Matching Items (38)
Filtering by
- Genre: Academic theses
Description
Humans and robots need to work together as a team to accomplish certain shared goals due to the limitations of current robot capabilities. Human assistance is required to accomplish the tasks as human capabilities are often better suited for certain tasks and they complement robot capabilities in many situations. Given the necessity of human-robot teams, it has been long assumed that for the robotic agent to be an effective team member, it must be equipped with automated planning technologies that helps in achieving the goals that have been delegated to it by their human teammates as well as in deducing its own goal to proactively support its human counterpart by inferring their goals. However there has not been any systematic evaluation on the accuracy of this claim.
In my thesis, I perform human factors analysis on effectiveness of such automated planning technologies for remote human-robot teaming. In the first part of my study, I perform an investigation on effectiveness of automated planning in remote human-robot teaming scenarios. In the second part of my study, I perform an investigation on effectiveness of a proactive robot assistant in remote human-robot teaming scenarios.
Both investigations are conducted in a simulated urban search and rescue (USAR) scenario where the human-robot teams are deployed during early phases of an emergency response to explore all areas of the disaster scene. I evaluate through both the studies, how effective is automated planning technology in helping the human-robot teams move closer to human-human teams. I utilize both objective measures (like accuracy and time spent on primary and secondary tasks, Robot Attention Demand, etc.) and a set of subjective Likert-scale questions (on situation awareness, immediacy etc.) to investigate the trade-offs between different types of remote human-robot teams. The results from both the studies seem to suggest that intelligent robots with automated planning capability and proactive support ability is welcomed in general.
In my thesis, I perform human factors analysis on effectiveness of such automated planning technologies for remote human-robot teaming. In the first part of my study, I perform an investigation on effectiveness of automated planning in remote human-robot teaming scenarios. In the second part of my study, I perform an investigation on effectiveness of a proactive robot assistant in remote human-robot teaming scenarios.
Both investigations are conducted in a simulated urban search and rescue (USAR) scenario where the human-robot teams are deployed during early phases of an emergency response to explore all areas of the disaster scene. I evaluate through both the studies, how effective is automated planning technology in helping the human-robot teams move closer to human-human teams. I utilize both objective measures (like accuracy and time spent on primary and secondary tasks, Robot Attention Demand, etc.) and a set of subjective Likert-scale questions (on situation awareness, immediacy etc.) to investigate the trade-offs between different types of remote human-robot teams. The results from both the studies seem to suggest that intelligent robots with automated planning capability and proactive support ability is welcomed in general.
ContributorsNarayanan, Vignesh (Author) / Kambhampati, Subbarao (Thesis advisor) / Zhang, Yu (Thesis advisor) / Cooke, Nancy J. (Committee member) / Fainekos, Georgios (Committee member) / Arizona State University (Publisher)
Created2015
Description
Many real-world planning problems can be modeled as Markov Decision Processes (MDPs) which provide a framework for handling uncertainty in outcomes of action executions. A solution to such a planning problem is a policy that handles possible contingencies that could arise during execution. MDP solvers typically construct policies for a problem instance without re-using information from previously solved instances. Research in generalized planning has demonstrated the utility of constructing algorithm-like plans that reuse such information. However, using such techniques in an MDP setting has not been adequately explored.
This thesis presents a novel approach for learning generalized partial policies that can be used to solve problems with different object names and/or object quantities using very few example policies for learning. This approach uses abstraction for state representation, which allows the identification of patterns in solutions such as loops that are agnostic to problem-specific properties. This thesis also presents some theoretical results related to the uniqueness and succinctness of the policies computed using such a representation. The presented algorithm can be used as fast, yet greedy and incomplete method for policy computation while falling back to a complete policy search algorithm when needed. Extensive empirical evaluation on discrete MDP benchmarks shows that this approach generalizes effectively and is often able to solve problems much faster than existing state-of-art discrete MDP solvers. Finally, the practical applicability of this approach is demonstrated by incorporating it in an anytime stochastic task and motion planning framework to successfully construct free-standing tower structures using Keva planks.
