Matching Items (113)
Description
It is difficult to imagine a society that does not utilize teams. At the same time, teams need to evolve to meet today’s challenges of the ever-increasing proliferation of data and complexity. It may be useful to add artificial intelligent (AI) agents to team up with humans. Then, as AI agents are integrated into the team, the first study asks what roles can AI agents take? The first study investigates this issue by asking whether an AI agent can take the role of a facilitator and in turn, improve planning outcomes by facilitating team processes. Results indicate that the human facilitator was significantly better than the AI facilitator at reducing cognitive biases such as groupthink, anchoring, and information pooling, as well as increasing decision quality and score. Additionally, participants viewed the AI facilitator negatively and ignored its inputs compared to the human facilitator. Yet, participants in the AI Facilitator condition performed significantly better than participants in the No Facilitator condition, illustrating that having an AI facilitator was better than having no facilitator at all. The second study explores whether artificial social intelligence (ASI) agents can take the role of advisors and subsequently improve team processes and mission outcome during a simulated search-and-rescue mission. The results of this study indicate that although ASI advisors can successfully advise teams, they also use a significantly greater number of taskwork interventions than teamwork interventions. Additionally, this study served to identify what the ASI advisors got right compared to the human advisor and vice versa. Implications and future directions are discussed.
ContributorsBuchanan, Verica (Author) / Cooke, Nancy J. (Thesis advisor) / Gutzwiller, Robert S. (Committee member) / Roscoe, Rod D. (Committee member) / Arizona State University (Publisher)
Created2023
Description
Recent breakthroughs in Artificial Intelligence (AI) have brought the dream of developing and deploying complex AI systems that can potentially transform everyday life closer to reality than ever before. However, the growing realization that there might soon be people from all walks of life using and working with these systems has also spurred a lot of interest in ensuring that AI systems can efficiently and effectively work and collaborate with their intended users. Chief among the efforts in this direction has been the pursuit of imbuing these agents with the ability to provide intuitive and useful explanations regarding their decisions and actions to end-users. In this dissertation, I will describe various works that I have done in the area of explaining sequential decision-making problems. Furthermore, I will frame the discussions of my work within a broader framework for understanding and analyzing explainable AI (XAI). My works herein tackle many of the core challenges related to explaining automated decisions to users including (1) techniques to address asymmetry in knowledge between the user and the system, (2) techniques to address asymmetry in inferential capabilities, and (3) techniques to address vocabulary mismatch.The dissertation will also describe the works I have done in generating interpretable behavior and policy summarization. I will conclude this dissertation, by using the framework of human-aware explanation as a lens to analyze and understand the current landscape of explainable planning.
ContributorsSreedharan, Sarath (Author) / Kambhampati, Subbarao (Thesis advisor) / Kim, Been (Committee member) / Smith, David E (Committee member) / Srivastava, Siddharth (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2022
Description
As intelligent agents become pervasive in our lives, they are expected to not only achieve tasks alone but also engage in tasks with humans in the loop. In such cases, the human naturally forms an understanding of the agent, which affects his perception of the agent’s behavior. However, such an understanding inevitably deviates from the ground truth due to reasons such as the human’s lack of understanding of the domain or misunderstanding of the agent’s capabilities. Such differences would result in an unmatched expectation of the agent’s behavior with the agent’s optimal behavior, thereby biasing the human’s assessment of the agent’s performance. In this dissertation, I focus on when these differences are due to a biased belief about domain dynamics. I especially investigate the impact of such a biased belief on the agent’s decision-making process in two different problem settings from a learning perspective. In the first setting, the agent is tasked to accomplish a task alone but must infer the human’s objectives from the human’s feedback on the agent’s behavior in the environment. In such a case, the human biased feedback could mislead the agent to learn a reward function that results in a sub-optimal and, potentially, undesired policy. In the second setting, the agent must accomplish a task with a human observer. Given that the agent’s optimal behavior may not match the human’s expectation due to the biased belief, the agent’s optimal behavior may be viewed as inexplicable, leading to degraded performance and loss of trust. Consequently, this dissertation proposes approaches that (1) endow the agent with the ability to be aware of the human’s biased belief while inferring the human’s objectives, thereby (2) neutralize the impact of the model differences in a reinforcement learning framework, and (3) behave explicably by reconciling the human’s expectation and optimality during decision-making.
