Title here
Summary here
Publications
2026
- OOPS: Out-of-Distribution Policy Summarization
IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2026Robots are increasingly deployed across diverse real-world domains. As they assume critical roles, it becomes essential for humans to understand how they sense, reason, and act to ensure safe and responsible use. Recent advances in Explainable AI (XAI) have sought to support this understanding through the explanation-by-example paradigm. Specifically, policy summarization has emerged as a promising solution, generating summaries composed of representative examples of robot behavior for users. However, existing methods select examples only from the robot's training set (i.e., in-distribution scenarios). As such, they fail to capture a variety of scenarios that the robot would encounter in practice but are absent from its training set (i.e., out-of-distribution scenarios). We argue that holistic explanations, containing both in-distribution and out-of-distribution examples, are crucial for fostering human understanding of robot behavior. To address this gap, we introduce Out-of-Distribution Policy Summarization (OOPS), an explanation-by-example approach designed to jointly teach users how robots perceive, reason, and act in novel scenarios.@inproceedings{huang2026oops, author = {Huang, Harrison and Rong, Yao and Qian, Peizhu and Unhelkar, Vaibhav}, title = {OOPS: Out-of-Distribution Policy Summarization}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = {2026} } - The NPSO Model Decreased Hospital-Acquired Infections and Sustained the Clinical Outcome
Sigma's 37th Intl. Nursing Research Congress, 2026@inproceedings{chen2026npso, author = {Chen, Hsin-Mei and Hamlin, Shannan and Unhelkar, Vaibhav and Kavraki, Lydia}, title = {The NPSO Model Decreased Hospital-Acquired Infections and Sustained the Clinical Outcome}, booktitle = {Sigma's 37th International Nursing Research Congress}, year = {2026} } - Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2026When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifications becomes critical for responsible AI deployment. Reward design provides a direct channel for such alignment by translating human expectations into reward functions that guide reinforcement learning (RL). However, existing methods are often too limited to capture nuanced human preferences that arise in long-horizon tasks. Hence, we introduce Hierarchical Reward Design from Language (HRDL): a problem formulation that extends classical reward design to encode richer behavioral specifications for hierarchical RL agents. We further propose Language to Hierarchical Rewards (L2HR) as a solution to HRDL. Experiments show that AI agents trained with rewards designed via L2HR not only complete tasks effectively but also better adhere to human specifications. Together, HRDL and L2HR advance the research on human-aligned AI agents.@inproceedings{qian2026hierarchical, author = {Qian, Zhiqin and Diaz, Ryan and Seo, Sangwon and Unhelkar, Vaibhav}, title = {Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, year = {2026} } - Sampling-Based Motion Planning with Scene Graphs Under Perception Constraints
IEEE Robotics and Automation Letters (RA-L), 2026It will be increasingly common for robots to operate in cluttered human-centered environments such as homes, workplaces, and hospitals, where the robot is often tasked to maintain perception constraints, such as monitoring people or multiple objects, for safety and reliability while executing its task. However, existing perception-aware approaches typically focus on low-degree-of-freedom (DoF) systems or only consider a single object in the context of high-DoF robots. This motivates us to consider the problem of perception-aware motion planning for high-DoF robots that accounts for multi-object monitoring constraints. We employ a scene graph representation of the environment, offering a great potential for incorporating long-horizon task and motion planning thanks to its rich semantic and spatial information. However, it does not capture perception-constrained information, such as the viewpoints the user prefers. To address these challenges, we propose MOPS-PRM, a roadmap-based motion planner, that integrates the perception cost of observing multiple objects or humans directly into motion planning for high-DoF robots. The perception cost is embedded to each object as part of a scene graph, and used to selectively sample configurations for roadmap construction, implicitly enforcing the perception constraints. Our method is extensively validated in both simulated and real-world experiments, achieving more than 36% improvement in the average number of detected objects and 17% better track rate against other perception-constrained baselines, with comparable planning times and path lengths.@article{meng2026sampling, author = {Meng, Qingxi and Flores, Emiliano and Duong, Thai and Unhelkar, Vaibhav and Kavraki, Lydia}, title = {Sampling-Based Motion Planning With Scene Graphs Under Perception Constraints}, journal = {IEEE Robotics and Automation Letters (RA-L)}, volume = {11}, number = {5}, pages = {5478--5485}, year = {2026}, doi = {10.1109/LRA.2026.3674013} }
2025
- Heart-to-Heart: Can Team Physiological Dynamics Showcase Task Interdependence in a Safety-Critical Environment?