This thesis presents a novel approach for learning generalized partial policies that can be used to solve problems with different object names and/or object quantities using very few example policies for learning. This approach uses abstraction for state representation, which allows the identification of patterns in solutions such as loops that are agnostic to problem-specific properties. This thesis also presents some theoretical results related to the uniqueness and succinctness of the policies computed using such a representation. The presented algorithm can be used as fast, yet greedy and incomplete method for policy computation while falling back to a complete policy search algorithm when needed. Extensive empirical evaluation on discrete MDP benchmarks shows that this approach generalizes effectively and is often able to solve problems much faster than existing state-of-art discrete MDP solvers. Finally, the practical applicability of this approach is demonstrated by incorporating it in an anytime stochastic task and motion planning framework to successfully construct free-standing tower structures using Keva planks.
ContributorsKala Vasudevan, Deepak (Author) / Srivastava, Siddharth (Thesis advisor) / Zhang, Yu (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2020
Description
Most planning agents assume complete knowledge of the domain, which may not be the case in scenarios where certain domain knowledge is missing. This problem could be due to design flaws or arise from domain ramifications or qualifications. In such cases, planning algorithms could produce highly undesirable behaviors. Planning with incomplete domain knowledge is more challenging than partial observability in the sense that the planning agent is unaware of the existence of such knowledge, in contrast to it being just unobservable or partially observable. That is the difference between known unknowns and unknown unknowns.
In this thesis, I introduce and formulate this as the problem of Domain Concretization, which is inverse to domain abstraction studied extensively before. Furthermore, I present a solution that starts from the incomplete domain model provided to the agent by the designer and uses teacher traces from human users to determine the candidate model set under a minimalistic model assumption. A robust plan is then generated for the maximum probability of success under the set of candidate models. In addition to a standard search formulation in the model-space, I propose a sample-based search method and also an online version of it to improve search time. The solution presented has been evaluated on various International Planning Competition domains where incompleteness was introduced by deleting certain predicates from the complete domain model. The solution is also tested in a robot simulation domain to illustrate its effectiveness in handling incomplete domain knowledge. The results show that the plan generated by the algorithm increases the plan success rate without impacting action cost too much.
In this thesis, I introduce and formulate this as the problem of Domain Concretization, which is inverse to domain abstraction studied extensively before. Furthermore, I present a solution that starts from the incomplete domain model provided to the agent by the designer and uses teacher traces from human users to determine the candidate model set under a minimalistic model assumption. A robust plan is then generated for the maximum probability of success under the set of candidate models. In addition to a standard search formulation in the model-space, I propose a sample-based search method and also an online version of it to improve search time. The solution presented has been evaluated on various International Planning Competition domains where incompleteness was introduced by deleting certain predicates from the complete domain model. The solution is also tested in a robot simulation domain to illustrate its effectiveness in handling incomplete domain knowledge. The results show that the plan generated by the algorithm increases the plan success rate without impacting action cost too much.
ContributorsSharma, Akshay (Author) / Zhang, Yu (Thesis advisor) / Fainekos, Georgios (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2020
Description
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Federated Learning (FL) is envisaged to be a promising solution for collaboratively training a machine learning model while keeping the training data decentralized and private. Instead of sharing raw data to the central entity, the participating client devices share focused updates for aggregation to ensure global convergence of the model. Owing to the shortcomings of manually handcrafted neural network architectures, the research community is striving to develop Neural Architecture Search (NAS) approaches to automatically search for optimal networks that fit the clients’ data. Despite the inaccessibility of clients’ data in an FL setting, the federated NAS literature has recently witnessed great progress to apply these NAS techniques to an FL setting. However, one of the key bottlenecks of Federated Learning is the cost of communication between clients and the server, and the state-of-the-art federated NAS techniques search for networks with millions of parameters that require several rounds of communication to find the optimal weight parameters. Also, deploying a network having millions of parameters on edge devices (which are the typical participants in an FL process) is infeasible due to its computational limitations and increased latency. Thus, this work proposes Weight-Agnostic Federated Neural Architecture Search (WFNAS), a novel evolutionary framework to search for well-performing and minimally connected weight-agnostic network architectures in an FL setting. As the connectivity of the networks themselves is the solution, there is no need for weight training and hyperparameter tuning, reducing the communication overhead significantly. The experiments indicate a gain of nearly 40% for orthogonal (vertical FL) data distributions compared to local training. This work is the first federated NAS technique in the literature for vertical FL. Although the experiments are performed in a resource-constrained environment, the aim of this thesis is to show a new direction of research to the FL community.
