling and POMDP ITSs work, while empirically demonstrating their efficacy.
Show less
Date Issued: 2012
Identifier: CFE0004506, ucf:49262
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004506

Title: Analysis of Behaviors in Crowd Videos.
Creator: Mehran, Ramin, Shah, Mubarak, Sukthankar, Gita, Behal, Aman, Tappen, Marshall, Moore, Brian, University of Central Florida
Abstract / Description: In this dissertation, we address the problem of discovery and representation of group activity of humans and objects in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a discriminative representation of human motion in social settings, which captures a wide variety of human activities observable in video sequences. Such motion emerges from the collective behavior of individuals and their interactions and is a significant source of...
Show moreIn this dissertation, we address the problem of discovery and representation of group activity of humans and objects in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a discriminative representation of human motion in social settings, which captures a wide variety of human activities observable in video sequences. Such motion emerges from the collective behavior of individuals and their interactions and is a significant source of information typically employed for applications such as event detection, behavior recognition, and activity recognition. We present new representations of human group motion for static cameras, and propose algorithms for their application to variety of problems.We first propose a method to model and learn the scene activity of a crowd using Social Force Model for the first time in the computer vision community. We present a method to densely estimate the interaction forces between people in a crowd, observed by a static camera. Latent Dirichlet Allocation (LDA) is used to learn the model of the normal activities over extended periods of time. Randomly selected spatio-temporal volumes of interaction forces are used to learn the model of normal behavior of the scene. The model encodes the latent topics of social interaction forces in the scene for normal behaviors. We classify a short video sequence of $n$ frames as normal or abnormal by using the learnt model. Once a sequence of frames is classified as an abnormal, the regions of anomalies in the abnormal frames are localized using the magnitude of interaction forces.The representation and estimation framework proposed above, however, has a few limitations. This algorithm proposes to use a global estimation of the interaction forces within the crowd. It, therefore, is incapable of identifying different groups of objects based on motion or behavior in the scene. Although the algorithm is capable of learning the normal behavior and detects the abnormality, but it is incapable of capturing the dynamics of different behaviors.To overcome these limitations, we then propose a method based on the Lagrangian framework for fluid dynamics, by introducing a streakline representation of flow. Streaklines are traced in a fluid flow by injecting color material, such as smoke or dye, which is transported with the flow and used for visualization. In the context of computer vision, streaklines may be used in a similar way to transport information about a scene, and they are obtained by repeatedly initializing a fixed grid of particles at each frame, then moving both current and past particles using optical flow. Streaklines are the locus of points that connect particles which originated from the same initial position.This approach is advantageous over the previous representations in two aspects: first, its rich representation captures the dynamics of the crowd and changes in space and time in the scene where the optical flow representation is not enough, and second, this model is capable of discovering groups of similar behavior within a crowd scene by performing motion segmentation. We propose a method to distinguish different group behaviors such as divergent/convergent motion and lanes using this framework. Finally, we introduce flow potentials as a discriminative feature to recognize crowd behaviors in a scene. Results of extensive experiments are presented for multiple real life crowd sequences involving pedestrian and vehicular traffic.The proposed method exploits optical flow as the low level feature and performs integration and clustering to obtain coherent group motion patterns. However, we observe that in crowd video sequences, as well as a variety of other vision applications, the co-occurrence and inter-relation of motion patterns are the main characteristics of group behaviors. In other words, the group behavior of objects is a mixture of individual actions or behaviors in specific geometrical layout and temporal order.We, therefore, propose a new representation for group behaviors of humans using the inter-relation of motion patterns in a scene. The representation is based on bag of visual phrases of spatio-temporal visual words. We present a method to match the high-order spatial layout of visual words that preserve the geometry of the visual words under similarity transformations. To perform the experiments we collected a dataset of group choreography performances from the YouTube website. The dataset currently contains four categories of group dances.
Show less
Date Issued: 2011
Identifier: CFE0004482, ucf:49317
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004482