69th Annual Meeting of the Human Factors and Ergonomics Society (HFES), 2025@inproceedings{khalid2025heart, author = {Khalid, Maha and Unhelkar, Vaibhav and Zenati, Marco and Salas, Eduardo}, title = {Heart-to-Heart: Can Team Physiological Dynamics Showcase Task Interdependence in a Safety-Critical Environment?}, booktitle = {69th Annual Meeting of the Human Factors and Ergonomics Society (HFES)}, year = {2025} } - ASTRID: A Robotic Tutor for Nurse Training to Reduce Healthcare-Associated Infections
Robotics: Science and Systems (RSS), 2025The central line dressing change is a life-critical procedure performed by nurses to provide patients with rapid infusion of fluids, such as blood and medications. Due to their complexity and the heavy workloads nurses face, dressing changes are prone to preventable errors that can result in central line-associated bloodstream infections (CLABSIs), leading to serious health complications or, in the worst cases, patient death. In the post-COVID-19 era, CLABSI rates have increased, partly due to the heightened nursing workload caused by shortages of both registered nurses and nurse educators. To address this challenge, healthcare facilities are seeking innovative nurse training solutions to complement expert nurse educators. In response, we present the design, development and evaluation of a robotic tutoring system, ASTRID: the Automated Sterile Technique Review and Instruction Device. ASTRID, which is the outcome of a two-year participatory design process, is designed to aid in the training of nursing skills essential for CLABSI prevention. First, we describe insights gained from interviews with nurse educators and nurses, which revealed the gaps of current training methods and requirements for new training tools. Based on these findings, we outline the development of our robotic tutor, which interacts with nursing students, providing real-time interventions and summary feedback to support skill acquisition. Finally, we present evaluations of the system's performance and perceived usefulness, conducted in a simulated clinical setting with nurse participants. These evaluations demonstrate the potential of our robotic tutor in nursing education. Our work highlights the importance of participatory design for robotics systems, and motivates new avenues for foundational research in robotics.@inproceedings{qian2025astrid, author = {Qian, Peizhu and Bajraktari, Filip and Quintero-Peña, Carlos and Meng, Qingxi and Hamlin, Shannan and Kavraki, Lydia and Unhelkar, Vaibhav}, title = {ASTRID: A Robotic Tutor for Nurse Training to Reduce Healthcare-Associated Infections}, booktitle = {Robotics: Science and Systems (RSS)}, year = {2025}, doi = {10.15607/RSS.2025.XXI.090} } - Evaluation of Large Language Models to Detect Team Mental Model Misalignments During Cardiac Surgery
Hamlyn Symp. on Medical Robotics, 2025@inproceedings{dias2025evaluation, author = {Dias, Roger and Unhelkar, Vaibhav and Shann, Kenneth and Weinberg, Allison and Rance, Geoffrey and Srey, Rithy and O'Gara, Paul and Shapeton, Alexander and Robertson, Jamie and Borges, Paulo and Verly, Robson and Mendu, Sanjana and Zenati, Marco}, title = {Evaluation of Large Language Models to Detect Team Mental Model Misalignments During Cardiac Surgery}, booktitle = {Hamlyn Symposium on Medical Robotics}, year = {2025} } - Socratic: Enhancing Human Teamwork via AI-enabled Coaching
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2025Coaches are vital for effective collaboration, but cost and resource constraints often limit their availability during real-world tasks. This limitation poses serious challenges in life-critical domains that rely on effective teamwork, such as healthcare and disaster response. To address this gap, we propose and realize an innovative application of AI: task-time team coaching. Specifically, we introduce Socratic, a novel AI system that complements human coaches by providing real-time guidance during task execution. Socratic monitors team behavior, detects misalignments in team members' shared understanding, and delivers automated interventions to improve team performance. We validated Socratic through two human subject experiments involving dyadic collaboration. The results demonstrate that the system significantly enhances team performance with minimal interventions. Participants also perceived Socratic as helpful and trustworthy, supporting its potential for adoption. Our findings also suggest promising directions both for AI research and its practical applications to enhance human teamwork.@inproceedings{seo2025socratic, author = {Seo, Sangwon and Han, Bing and Harari, Rayan and Dias, Roger and Zenati, Marco and Salas, Eduardo and Unhelkar, Vaibhav}, title = {Socratic: Enhancing Human Teamwork via AI-enabled Coaching}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, pages = {1876--1885}, year = {2025}, doi = {10.5555/3709347.3743824} } - Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2025Successful collaboration requires team members to stay aligned, especially in complex sequential tasks. Team members must dynamically coordinate which subtasks to perform and in what order. However, real-world constraints like partial observability and limited communication bandwidth often lead to suboptimal collaboration. Even among expert teams, the same task can be executed in multiple ways. To develop multi-agent systems and human-AI teams for such tasks, we are interested in data-driven learning of multimodal team behaviors. Multi-Agent Imitation Learning (MAIL) provides a promising framework for data-driven learning of team behavior from demonstrations, but existing methods struggle with heterogeneous demonstrations, as they assume that all demonstrations originate from a single team policy. Hence, in this work, we introduce DTIL: a hierarchical MAIL algorithm designed to learn multimodal team behaviors in complex sequential tasks. DTIL represents each team member with a hierarchical policy and learns these policies from heterogeneous team demonstrations in a factored manner. By employing a distribution-matching approach, DTIL mitigates compounding errors and scales effectively to long horizons and continuous state representations. Experimental results show that DTIL outperforms MAIL baselines and accurately models team behavior across a variety of collaborative scenarios.@inproceedings{seo2025hierarchical, author = {Seo, Sangwon and Unhelkar, Vaibhav}, title = {Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, pages = {1886--1894}, year = {2025}, doi = {10.5555/3709347.3743825} } - Interactive AI Tutors for Training the Workforce of the Future