ContributorsThakkar, Om (Author) / Bazzi, Rida (Thesis advisor) / Li, Baoxin (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2021
Description
Millimeter wave (mmWave) and massive multiple-input multiple-output (MIMO) systems are intrinsic components of 5G and beyond. These systems rely on using beamforming codebooks for both initial access and data transmission. Current beam codebooks, however, are not optimized for the given deployment, which can sometimes incur noticeable performance loss. To address these problems, in this dissertation, three novel machine learning (ML) based frameworks for site-specific analog beam codebook design are proposed. In the first framework, two special neural network-based architectures are designed for learning environment and hardware aware beam codebooks through supervised and self-supervised learning respectively. To avoid explicitly estimating the channels, in the second framework, a deep reinforcement learning-based architecture is developed. The proposed solution significantly relaxes the system requirements and is particularly interesting in scenarios where the channel acquisition is challenging. Building upon it, in the third framework, a sample-efficient online reinforcement learning-based beam codebook design algorithm that learns how to shape the beam patterns to null the interfering directions, without requiring any coordination with the interferers, is developed. In the last part of the dissertation, the proposed beamforming framework is further extended to tackle the beam focusing problem in near field wideband systems. %Specifically, the developed solution can achieve beam focusing without knowing the user position and can account for unknown and non-uniform array geometry. All the frameworks are numerically evaluated and the simulation results highlight their potential of learning site-specific codebooks that adapt to the deployment. Furthermore, a hardware proof-of-concept prototype based on mmWave phased arrays is built and used to evaluate the developed online beam learning solutions in realistic scenarios. The learned beam patterns, measured in an anechoic chamber, show the performance gains of the developed framework. All that highlights a promising ML-based beam/codebook optimization direction for practical and hardware-constrained mmWave and terahertz systems.
ContributorsZhang, Yu (Author) / Alkhateeb, Ahmed AA (Thesis advisor) / Tepedelenlioglu, Cihan CT (Committee member) / Bliss, Daniel DB (Committee member) / Dasarathy, Gautam GD (Committee member) / Arizona State University (Publisher)
Created2023
Description
Visual Odometry is an essential component in a Visual SLAM system. The aim of Visual SLAM (Simultaneous Localization and Mapping) is to create a 3D map of the world while simultaneously estimating the camera’s position in the created map. Visual odometry attempts to estimate the camera’s motion by analyzing the changes in images due to camera movement. This element is pivotal in various fields, including SLAM, 3D reconstruction, augmented reality, and more. A classic pipeline for visual odometry consists of camera calibration, feature detection, feature matching, triangulation, and local optimization (Bundle Adjustment). This geometry-based method has been broadly implemented in various SLAM algorithms. On the other hand, deep learning-based methods have dominated many computer vision tasks, but learning-based visual odometry is not on par with strong geometric methods. This is attributed to the insufficient diversity of data and scale ambiguity in triangulation. These issues can explicitly be addressed using Contrastive Learning. Contrastive learning utilizes data augmentation to improve learning performance, allowing it to derive benefits from sparsely diverse data available for visual odometry tasks through valid augmentations. Contrastive loss pulls feature vectors of negative pairs far apart while keeping positive pairs close together in latent space. This control over stretching in latent space can be highly useful for visual odometry problems.