Title: A study of holistic strategies for the recognition of characters in natural scene images.
Creator: Ali, Muhammad, Foroosh, Hassan, Hughes, Charles, Sukthankar, Gita, Wiegand, Rudolf, Yun, Hae-Bum, University of Central Florida
Abstract / Description: Recognition and understanding of text in scene images is an important and challenging task. The importance can be seen in the context of tasks such as assisted navigation for the blind, providing directions to driverless cars, e.g. Google car, etc. Other applications include automated document archival services, mining text from images, and so on. The challenge comes from a variety of factors, like variable typefaces, uncontrolled imaging conditions, and various sources of noise corrupting...
Show moreRecognition and understanding of text in scene images is an important and challenging task. The importance can be seen in the context of tasks such as assisted navigation for the blind, providing directions to driverless cars, e.g. Google car, etc. Other applications include automated document archival services, mining text from images, and so on. The challenge comes from a variety of factors, like variable typefaces, uncontrolled imaging conditions, and various sources of noise corrupting the captured images. In this work, we study and address the fundamental problem of recognition of characters extracted from natural scene images, and contribute three holistic strategies to deal with this challenging task. Scene text recognition (STR) has been a known problem in computer vision and pattern recognition community for over two decades, and is still an active area of research owing to the fact that the recognition performance has still got a lot of room for improvement. Recognition of characters lies at the heart of STR and is a crucial component for a reliable STR system. Most of the current methods heavily rely on discriminative power of local features, such as histograms of oriented gradient (HoG), scale invariant feature transform (SIFT), shape contexts (SC), geometric blur (GB), etc. One of the problems with such methods is that the local features are rasterized in an ad hoc manner to get a single vector for subsequent use in recognition. This rearrangement of features clearly perturbs the spatial correlations that may carry crucial information vis-(&)#224;-vis recognition. Moreover, such approaches, in general, do not take into account the rotational invariance property that often leads to failed recognition in cases where characters in scene images do not occur in upright position. To eliminate this local feature dependency and the associated problems, we propose the following three holistic solutions: The first one is based on modelling character images of a class as a 3-mode tensor and then factoring it into a set of rank-1 matrices and the associated mixing coefficients. Each set of rank-1 matrices spans the solution subspace of a specific image class and enables us to capture the required holistic signature for each character class along with the mixing coefficients associated with each character image. During recognition, we project each test image onto the candidate subspaces to derive its mixing coefficients, which are eventually used for final classification.The second approach we study in this work lets us form a novel holistic feature for character recognition based on active contour model, also known as snakes. Our feature vector is based on two variables, direction and distance, cumulatively traversed by each point as the initial circular contour evolves under the force field induced by the character image. The initial contour design in conjunction with cross-correlation based similarity metric enables us to account for rotational variance in the character image. Our third approach is based on modelling a 3-mode tensor via rotation of a single image. This is different from our tensor based approach described above in that we form the tensor using a single image instead of collecting a specific number of samples of a particular class. In this case, to generate a 3D image cube, we rotate an image through a predefined range of angles. This enables us to explicitly capture rotational variance and leads to better performance than various local approaches.Finally, as an application, we use our holistic model to recognize word images extracted from natural scenes. Here we first use our novel word segmentation method based on image seam analysis to split a scene word into individual character images. We then apply our holistic model to recognize individual letters and use a spell-checker module to get the final word prediction. Throughout our work, we employ popular scene text datasets, like Chars74K-Font, Chars74K-Image, SVT, and ICDAR03, which include synthetic and natural image sets, to test the performance of our strategies. We compare results of our recognition models with several baseline methods and show comparable or better performance than several local feature-based methods justifying thus the importance of holistic strategies.
Show less
Date Issued: 2016
Identifier: CFE0006247, ucf:51076
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006247