Ph.D. Thesis, Rice University, 2025The need to train new workers effectively and upskill the existing workforce is a challenge faced by almost every industry across the globe. The healthcare industry, in particular, is confronting a crisis. The World Health Organization (WHO) projects a shortage of 10 million healthcare workers by 2030. However, according to the Future of Jobs Report by the World Economic Forum, only half of the workers have access to training and learning opportunities. To sustain a resilient workforce and to protect the health of the world's population, my thesis looks at using AI and robots to accelerate human learners' acquisition of workforce skills. Specifically, I develop novel Explainable AI (XAI) algorithms to automate training to enable workers to collaborate with autonomous robots - a trend that is fast-growing. I also use statistical models to model human learner cognitive processes to create Human-Robot Interaction (HRI) systems to generate effective instructions tailored to individual learners. In addition to driving technical advances, my research is having a positive societal impact. I collaborate with Houston Methodist Hospital to create a first-of-its-kind robotic tutor for clinical nursing education to reduce healthcare-associated infections.@phdthesis{qian2025thesis, author = {Qian, Peizhu}, title = {Interactive AI Tutors for Training the Workforce of the Future}, school = {Rice University}, year = {2025} } - Personalized Explanations of Robot Behavior for Human Users
M.S. Thesis, Rice University, 2025AI and robotic agents are becoming increasingly prevalent in sectors such as transportation, manufacturing, and disaster response. As these robots are integrated into existing workflows, it is important for their users to understand and anticipate their actions to ensure efficient human-robot collaboration. Most notably, explainable AI (XAI) has emerged as a solution for making robot behavior more transparent. However, a major challenge remains: each user has their own preconceptions of the robot, meaning that a single explanation method may not be effective for everyone. This thesis explores the role of personalized explanations in improving human users' ability to understand robot behavior. We design an algorithm, PPS, to model a user's knowledge about a robot to select informative explanations tailored to that user. We also introduce STOREE as a paradigm for users to personalize their lesson modality. Through our experiments, we find evidence that personalization increases user knowledge of robot behavior.@mastersthesis{huang2025thesis, author = {Huang, Harrison}, title = {Personalized Explanations of Robot Behavior for Human Users}, school = {Rice University}, year = {2025} } - AI-Assisted Coordination of Human Teams in Situated Tasks
AAAI Spring Symp. on Current and Future Varieties of Human-AI Collaboration, 2025Effective teamwork is crucial in high-stakes domains, yet it is highly challenging to achieve. Team members often must make decisions with limited information and under constraints on communication and time. Recognizing both the value of human coaches as well as the challenges of integrating them into practical settings, we envision AI-based coaching agents to enhance team coordination and performance. This extended abstract introduces AI Coaches and Coordinators, highlights key research questions from both human and AI perspectives that must be addressed to realize them, and summarizes our recent work in developing algorithms and systems to bring AI Coaches and Coordinators to fruition.@inproceedings{seo2025ai, author = {Seo, Sangwon and Qian, Zhiqin and Unhelkar, Vaibhav}, title = {AI-Assisted Coordination of Human Teams in Situated Tasks}, booktitle = {AAAI Spring Symposium Series}, pages = {104--106}, year = {2025}, doi = {10.1609/aaaiss.v5i1.35570} } - The Need for Human-AI Collaborative Methods for Conducting Audits of Machine Learning Models
AAAI Spring Symp. on Current and Future Varieties of Human-AI Collaboration, 2025Conducting application audits of ML models is essential for ensuring their safe and responsible deployment, particularly in high-stakes applications. However, the auditing of ML models deployed in domain-specific applications remains largely a manual process, relying on domain experts to identify model errors. The manual nature of the process limits scalability of audits and hinders the discovery of problematic model behaviors. We posit that a human-AI collaborative paradigm is key to conducting effective application audits. In this abstract, we propose a research agenda to develop Human-AI collaborative methods for conducting application audits of ML models.@inproceedings{rong2025need, author = {Rong, Yao and Unhelkar, Vaibhav}, title = {The Need for Human-AI Collaborative Methods for Conducting Audits of Machine Learning Models}, booktitle = {AAAI Spring Symposium Series}, pages = {95--97}, year = {2025}, doi = {10.1609/aaaiss.v5i1.35567} } - Spatiotemporally Controlled Soft Robotics with Optically Responsive Liquid Crystal Elastomers