ContributorsGong, Ze (Author) / Zhang, Yu (Thesis advisor) / Amor, Hani Ben (Committee member) / Kambhampati, Subbarao (Committee member) / Zhang, Wenlong (Committee member) / Arizona State University (Publisher)
Created2022
Description
The implementation of chatbots in customer service is widely prevalent in today’s world with insufficient research to appropriately refine all of their conversational abilities. Chatbots are favored for their ability to handle simple and typical requests made by users, but chatbots have proven to be prone to conversational breakdowns. The study researched how the use of repair strategies to combat conversational breakdowns in a simple versus complex task setting affected user experience. Thirty participants were collected and organized into six different groups in a two by three between subjects factorial design. Participants were assigned one of two tasks (simple or complex) and one of three repair strategies (repeat, confirmation, or options). A Wizard-of-Oz approach was used to simulate a chatbot that participants interacted with to complete a task in a hypothetical setting. Participants completed the task with this researcher-controlled chatbot as it intentionally failed the conversation multiple times, only to repair it with a repair strategy. Participants recorded their user experience regarding the chatbot afterwards. An Analysis of Covariance statistical test was run with task duration being a covariate variable. Findings indicate that the simple task difficulty was significant in improving the user experience that participants recorded whereas the particular repair strategy had no effect on the user experience. This indicates that simpler tasks lead to improved positive user experience and the more time that is spent on a task, the less positive the user experience. Overall, results associated with the effects of task difficulty and repair strategies on user experience were only partially consistent with previous literature.
ContributorsRios, Aaron (Author) / Cooke, Nancy J. (Thesis advisor) / Gutzwiller, Robert S. (Committee member) / Chiou, Erin K. (Committee member) / Arizona State University (Publisher)
Created2022
Description
With improvements in automation and system capabilities, human responsibilities in those advanced systems can get more complicated; greater situational awareness and performance may be asked of human agents in roles such as fail-safe operators. This phenomenon of automation improvements requiring more from humans in the loop, is connected to the well-known “paradox of automation”. Unfortunately, humans have cognitive limitations that can constrain a person's performance on a task. If one considers human cognitive limitations when designing solutions or policies for human agents, then better results are possible. The focus of this dissertation is on improving human involvement in planning and execution for Sequential Decision Making (SDM) problems. Existing work already considers incorporating humans into planning and execution in SDM, but with limited consideration for cognitive limitations. The work herein focuses on how to improve human involvement through problems in motion planning, planning interfaces, Markov Decision Processes (MDP), and human-team scheduling. This done by first discussing the human modeling assumptions currently used in the literature and their shortcomings. Then this dissertation tackles a set of problems by considering problem-specific human cognitive limitations --such as those associated with memory and inference-- as well as use lessons from fields such as cognitive ergonomics.
ContributorsGopalakrishnan, Sriram (Author) / Kambhampati, Subbarao (Thesis advisor) / Srivastava, Siddharth (Committee member) / Scheutz, Matthias (Committee member) / Zhang, Yu (Tony) (Committee member) / Arizona State University (Publisher)
Created2022
Description
This project is a video game implementation of the Filipino ruleset of Mahjong for the purpose of increasing awareness of the Mahjong game and Filipino culture. The game, titled Todas!, is built from scratch using various free resources and contains a Tutorial for teaching players the basics of the game and a Multiplayer mode that enables remote gameplay for up to four people.
ContributorsPimentel, Dion (Author) / Selgrad, Justin (Thesis director) / Kambhampati, Subbarao (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Dean, W.P. Carey School of Business (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-05
Description
This paper explores the inner workings of algorithms that computers may use to play Chess. First, we discuss the classical Alpha-Beta algorithm and several improvements, including Quiescence Search, Transposition Tables, and more. Next, we examine the state-of-the-art Monte Carlo Tree Search algorithm and relevant optimizations. After that, we consider a recent algorithm that transforms Alpha-Beta into a “Rollout” search, blending it with Monte Carlo Tree Search under the rollout paradigm. We then discuss our C++ Chess Engine, Homura, and explain its implementation of a hybrid algorithm combining Alpha-Beta with MCTS. Finally, we show that Homura can play master-level Chess at a strength currently exceeding that of our backtracking Alpha-Beta.