Title: Exploring the Multi-touch Interaction Design Space for 3D Virtual Objects to Support Procedural Training Tasks.
Creator: Holderness, Sarah, Laviola II, Joseph, Hughes, Charles, Sukthankar, Gita, Hatchett, Martin, University of Central Florida
Abstract / Description: Multi-touch interaction has the potential to be an important input method for realistic training in 3D environments. However, multi-touch interaction has not been explored much in 3D tasks, especially when trying to leverage realistic, real-world interaction paradigms. A systematic inquiry into what realistic gestures look like for 3D environments is required to understand how users translate real-world motions to multi-touch motions. Once those gestures are defined, it is important to see...
Show moreMulti-touch interaction has the potential to be an important input method for realistic training in 3D environments. However, multi-touch interaction has not been explored much in 3D tasks, especially when trying to leverage realistic, real-world interaction paradigms. A systematic inquiry into what realistic gestures look like for 3D environments is required to understand how users translate real-world motions to multi-touch motions. Once those gestures are defined, it is important to see how we can leverage those gestures to enhance training tasks.In order to explore the interaction design space for 3D virtual objects, we began by conducting our first study exploring user-defined gestures. From this work we identified a taxonomy and design guidelines for 3D multi-touch gestures and how perspective view plays a role in the chosen gesture. We also identified a desire to use pressure on capacitive touch screens. Since the best way to implement pressure still required some investigation, our second study evaluated two different pressure estimation techniques in two different scenarios.Once we had a taxonomy of gestures we wanted to examine whether implementing these realistic multi-touch interactions in a training environment provided training benefits. Our third study compared multi-touch interaction to standard 2D mouse interaction and to actual physical training and found that multi-touch interaction performed better than 2D mouse and as well as physical training. This study showed us that multi-touch training using a realistic gesture set can perform as well as training on the actual apparatus.One limitation of the first training study was that the user had constrained perspective to allow for us to focus on isolating the gestures. Since users can change their perspective in a real life training scenario and therefore gain spatial knowledge of components, we wanted to see if allowing users to alter their perspective helped or hindered training. Our final study compared training with Unconstrained multi-touch interaction, Constrained multi-touch interaction, or training on the actual physical apparatus. Results show that the Unconstrained multi-touch interaction and the Physical groups had significantly better performance scores than the Constrained multi-touch interaction group, with no significant difference between the Unconstrained multi-touch and Physical groups. Our results demonstrate that allowing users more freedom to manipulate objects as they would in the real world benefits training. In addition to the research already performed, we propose several avenues for future research into the interaction design space for 3D virtual objects that we believe will be of value to researchers and designers of 3D multi-touch training environments.
Show less
Date Issued: 2017
Identifier: CFE0006603, ucf:51287
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006603

Title: Data-Driven Simulation Modeling of Construction and Infrastructure Operations Using Process Knowledge Discovery.
Creator: Akhavian, Reza, Behzadan, Amir, Oloufa, Amr, Yun, Hae-Bum, Sukthankar, Gita, Zheng, Qipeng, University of Central Florida
Abstract / Description: Within the architecture, engineering, and construction (AEC) domain, simulation modeling is mainly used to facilitate decision-making by enabling the assessment of different operational plans and resource arrangements, that are otherwise difficult (if not impossible), expensive, or time consuming to be evaluated in real world settings. The accuracy of such models directly affects their reliability to serve as a basis for important decisions such as project completion time estimation and...
Show moreWithin the architecture, engineering, and construction (AEC) domain, simulation modeling is mainly used to facilitate decision-making by enabling the assessment of different operational plans and resource arrangements, that are otherwise difficult (if not impossible), expensive, or time consuming to be evaluated in real world settings. The accuracy of such models directly affects their reliability to serve as a basis for important decisions such as project completion time estimation and resource allocation. Compared to other industries, this is particularly important in construction and infrastructure projects due to the high resource costs and the societal impacts of these projects. Discrete event simulation (DES) is a decision making tool that can benefit the process of design, control, and management of construction operations. Despite recent advancements, most DES models used in construction are created during the early planning and design stage when the lack of factual information from the project prohibits the use of realistic data in simulation modeling. The resulting models, therefore, are often built using rigid (subjective) assumptions and design parameters (e.g. precedence logic, activity durations). In all such cases and in the absence of an inclusive methodology to incorporate real field data as the project evolves, modelers rely on information from previous projects (a.k.a. secondary data), expert judgments, and subjective assumptions to generate simulations to predict future performance. These and similar shortcomings have to a large extent limited the use of traditional DES tools to preliminary studies and long-term planning of construction projects.In the realm of the business process management, process mining as a relatively new research domain seeks to automatically discover a process model by observing activity records and extracting information about processes. The research presented in this Ph.D. Dissertation was in part inspired by the prospect of construction process mining using sensory data collected from field agents. This enabled the extraction of operational knowledge necessary to generate and maintain the fidelity of simulation models. A preliminary study was conducted to demonstrate the feasibility and applicability of data-driven knowledge-based simulation modeling with focus on data collection using wireless sensor network (WSN) and rule-based taxonomy of activities. The resulting knowledge-based simulation models performed very well in properly predicting key performance measures of real construction systems. Next, a pervasive mobile data collection and mining technique was adopted and an activity recognition framework for construction equipment and worker tasks was developed. Data was collected using smartphone accelerometers and gyroscopes from construction entities to generate significant statistical time- and frequency-domain features. The extracted features served as the input of different types of machine learning algorithms that were applied to various construction activities. The trained predictive algorithms were then used to extract activity durations and calculate probability distributions to be fused into corresponding DES models. Results indicated that the generated data-driven knowledge-based simulation models outperform static models created based upon engineering assumptions and estimations with regard to compatibility of performance measure outputs to reality.
Show less
Date Issued: 2015
Identifier: CFE0006023, ucf:51014
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006023