Advanced Intelligent Systems (Wiley), 2025Light-responsive materials enable the development of soft robots that are controlled remotely in 3D space and time without the need for cumbersome wires, onboard batteries, or altering the local environment. Azobenzene liquid crystal polymer networks are one such material that can move and deform in response to light actuation. Previous works have demonstrated azo-based soft robotic grippers and transporters that are remotely powered by light. However, highly adaptive, automated spatiotemporal optical control over these materials has not yet been realized. Herein, a system for an azobenzene liquid crystal elastomer soft robotic arm is created by dynamically patterning light for independently maneuverable joints. The nonlinear material response to optical actuation is characterized, and the broad actuation space is explored with diverse arm configurations. A neural network is trained on the arm configurations and corresponding laser pattern to automate the pattern generation for a desired configuration. Finally, the azobenzene liquid crystal elastomer arm demonstrates complex targeted motion, marking an important step toward optically actuated soft robotics with applications ranging from optomechanics to biomedical tools.@article{blackert2025spatio, author = {Blackert, Elizabeth and Scaccia, Phoebe and Barnes, Morgan and Pathiranage, Taniya and Verduzco, Rafael and Unhelkar, Vaibhav and Zhu, Hanyu}, title = {Spatiotemporally Controlled Soft Robotics with Optically Responsive Liquid Crystal Elastomers}, journal = {Advanced Intelligent Systems}, volume = {7}, number = {6}, year = {2025}, doi = {10.1002/aisy.202500045} }
2024
- PPS: Personalized Policy Summarization for Explaining Sequential Behavior of Autonomous Agents
AAAI/ACM Conf. on Artificial Intelligence, Ethics, and Society (AIES), 2024AI-enabled agents designed to assist humans are gaining traction in a variety of domains such as healthcare and disaster response. It is evident that, as we move forward, these agents will play increasingly vital roles in our lives. To realize this future successfully and mitigate its unintended consequences, it is imperative that humans have a clear understanding of the agents that they work with. Policy summarization methods help facilitate this understanding by showcasing key examples of agent behaviors to their human users. Yet, existing methods produce "one-size-fits-all" summaries for a generic audience ahead of time. Drawing inspiration from research in pedagogy, we posit that personalized policy summaries can more effectively enhance user understanding. To evaluate this hypothesis, this paper presents and benchmarks a novel technique: Personalized Policy Summarization (PPS). PPS discerns a user's mental model of the agent through a series of algorithmically generated questions and crafts customized policy summaries to enhance user understanding. Unlike existing methods, PPS actively engages with users to gauge their comprehension of the agent behavior, subsequently generating tailored explanations on the fly. Through a combination of numerical and human subject experiments, we confirm the utility of this personalized approach to explainable AI.@inproceedings{qian2024pps, author = {Qian, Peizhu and Huang, Harrison and Unhelkar, Vaibhav}, title = {PPS: Personalized Policy Summarization for Explaining Sequential Behavior of Autonomous Agents}, booktitle = {AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES)}, pages = {1167--1179}, year = {2024}, doi = {10.1609/aies.v7i1.31714} } - Perception-aware Planning for Robotics: Challenges and Opportunities
40th Anniversary of the IEEE Conf. on Robotics and Automation (ICRA40), 2024@inproceedings{meng2024perception, author = {Meng, Qingxi and Quintero-Peña, Carlos and Kingston, Zachary and Unhelkar, Vaibhav and Kavraki, Lydia}, title = {Perception-aware Planning for Robotics: Challenges and Opportunities}, booktitle = {40th Anniversary of the IEEE Conference on Robotics and Automation (ICRA40)}, year = {2024} } - RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models
arXiv preprint (arXiv:2409.12294), 2024Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as LLM-based agents), when paired with appropriate critics, have demonstrated potential in solving complex, long-horizon tasks with relatively few interactions. However, most existing LLM-based agents lack the ability to retain and learn from past interactions - an essential trait of learning-based robotic systems. We propose RAG-Modulo, a framework that enhances LLM-based agents with a memory of past interactions and incorporates critics to evaluate the agents' decisions. The memory component allows the agent to automatically retrieve and incorporate relevant past experiences as in-context examples, providing context-aware feedback for more informed decision-making. Further by updating its memory, the agent improves its performance over time, thereby exhibiting learning. Through experiments in the challenging BabyAI and AlfWorld domains, we demonstrate significant improvements in task success rates and efficiency, showing that the proposed RAG-Modulo framework outperforms state-of-the-art baselines.@article{jain2024rag, author = {Jain, Abhinav and Jermaine, Chris and Unhelkar, Vaibhav}, title = {RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models}, journal = {arXiv preprint arXiv:2409.12294}, year = {2024} } - Misalignment of Cognitive Processes within Cardiac Surgery Teams