ContributorsBhatt, Zeel Shaileshkumar (Author) / Yang, Yezhou (Thesis advisor) / Jayasurya, Suren (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2024
Description
In classification applications, such as medical disease diagnosis, the cost of one type of error (false negative) could greatly outweigh the other (false positive) enabling the need of asymmetric error control. Due to this unique nature of the problem, traditional machine learning techniques, even with much improved accuracy, may not be ideal as they do not provide a way to control the false negatives below a certain threshold. To address this need, a classification algorithm that can provide asymmetric error control is proposed. The theoretical foundation for this algorithm is based on Neyman-Pearson (NP) Lemma and it is complemented with sample splitting and order statistics to pick a threshold that enables an upper bound on the number of false negatives. Additionally, this classifier addresses the imbalance of the data, which is common in medical datasets, by using Hellinger distance as the splitting criterion. This eliminates the need of sampling methods, which add complexity and the need for parameter selection. This approach is used to create a novel tree-based classifier that enables asymmetric error control. Applications, such as prediction of the severity of cardiac arrhythmia, require classification over multiple classes. The NP oracle inequalities for binary classes are not immediately applicable for the multiclass NP classification, leading to a multi-step procedure proposed in this dissertation to extend the algorithm in the context of multiple classes. This classifier is used in predicting various forms of cardiac disease for both binary and multi-class classification problems with not only comparable accuracy metrics but also with full control over the number of false negatives. Moreover, this research allows us to pick the threshold for the classifier in a data adaptive way. This dissertation also shows that this methodology can be extended to non medical applications that require classification with asymmetric error control.
ContributorsBokhari, Wasif (Author) / Bansal, Ajay (Thesis advisor) / Zhang, Yu (Committee member) / Yang, Yezhou (Committee member) / Bahadur, Faisal (Committee member) / Arizona State University (Publisher)
Created2021
Description
Understanding the limits and capabilities of an AI system is essential for safe and effective usability of modern AI systems. In the query-based AI assessment paradigm, a personalized assessment module queries a black-box AI system on behalf of a user and returns a user-interpretable model of the AI system’s capabilities. This thesis develops this paradigm to learn interpretable action models of simulator-based agents. Two types of agents are considered: the first uses high-level actions where the user’s vocabulary captures the simulator state perfectly, and the second operates on low-level actions where the user’s vocabulary captures only an abstraction of the simulator state. Methods are developed to interface the assessment module with these agents. Empirical results show that this method is capable of learning interpretable models of agents operating in a range of domains.
ContributorsMarpally, Shashank Rao (Author) / Srivastava, Siddharth (Thesis advisor) / Zhang, Yu (Committee member) / Fainekos, Georgios E (Committee member) / Arizona State University (Publisher)
Created2021
Description
A critical challenge in the design of AI systems that operate with humans in the loop is to be able to model the intentions and capabilities of the humans, as well as their beliefs and expectations of the AI system itself. This allows the AI system to be "human- aware" -- i.e. the human task model enables it to envisage desired roles of the human in joint action, while the human mental model allows it to anticipate how its own actions are perceived from the point of view of the human. In my research, I explore how these concepts of human-awareness manifest themselves in the scope of planning or sequential decision making with humans in the loop. To this end, I will show (1) how the AI agent can leverage the human task model to generate symbiotic behavior; and (2) how the introduction of the human mental model in the deliberative process of the AI agent allows it to generate explanations for a plan or resort to explicable plans when explanations are not desired. The latter is in addition to traditional notions of human-aware planning which typically use the human task model alone and thus enables a new suite of capabilities of a human-aware AI agent. Finally, I will explore how the AI agent can leverage emerging mixed-reality interfaces to realize effective channels of communication with the human in the loop.
ContributorsChakraborti, Tathagata (Author) / Kambhampati, Subbarao (Thesis advisor) / Talamadupula, Kartik (Committee member) / Scheutz, Matthias (Committee member) / Ben Amor, Hani (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2018