Title: Towards Improving Human-Robot Interaction For Social Robots.
Creator: Khan, Saad, Boloni, Ladislau, Behal, Aman, Sukthankar, Gita, Garibay, Ivan, Fiore, Stephen, University of Central Florida
Abstract / Description: Autonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture...
Show moreAutonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture sanctioned social metrics (CSSMs) to quantify, analyze and predict the behavior of the robot, human soldiers and the public perception in the Market Patrol peacekeeping scenario. 2. We validated the results of the Market Patrol scenario by comparing the predicted values with the judgment of a large group of human observers cognizant of the modeled culture. 3. We modeled the movement of a socially aware mobile robot in a dense crowds, using the concept of a micro-conflict to represent the challenge of giving or not giving way to pedestrians. 4. We developed an approach for the robot behavior in micro-conflicts based on the psychological observation that human opponents will use a consistent strategy. For this, the mobile robot classifies the opponent strategy reflected by the personality and social status of the person and chooses an appropriate counter-strategy that takes into account the urgency of the robots' mission. 5. We developed an alternative approach for the resolution of micro-conflicts based on the imitation of the behavior of the human agent. This approach aims to make the behavior of an autonomous robot closely resemble that of a remotely operated one.
Show less
Date Issued: 2015
Identifier: CFE0005965, ucf:50819
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005965

Title: Content-based Information Retrieval via Nearest Neighbor Search.
Creator: Huang, Yinjie, Georgiopoulos, Michael, Anagnostopoulos, Georgios, Hu, Haiyan, Sukthankar, Gita, Ni, Liqiang, University of Central Florida
Abstract / Description: Content-based information retrieval (CBIR) has attracted significant interest in the past few years. When given a search query, the search engine will compare the query with all the stored information in the database through nearest neighbor search. Finally, the system will return the most similar items. We contribute to the CBIR research the following: firstly, Distance Metric Learning (DML) is studied to improve retrieval accuracy of nearest neighbor search. Additionally, Hash Function...
Show moreContent-based information retrieval (CBIR) has attracted significant interest in the past few years. When given a search query, the search engine will compare the query with all the stored information in the database through nearest neighbor search. Finally, the system will return the most similar items. We contribute to the CBIR research the following: firstly, Distance Metric Learning (DML) is studied to improve retrieval accuracy of nearest neighbor search. Additionally, Hash Function Learning (HFL) is considered to accelerate the retrieval process.On one hand, a new local metric learning framework is proposed - Reduced-Rank Local Metric Learning (R2LML). By considering a conical combination of Mahalanobis metrics, the proposed method is able to better capture information like data's similarity and location. A regularization to suppress the noise and avoid over-fitting is also incorporated into the formulation. Based on the different methods to infer the weights for the local metric, we considered two frameworks: Transductive Reduced-Rank Local Metric Learning (T-R2LML), which utilizes transductive learning, while Efficient Reduced-Rank Local Metric Learning (E-R2LML)employs a simpler and faster approximated method. Besides, we study the convergence property of the proposed block coordinate descent algorithms for both our frameworks. The extensive experiments show the superiority of our approaches.On the other hand, *Supervised Hash Learning (*SHL), which could be used in supervised, semi-supervised and unsupervised learning scenarios, was proposed in the dissertation. By considering several codewords which could be learned from the data, the proposed method naturally derives to several Support Vector Machine (SVM) problems. After providing an efficient training algorithm, we also study the theoretical generalization bound of the new hashing framework. In the final experiments, *SHL outperforms many other popular hash function learning methods. Additionally, in order to cope with large data sets, we also conducted experiments running on big data using a parallel computing software package, namely LIBSKYLARK.
Show less
Date Issued: 2016
Identifier: CFE0006327, ucf:51544
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006327