Hamlyn Symp. on Medical Robotics, 2024@inproceedings{harari2024misalignment, author = {Harari, Rayan and Dias, Roger and Yule, Steven and Salas, Eduardo and Unhelkar, Vaibhav and Chaspari, Theodora and Zenati, Marco}, title = {Misalignment of Cognitive Processes within Cardiac Surgery Teams}, booktitle = {Hamlyn Symposium on Medical Robotics}, year = {2024} } - Monitoring Constraints for Robotic Tutors in Nurse Education: A Motion Planning Perspective
ICRA 2024 Workshop on Nursing Robotics, 2024@inproceedings{meng2024monitoring, author = {Meng, Qingxi and Quintero-Peña, Carlos and Kingston, Zachary and Unhelkar, Vaibhav and Kavraki, Lydia}, title = {Monitoring Constraints for Robotic Tutors in Nurse Education: A Motion Planning Perspective}, booktitle = {ICRA 2024 Workshop on Nursing Robotics}, year = {2024} } - IDIL: Imitation Learning of Intent-Driven Expert Behavior
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2024When faced with accomplishing a task, human experts exhibit intentional behavior. Their unique intents shape their plans and decisions, resulting in experts demonstrating diverse behaviors to accomplish the same task. Due to the uncertainties encountered in the real world and their bounded rationality, experts sometimes adjust their intents, which in turn influences their behaviors during task execution. This paper introduces IDIL, a novel imitation learning algorithm to mimic these diverse intent-driven behaviors of experts. Iteratively, our approach estimates expert intent from heterogeneous demonstrations and then uses it to learn an intent-aware model of their behavior. Unlike contemporary approaches, IDIL is capable of addressing sequential tasks with high-dimensional state representations, while sidestepping the complexities and drawbacks associated with adversarial training (a mainstay of related techniques). Our empirical results suggest that the models generated by IDIL either match or surpass those produced by recent imitation learning benchmarks in metrics of task performance. Moreover, as it creates a generative model, IDIL demonstrates superior performance in intent inference metrics, crucial for human-agent interactions, and aptly captures a broad spectrum of expert behaviors.@inproceedings{seo2024idil, author = {Seo, Sangwon and Unhelkar, Vaibhav}, title = {IDIL: Imitation Learning of Intent-Driven Expert Behavior}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, pages = {1673--1682}, year = {2024}, doi = {10.5555/3635637.3663028} } - Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge. In this paper, we explore how human-computer interaction (HCI) and AI researchers conduct user studies in XAI applications based on a systematic literature review. After identifying and thoroughly analyzing 97 core papers with human-based XAI evaluations over the past five years, we categorize them along the measured characteristics of explanatory methods, namely trust, understanding, usability, and human-AI collaboration performance. Our research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems, than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences. Based on a comprehensive discussion of best practices, i.e., common models, design choices, and measures in user studies, we propose practical guidelines on designing and conducting user studies for XAI researchers and practitioners. Lastly, this survey also highlights several open research directions, particularly linking psychological science and human-centered XAI.@article{rong2023towards, author = {Rong, Yao and Leemann, Tobias and Nguyen, Thai-trang and Fiedler, Lisa and Qian, Peizhu and Unhelkar, Vaibhav and Seidel, Tina and Kasneci, Gjergji and Kasneci, Enkelejda}, title = {Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}, volume = {46}, number = {4}, pages = {2104--2122}, year = {2024}, doi = {10.1109/TPAMI.2023.3331846} } - Measuring Variations in Workload during Human-Robot Collaboration through Automated After-Action Reviews
Companion of the ACM/IEEE Intl. Conf. on Human-Robot Interaction (HRI), 2024Human collaborator's workload plays a central role in human-robot collaboration. Algorithms designed to minimize cognitive workload enhance fluent human-robot teamwork. Time series data of workload is vital for both designing and assessing these algorithms. However, accurately quantifying and measuring cognitive workload, particularly at high temporal resolution, poses a substantial challenge. Towards addressing this challenge, we explore the potential of after-action reviews (AARs) as a tool for gauging workload during human-robot collaboration. First, through a case study, we present and demonstrate AutoAAR for measuring human workload post-task at a high temporal resolution. Second, through a user study, we quantify the validity and utility of measurements derived using AutoAAR for human-robot teamwork. The paper concludes with guidelines and future directions to extend this method to measure other internal states, such as trust and intent.@inproceedings{qian2024measuring, author = {Qian, Zhiqin and Orlov-Savko, Liubove and Gremillion, Gregory and Neubauer, Catherine and Unhelkar, Vaibhav}, title = {Measuring Variations in Workload during Human-Robot Collaboration through Automated After-Action Reviews}, booktitle = {Companion of the ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, pages = {852--856}, year = {2024}, doi = {10.1145/3610978.3640677} } - Interactively Explaining Robot Policies to Humans in Integrated Virtual and Physical Training Environments