ContributorsMoore, Evan (Author) / Kobayashi, Yoshihiro (Thesis director) / Kambhampati, Subbarao (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-05
Description
Imitation learning is a promising methodology for teaching robots how to physically interact and collaborate with human partners. However, successful interaction requires complex coordination in time and space, i.e., knowing what to do as well as when to do it. This dissertation introduces Bayesian Interaction Primitives, a probabilistic imitation learning framework which establishes a conceptual and theoretical relationship between human-robot interaction (HRI) and simultaneous localization and mapping. In particular, it is established that HRI can be viewed through the lens of recursive filtering in time and space. In turn, this relationship allows one to leverage techniques from an existing, mature field and develop a powerful new formulation which enables multimodal spatiotemporal inference in collaborative settings involving two or more agents. Through the development of exact and approximate variations of this method, it is shown in this work that it is possible to learn complex real-world interactions in a wide variety of settings, including tasks such as handshaking, cooperative manipulation, catching, hugging, and more.
ContributorsCampbell, Joseph (Author) / Ben Amor, Heni (Thesis advisor) / Fainekos, Georgios (Thesis advisor) / Yamane, Katsu (Committee member) / Kambhampati, Subbarao (Committee member) / Arizona State University (Publisher)
Created2021
Description
In this work, the problem of multi-object tracking (MOT) is studied, particularly the challenges that arise from object occlusions. A solution based on a principled approximate dynamic programming approach called ADPTrack is presented. ADPTrack relies on existing MOT solutions and directly improves them. When matching tracks to objects at a particular frame, the proposed approach simulates executions of these existing solutions into future frames to obtain approximate track extensions, from which a comparison of past and future appearance feature information is leveraged to improve overall robustness to occlusion-based error. The proposed solution when applied to the renowned MOT17 dataset empirically demonstrates a 0.7% improvement in the association accuracy (IDF1 metric) over a state-of-the-art baseline that it builds upon while obtaining minor improvements with respect to all other metrics. Moreover, it is shown that this improvement is even more pronounced in scenarios where the camera maintains a fixed position. This implies that the proposed method is effective in addressing MOT issues pertaining to object occlusions.
ContributorsMusunuru, Pratyusha (Author) / Bertsekas, Dimitri (Thesis advisor) / Kambhampati, Subbarao (Thesis advisor) / Richa, Andrea (Committee member) / Arizona State University (Publisher)
Created2024
Description
In this work, I propose to bridge the gap between human users and adaptive control of robotic systems. The goal is to enable robots to consider user feedback and adjust their behaviors. A critical challenge with designing such systems is that users are often non-experts, with limited knowledge about the robot's hardware and dynamics. In the domain of human-robot interaction, there exist different modalities of conveying information regarding the desired behavior of the robot, most commonly used are demonstrations, and preferences. While it is challenging for non-experts to provide demonstrations of robot behavior, works that consider preferences expressed as trajectory rankings lead to users providing noisy and possibly conflicting information, leading to slow adaptation or system failures. The end user can be expected to be familiar with the dynamics and how they relate to their desired objectives through repeated interactions with the system. However, due to inadequate knowledge about the system dynamics, it is expected that the user would find it challenging to provide feedback on all dimension's of the system's behavior at all times. Thus, the key innovation of this work is to enable users to provide partial instead of completely specified preferences as with traditional methods that learn from user preferences. In particular, I consider partial preferences in the form of preferences over plant dynamic parameters, for which I propose Adaptive User Control (AUC) of robotic systems. I leverage the correlations between the observed and hidden parameter preferences to deal with incompleteness. I use a sparse Gaussian Process Latent Variable Model formulation to learn hidden variables that represent the relationships between the observed and hidden preferences over the system parameters. This model is trained using Stochastic Variational Inference with a distributed loss formulation. I evaluate AUC in a custom drone-swarm environment and several domains from DeepMind control suite. I compare AUC with the state-of-the-art preference-based reinforcement learning methods that are utilized with user preferences. Results show that AUC outperforms the baselines substantially in terms of sample and feedback complexity.
ContributorsBiswas, Upasana (Author) / Zhang, Yu (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Berman, Spring (Committee member) / Liu, Lantao (Committee member) / Arizona State University (Publisher)
Created2023