Title: Modified System Design and Implementation of an Intelligent Assistive Robotic Manipulator.
Creator: Paperno, Nicholas, Behal, Aman, Haralambous, Michael, Sukthankar, Gita, Boloni, Ladislau, Smither, Janan, University of Central Florida
Abstract / Description: This thesis presents three improvements to the current UCF MANUS systems. The first improvement modifies the existing fine motion controller into PI controller that has been optimized to prevent the object from leaving the view of the cameras used for visual servoing. This is achieved by adding a weight matrix to the proportional part of the controller that is constrained by an artificial ROI. When the feature points being used are approaching the boundaries of the ROI, the optimized...
Show moreThis thesis presents three improvements to the current UCF MANUS systems. The first improvement modifies the existing fine motion controller into PI controller that has been optimized to prevent the object from leaving the view of the cameras used for visual servoing. This is achieved by adding a weight matrix to the proportional part of the controller that is constrained by an artificial ROI. When the feature points being used are approaching the boundaries of the ROI, the optimized controller weights are calculated using quadratic programming and added to the nominal proportional gain portion of the controller. The second improvement was a compensatory gross motion method designed to ensure that the desired object can be identified. If the object cannot be identified after the initial gross motion, the end-effector will then be moved to one of three different locations around the object until the object is identified or all possible positions are checked. This framework combines the Kanade-Lucase-Tomasi local tracking method with the ferns global detector/tracker to create a method that utilizes the strengths of both systems to overcome their inherent weaknesses. The last improvement is a particle-filter based tracking algorithm that robustifies the visual servoing function of fine motion. This method performs better than the current global detector/tracker that was being implemented by allowing the tracker to successfully track the object in complex environments with non-ideal conditions.
Show less
Date Issued: 2015
Identifier: CFE0005681, ucf:50180
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005681

Title: Learning Collective Behavior in Multi-relational Networks.
Creator: Wang, Xi, Sukthankar, Gita, Tappen, Marshall, Georgiopoulos, Michael, Hu, Haiyan, Anagnostopoulos, Georgios, University of Central Florida
Abstract / Description: With the rapid expansion of the Internet and WWW, the problem of analyzing social media data has received an increasing amount of attention in the past decade. The boom in social media platforms offers many possibilities to study human collective behavior and interactions on an unprecedented scale. In the past, much work has been done on the problem of learning from networked data with homogeneous topologies, where instances are explicitly or implicitly inter-connected by a single type of...
Show moreWith the rapid expansion of the Internet and WWW, the problem of analyzing social media data has received an increasing amount of attention in the past decade. The boom in social media platforms offers many possibilities to study human collective behavior and interactions on an unprecedented scale. In the past, much work has been done on the problem of learning from networked data with homogeneous topologies, where instances are explicitly or implicitly inter-connected by a single type of relationship. In contrast to traditional content-only classification methods, relational learning succeeds in improving classification performance by leveraging the correlation of the labels between linked instances. However, networked data extracted from social media, web pages, and bibliographic databases can contain entities of multiple classes and linked by various causal reasons, hence treating all links in a homogeneous way can limit the performance of relational classifiers. Learning the collective behavior and interactions in heterogeneous networks becomes much more complex.The contribution of this dissertation include 1) two classification frameworks for identifying human collective behavior in multi-relational social networks; 2) unsupervised and supervised learning models for relationship prediction in multi-relational collaborative networks. Our methods improve the performance of homogeneous predictive models by differentiating heterogeneous relations and capturing the prominent interaction patterns underlying the network structure. The work has been evaluated in various real-world social networks. We believe that this study will be useful for analyzing human collective behavior and interactions specifically in the scenario when the heterogeneous relationships in the network arise from various causal reasons.
Show less
Date Issued: 2014
Identifier: CFE0005439, ucf:50376
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005439