Companion of the ACM/IEEE Intl. Conf. on Human-Robot Interaction (HRI), 2024Policy summarization is a computational paradigm for explaining the behavior and decision-making processes of autonomous robots to humans. It summarizes robot policies via exemplary demonstrations, aiming to improve human understanding of robotic behaviors. This understanding is crucial, especially since users often make critical decisions about robot deployment in the real world. Previous research in policy summarization has predominantly focused on simulated robots and environments, overlooking its application to physically embodied robots. Our work fills this gap by combining current policy summarization methods with a novel, interactive user interface that involves physical interaction with robots. We conduct human-subject experiments to assess our explanation system, focusing on the impact of different explanation modalities in policy summarization. Our findings underscore the unique advantages of combining virtual and physical training environments to effectively communicate robot behavior to human users.@inproceedings{qian2024interactively, author = {Qian, Peizhu and Unhelkar, Vaibhav}, title = {Interactively Explaining Robot Policies to Humans in Integrated Virtual and Physical Training Environments}, booktitle = {Companion of the ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, pages = {847--851}, year = {2024}, doi = {10.1145/3610978.3640656} } - RW4T Dataset: Data of Human-Robot Behavior and Cognitive States in Simulated Disaster Response Tasks
ACM/IEEE Intl. Conf. on Human-Robot Interaction (HRI), 2024To forge effective collaborations with humans, robots require the capacity to understand and predict the behaviors of their human counterparts. There is a growing body of computational research on human modeling for human-robot interaction (HRI). However, a key bottleneck in conducting this research is the relative lack of data of human internal states - like intent, workload, and trust - which undeniably affect human behavior. Despite their significance, these states are elusive to measure, making the assembly of datasets a challenge and hindering the progression of human modeling techniques. To help address this, we first introduce Rescue World for Teams (RW4T): a configurable testbed to simulate disaster response scenarios requiring human-robot collaboration. Next, using RW4T, we curate a multimodal dataset of human-robot behavior and internal states in dyadic human-robot collaboration. This RW4T dataset includes state, action and reward sequences, and all the necessary data to replay a visual task execution. It further contains psychophysiological metrics like heart rate and pupillometry, complemented by self-reported cognitive state measures. With data from 20 participants, each undertaking five human-robot collaborative tasks, this dataset accompanied with the simulator can serve as a valuable benchmark for human behavior modeling.@inproceedings{orlov2024rw4t, author = {Orlov-Savko, Liubove and Qian, Zhiqin and Gremillion, Gregory and Neubauer, Catherine and Canady, Jonroy and Unhelkar, Vaibhav}, title = {RW4T Dataset: Data of Human-Robot Behavior and Cognitive States in Simulated Disaster Response Tasks}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, pages = {924--928}, year = {2024}, doi = {10.1145/3610977.3637481} } - I-CEE: Tailoring Explanations of Image Classification Models to User Expertise
AAAI Conf. on Artificial Intelligence, 2024Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to generate these explanations. Yet, there is relatively little emphasis on the user (the explainee) in this growing body of work and most XAI techniques generate "one-size-fits-all" explanations. To bridge this gap and achieve a step closer towards human-centered XAI, we present I-CEE, a framework that provides Image Classification Explanations tailored to User Expertise. Informed by existing work, I-CEE explains the decisions of image classification models by providing the user with an informative subset of training data (i.e., example images), corresponding local explanations, and model decisions. However, unlike prior work, I-CEE models the informativeness of the example images to depend on user expertise, resulting in different examples for different users. We posit that by tailoring the example set to user expertise, I-CEE can better facilitate users' understanding and simulatability of the model. To evaluate our approach, we conduct detailed experiments in both simulation and with human participants (N = 100) on multiple datasets. Experiments with simulated users show that I-CEE improves users' ability to accurately predict the model's decisions (simulatability) compared to baselines, providing promising preliminary results. Experiments with human participants demonstrate that our method significantly improves user simulatability accuracy, highlighting the importance of human-centered XAI.@inproceedings{rong2024icee, author = {Rong, Yao and Qian, Peizhu and Unhelkar, Vaibhav and Kasneci, Enkelejda}, title = {I-CEE: Tailoring Explanations of Image Classification Models to User Expertise}, booktitle = {AAAI Conference on Artificial Intelligence}, pages = {21545--21553}, year = {2024}, doi = {10.1609/aaai.v38i19.30152} } - GO-DICE: Goal-conditioned Option-aware Offline Imitation Learning via Stationary Distribution Correction Estimation