Title: Pen-based Methods For Recognition and Animation of Handwritten Physics Solutions.
Creator: Cheema, Salman, Laviola II, Joseph, Hughes, Charles, Sukthankar, Gita, Hammond, Tracy, University of Central Florida
Abstract / Description: There has been considerable interest in constructing pen-based intelligent tutoring systems due to the natural interaction metaphor and low cognitive load afforded by pen-based interaction. We believe that pen-based intelligent tutoring systems can be further enhanced by integrating animation techniques. In this work, we explore methods for recognizing and animating sketched physics diagrams. Our methodologies enable an Intelligent Tutoring System (ITS) to understand the scenario and...
Show moreThere has been considerable interest in constructing pen-based intelligent tutoring systems due to the natural interaction metaphor and low cognitive load afforded by pen-based interaction. We believe that pen-based intelligent tutoring systems can be further enhanced by integrating animation techniques. In this work, we explore methods for recognizing and animating sketched physics diagrams. Our methodologies enable an Intelligent Tutoring System (ITS) to understand the scenario and requirements posed by a given problem statement and to couple this knowledge with a computational model of the student's handwritten solution. These pieces of information are used to construct meaningful animations and feedback mechanisms that can highlight errors in student solutions. We have constructed a prototype ITS that can recognize mathematics and diagrams in a handwritten solution and infer implicit relationships among diagram elements, mathematics and annotations such as arrows and dotted lines. We use natural language processing to identify the domain of a given problem, and use this information to select one or more of four domain-specific physics simulators to animate the user's sketched diagram. We enable students to use their answers to guide animation behavior and also describe a novel algorithm for checking recognized student solutions. We provide examples of scenarios that can be modeled using our prototype system and discuss the strengths and weaknesses of our current prototype.Additionally, we present the findings of a user study that aimed to identify animation requirements for physics tutoring systems. We describe a taxonomy for categorizing different types of animations for physics problems and highlight how the taxonomy can be used to define requirements for 50 physics problems chosen from a university textbook. We also present a discussion of 56 handwritten solutions acquired from physics students and describe how suitable animations could be constructed for each of them.
Show less
Date Issued: 2014
Identifier: CFE0005472, ucf:50380
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005472

Title: Human-Robot Interaction For Multi-Robot Systems.
Creator: Lewis, Bennie, Sukthankar, Gita, Hughes, Charles, Laviola II, Joseph, Boloni, Ladislau, Hancock, Peter, University of Central Florida
Abstract / Description: Designing an effective human-robot interaction paradigm is particularly important for complex tasks such as multi robot manipulation that require the human and robot to work together in a tightly coupled fashion. Although increasing the number of robots can expand the area that therobots can cover within a bounded period of time, a poor human-robot interface will ultimately compromise the performance of the team of robots. However, introducing a human operator to the team of robots, does not...
Show moreDesigning an effective human-robot interaction paradigm is particularly important for complex tasks such as multi robot manipulation that require the human and robot to work together in a tightly coupled fashion. Although increasing the number of robots can expand the area that therobots can cover within a bounded period of time, a poor human-robot interface will ultimately compromise the performance of the team of robots. However, introducing a human operator to the team of robots, does not automatically improve performance due to the difficulty of teleoperating mobile robots with manipulators. The human operator's concentration is divided not only amongmultiple robots but also between controlling each robot's base and arm. This complexity substantially increases the potential neglect time, since the operator's inability to effectively attend to each robot during a critical phase of the task leads to a significant degradation in task performance.There are several proven paradigms for increasing the efficacy of human-robot interaction: 1) multimodal interfaces in which the user controls the robots using voice and gesture; 2) configurable interfaces which allow the user to create new commands by demonstrating them; 3) adaptive interfaceswhich reduce the operator's workload as necessary through increasing robot autonomy. This dissertation presents an evaluation of the relative benefits of different types of user interfaces for multi-robot systems composed of robots with wheeled bases and three degree of freedom arms. It describes a design for constructing low-cost multi-robot manipulation systems from off the shelfparts.User expertise was measured along three axes (navigation, manipulation, and coordination), and participants who performed above threshold on two out of three dimensions on a calibration task were rated as expert. Our experiments reveal that the relative expertise of the user was the key determinant of the best performing interface paradigm for that user, indicating that good user modeling is essential for designing a human-robot interaction system that will be used for an extended period of time. The contributions of the dissertation include: 1) a model for detecting operator distraction from robot motion trajectories; 2) adjustable autonomy paradigms for reducing operator workload; 3) a method for creating coordinated multi-robot behaviors from demonstrations with a single robot; 4) a user modeling approach for identifying expert-novice differences from short teleoperation traces.
Show less
Date Issued: 2014
Identifier: CFE0005198, ucf:50613
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005198

Title: Identifying Influential Agents in Social Systems.
Creator: Maghami, Mahsa, Sukthankar, Gita, Turgut, Damla, Wu, Annie, Boloni, Ladislau, Garibay, Ivan, University of Central Florida
Abstract / Description: This dissertation addresses the problem of influence maximization in social networks. Influence maximization is applicable to many types of real-world problems, including modeling contagion, technology adoption, and viral marketing. Here we examine an advertisement domain in which the overarching goal is to find the influential nodes in a social network, based on the network structure and the interactions, as targets of advertisement. The assumption is that advertisement budget limits prevent...
Show moreThis dissertation addresses the problem of influence maximization in social networks. Influence maximization is applicable to many types of real-world problems, including modeling contagion, technology adoption, and viral marketing. Here we examine an advertisement domain in which the overarching goal is to find the influential nodes in a social network, based on the network structure and the interactions, as targets of advertisement. The assumption is that advertisement budget limits prevent us from sending the advertisement to everybody in the network. Therefore, a wise selection of the people can be beneficial in increasing the product adoption. To model these social systems, agent-based modeling, a powerful tool for the study of phenomena that are difficult to observe within the confines of the laboratory, is used.To analyze marketing scenarios, this dissertation proposes a new method for propagating information through a social system and demonstrates how it can be used to develop a product advertisement strategy in a simulated market. We consider the desire of agents toward purchasing an item as a random variable and solve the influence maximization problem in steady state using an optimization method to assign the advertisement of available products to appropriate messenger agents. Our market simulation 1) accounts for the effects of group membership on agent attitudes 2) has a network structure that is similar to realistic human systems 3) models inter-product preference correlations that can be learned from market data. The results on synthetic data show that this method is significantly better than network analysis methods based on centrality measures.The optimized influence maximization (OIM) described above, has some limitations. For instance, it relies on a global estimation of the interaction among agents in the network, rendering it incapable of handling large networks. Although OIM is capable of finding the influential nodes in the social network in an optimized way and targeting them for advertising, in large networks, performing the matrix operations required to find the optimized solution is intractable.To overcome this limitation, we then propose a hierarchical influence maximization (HIM) algorithm for scaling influence maximization to larger networks. In the hierarchical method the network is partitioned into multiple smaller networks that can be solved exactly with optimization techniques, assuming a generalized IC model, to identify a candidate set of seed nodes. The candidate nodes are used to create a distance-preserving abstract version of the network that maintains an aggregate influence model between partitions. The budget limitation for the advertising dictates the algorithm's stopping point. On synthetic datasets, we show that our method comes close to the optimal node selection, at substantially lower runtime costs.We present results from applying the HIM algorithm to real-world datasets collected from social media sites with large numbers of users (Epinions, SlashDot, and WikiVote) and compare it with two benchmarks, PMIA and DegreeDiscount, to examine the scalability and performance.Our experimental results reveal that HIM scales to larger networks but is outperformed by degree-based algorithms in highly-connected networks. However, HIM performs well in modular networks where the communities are clearly separable with small number of cross-community edges. This finding suggests that for practical applications it is useful to account for network properties when selecting an influence maximization method.
Show less
Date Issued: 2014
Identifier: CFE0005205, ucf:50647
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005205

Title: Complementary Layered Learning.
Creator: Mondesire, Sean, Wu, Annie, Wiegand, Rudolf, Sukthankar, Gita, Proctor, Michael, University of Central Florida
Abstract / Description: Layered learning is a machine learning paradigm used to develop autonomous robotic-based agents by decomposing a complex task into simpler subtasks and learns each sequentially. Although the paradigm continues to have success in multiple domains, performance can be unexpectedly unsatisfactory. Using Boolean-logic problems and autonomous agent navigation, we show poor performance is due to the learner forgetting how to perform earlier learned subtasks too quickly (favoring plasticity) or...
Show moreLayered learning is a machine learning paradigm used to develop autonomous robotic-based agents by decomposing a complex task into simpler subtasks and learns each sequentially. Although the paradigm continues to have success in multiple domains, performance can be unexpectedly unsatisfactory. Using Boolean-logic problems and autonomous agent navigation, we show poor performance is due to the learner forgetting how to perform earlier learned subtasks too quickly (favoring plasticity) or having difficulty learning new things (favoring stability). We demonstrate that this imbalance can hinder learning so that task performance is no better than that of a sub-optimal learning technique, monolithic learning, which does not use decomposition. Through the resulting analyses, we have identified factors that can lead to imbalance and their negative effects, providing a deeper understanding of stability and plasticity in decomposition-based approaches, such as layered learning.To combat the negative effects of the imbalance, a complementary learning system is applied to layered learning. The new technique augments the original learning approach with dual storage region policies to preserve useful information from being removed from an agent's policy prematurely. Through multi-agent experiments, a 28% task performance increase is obtained with the proposed augmentations over the original technique.
Show less
Date Issued: 2014
Identifier: CFE0005213, ucf:50626
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005213

Machine Learning (5)	+ -
Robotics (3)	+ -
machine learning (3)	+ -
Deep Learning (2)	+ -
POMDP (2)	+ -

UAV (2)	+ -
artificial intelligence (2)	+ -
deep learning (2)	+ -
multi-agent systems (2)	+ -
neural networks (2)	+ -
simulation (2)	+ -
social networks (2)	+ -
user study (2)	+ -
3D (1)	+ -
3D interaction (1)	+ -
Active Learning (1)	+ -
Activity Recognition (1)	+ -
Advertising (1)	+ -
Affect Recognition (1)	+ -
Agent system (1)	+ -
Animation (1)	+ -
Annotation noise (1)	+ -
Applications (1)	+ -
Argumentation (1)	+ -
Artificial Evolution (1)	+ -
Artificial Intelligence (1)	+ -
Artificial Neural Networks (1)	+ -
Assistive Robotic (1)	+ -
Assistive Robotics (1)	+ -
Attention (1)	+ -

ETD Collection (40)	+ -
Honors Collection (1)	+ -

Sukthankar, Gita (41)	+ -
University of Central Florida (41)	+ -
Boloni, Ladislau (11)	+ -
Hughes, Charles (9)	+ -
Wu, Annie (8)	+ -

Georgiopoulos, Michael (6)	+ -
Behal, Aman (5)	+ -
Foroosh, Hassan (5)	+ -
Garibay, Ivan (5)	+ -
Gonzalez, Avelino (5)	+ -
Laviola II, Joseph (5)	+ -
Shah, Mubarak (5)	+ -
Anagnostopoulos, Georgios (4)	+ -
Stanley, Kenneth (4)	+ -
Turgut, Damla (4)	+ -
Fiore, Stephen (3)	+ -
Sukthankar, Rahul (3)	+ -
Tappen, Marshall (3)	+ -
Wiegand, Rudolf (3)	+ -
Haralambous, Michael (2)	+ -
Hu, Haiyan (2)	+ -
Lin, Mingjie (2)	+ -
Mohammed Ali, Awrad (2)	+ -
Moore, Brian (2)	+ -
Wei, Lei (2)	+ -
Yun, Hae-Bum (2)	+ -
Abolghasemi, Pooya (1)	+ -
Akhavian, Reza (1)	+ -
Alabachi, Saif (1)	+ -
Ali, Muhammad (1)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Topical Subject

Collection

Type of Resource

Language

Creator

Format

Owner