AAAI Conf. on Artificial Intelligence, 2024Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations, without any additional interaction with the environment. Despite significant advances in offline IL, existing techniques find it challenging to learn policies for long-horizon tasks and require significant re-training when task specifications change. Towards addressing these limitations, we present GO-DICE an offline IL technique for goal-conditioned long-horizon sequential tasks. GO-DICE discerns a hierarchy of sub-tasks from demonstrations and uses these to learn separate policies for sub-task transitions and action execution, respectively; this hierarchical policy learning facilitates long-horizon reasoning. Inspired by the expansive DICE-family of techniques, policy learning at both the levels transpires within the space of stationary distributions. Further, both policies are learnt with goal conditioning to minimize need for retraining when task goals change. Experimental results substantiate that GO-DICE outperforms recent baselines, as evidenced by a marked improvement in the completion rate of increasingly challenging pick-and-place Mujoco robotic tasks. GO-DICE is also capable of leveraging imperfect demonstration and partial task segmentation when available, both of which boost task performance relative to learning from expert demonstrations alone.@inproceedings{jain2024godice, author = {Jain, Abhinav and Unhelkar, Vaibhav}, title = {GO-DICE: Goal-conditioned Option-aware Offline Imitation Learning via Stationary Distribution Correction Estimation}, booktitle = {AAAI Conference on Artificial Intelligence}, pages = {12763--12772}, year = {2024}, doi = {10.1609/aaai.v38i11.29172} } - A Novel Multimodal Perspective on Objective Assessment of Non-Technical Skills in Cardiac Surgery
Academic Surgical Congress (ASC), 2024@inproceedings{ebnali2024novel, author = {Ebnali, Mahdi and Kennedy-Metz, Lauren and Varni, Giovanna and Unhelkar, Vaibhav and Salas, Eduardo and Dias, Roger and Zenati, Marco}, title = {A Novel Multimodal Perspective on Objective Assessment of Non-Technical Skills in Cardiac Surgery}, booktitle = {Academic Surgical Congress (ASC)}, year = {2024} }
2023
- Using Deep Learning to Assess Teamwork during Cardiac Surgery
Clinical Translation of Medical Image Computing and Computer Assisted Interventions (CLINICCAI), 2023@inproceedings{ebnali2023using, author = {Ebnali, Mahdi and Zenati, Marco and Yule, Steven and Unhelkar, Vaibhav and Dias, Roger}, title = {Using Deep Learning to Assess Teamwork during Cardiac Surgery}, booktitle = {Clinical Translation of Medical Image Computing and Computer Assisted Interventions (CLINICCAI)}, year = {2023} } - Opportunities and Challenges of Real-Time Measurement of Team Performance in the Cardiac Operating Room
67th Annual Meeting of the Human Factors and Ergonomics Society (HFES), 2023@inproceedings{khalid2023opportunities, author = {Khalid, Maha and Seo, Sangwon and Zenati, Marco and Ebnali, Mahdi and Kennedy-Metz, Lauren and Dias, Roger and Unhelkar, Vaibhav and Salas, Eduardo}, title = {Opportunities and Challenges of Real-Time Measurement of Team Performance in the Cardiac Operating Room}, booktitle = {67th Annual Meeting of the Human Factors and Ergonomics Society (HFES)}, year = {2023} } - Robotic Tutors for Nurse Training: Opportunities for HRI Researchers
IEEE Intl. Symp. on Robot and Human Interactive Communication (RO-MAN), 2023An ongoing nurse labor shortage has the potential to impact patient care well-being in the entire healthcare system. Moreover, more complex and sophisticated nursing care is required today for patients in hospitals forcing hospital-based nurses to carry out frequent training and assessment procedures, both to onboard new nurses and to validate skills of existing staff that guarantees best practices and safety. In this paper we recognize an opportunity for the development and integration of intelligent robot tutoring technology into nursing education to tackle the growing challenges of nurse deficit. To this end, we identify specific research problems in the area of human-robot interaction that will need to be addressed to enable robot tutors for nurse training.@inproceedings{quintero2023robotic, author = {Quintero-Peña, Carlos and Qian, Peizhu and Fontenot, Nicole and Chen, Hsin-Mei and Hamlin, Shannan and Kavraki, Lydia and Unhelkar, Vaibhav}, title = {Robotic Tutors for Nurse Training: Opportunities for HRI Researchers}, booktitle = {IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)}, pages = {220--225}, year = {2023}, doi = {10.1109/RO-MAN57019.2023.10309573} } - Automated Task-Time Interventions to Improve Teamwork using Imitation Learning
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2023Effective human-human and human-autonomy teamwork is critical but often challenging to perfect. The challenge is particularly relevant in time-critical domains, such as healthcare and disaster response, where the time pressures can make coordination increasingly difficult to achieve and the consequences of imperfect coordination can be severe. To improve teamwork in these and other domains, we present TIC: an automated intervention approach for improving coordination between team members. Using BTIL, a multi-agent imitation learning algorithm, our approach first learns a generative model of team behavior from past task execution data. Next, it utilizes the learned generative model and team's task objective (shared reward) to algorithmically generate execution-time interventions. We evaluate our approach in synthetic multi-agent teaming scenarios, where team members make decentralized decisions without full observability of the environment. The experiments demonstrate that the automated interventions can successfully improve team performance and shed light on the design of autonomous agents for improving teamwork.@inproceedings{seo2023automated, author = {Seo, Sangwon and Han, Bing and Unhelkar, Vaibhav}, title = {Automated Task-Time Interventions to Improve Teamwork using Imitation Learning}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, pages = {335--344}, year = {2023}, doi = {10.5555/3545946.3598655} }
2022
- Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations
Intl. Joint Conferences on Artificial Intelligence (IJCAI), 2022We present Bayesian Team Imitation Learner (BTIL), an imitation learning algorithm to model the behavior of teams performing sequential tasks in Markovian domains. In contrast to existing multi-agent imitation learning techniques, BTIL explicitly models and infers the time-varying mental states of team members, thereby enabling learning of decentralized team policies from demonstrations of suboptimal teamwork. Further, to allow for sample- and label-efficient policy learning from small datasets, BTIL employs a Bayesian perspective and is capable of learning from semi-supervised demonstrations. We demonstrate and benchmark the performance of BTIL on synthetic multi-agent tasks as well as a novel dataset of human-agent teamwork. Our experiments show that BTIL can successfully learn team policies from demonstrations despite the influence of team members' (time-varying and potentially misaligned) mental states on their behavior.@inproceedings{seo2022semi, author = {Seo, Sangwon and Unhelkar, Vaibhav}, title = {Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations}, booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)}, pages = {2492--2500}, year = {2022}, doi = {10.24963/ijcai.2022/346} } - Factorial Agent Markov Model: Modeling Other Agents' Behavior in presence of Dynamic Latent Decision Factors
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2022Autonomous agents operating in the real world often need to interact with other agents to accomplish their tasks. For such agents, the ability to model behavior of other agents - both human and artificial - without complete knowledge of their decision factors is essential. Towards realizing this ability, we present Factorial Agent Markov Model (FAMM), a model to represent behavior of other agents performing sequential tasks. In contrast with most existing models, FAMM allows for behavior of other agents to depend on multiple, time-varying latent decision factors and does not assume rationality. To enable learning of FAMM parameters by observing behavior of other agents, we provide a set of variational inference algorithms for the unsupervised, semi-supervised, and supervised settings. These Bayesian learning algorithms for the FAMM enable agents to model other agents using execution traces and domain-specific priors. We demonstrate the utility of FAMM and corresponding learning algorithms using three synthetic domains and benchmark them against existing algorithms for modeling agent behavior. Our numerical experiments demonstrate that, despite the presence of multiple and time-varying latent states, our approach is capable of learning predictive models of other agents with semi-supervision.@inproceedings{orlov2022factorial, author = {Orlov-Savko, Liubove and Jain, Abhinav and Gremillion, Gregory and Neubauer, Catherine and Canady, Jonroy and Unhelkar, Vaibhav}, title = {Factorial Agent Markov Model: Modeling Other Agents' Behavior in presence of Dynamic Latent Decision Factors}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, pages = {982--1000}, year = {2022}, doi = {10.5555/3535850.3535960} } - Evaluating the Role of Interactivity on Improving Transparency in Autonomous Agents
Intl. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 2022Autonomous agents are increasingly being deployed amongst human end-users. Yet, human users often have little knowledge of how these agents work or what they will do next. This lack of transparency has already resulted in unintended consequences during AI use: a concerning trend which is projected to increase with the proliferation of autonomous agents. To curb this trend and ensure safe use of AI, assisting users in establishing an accurate understanding of agents that they work with is essential. In this work, we present AI teacher, a user-centered Explainable AI framework to address this need for autonomous agents that follow a Markovian policy. Our framework first computes salient instructions of agent behavior by estimating a user's mental model and utilizing algorithms for sequential decision-making. Next, in contrast to existing solutions, these instructions are presented interactively to the end-users, thereby enabling a personalized approach to improving AI transparency. We evaluate our framework, with emphasis on its interactive features, through experiments with human participants. The experiment results suggest that, relative to non-interactive approaches, interactive teaching can both reduce the amount of time it takes for humans to create accurate mental models of these agents and is subjectively preferred by human users.@inproceedings{qian2022evaluating, author = {Qian, Peizhu and Unhelkar, Vaibhav}, title = {Evaluating the Role of Interactivity on Improving Transparency in Autonomous Agents}, booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)}, pages = {1083--1091}, year = {2022}, doi = {10.5555/3535850.3535971} } - Human-Guided Motion Planning in Partially Observable Environments
Intl. Conf. on Robotics and Automation (ICRA), 2022Motion planning is a core problem in robotics, with a range of existing methods aimed to address its diverse set of challenges. However, most existing methods rely on complete knowledge of the robot environment; an assumption that seldom holds true due to inherent limitations of robot perception. To enable tractable motion planning for high-DOF robots under partial observability, we introduce BLIND, an algorithm that leverages human guidance. BLIND utilizes inverse reinforcement learning to derive motion-level guidance from human critiques. The algorithm overcomes the computational challenge of reward learning for high-DOF robots by projecting the robot's continuous configuration space to a motion-planner-guided discrete task model. The learned reward is in turn used as guidance to generate robot motion using a novel motion planner. We demonstrate BLIND using the Fetch robot and perform two simulation experiments with partial observability. Our experiments demonstrate that, despite the challenge of partial observability and high dimensionality, BLIND is capable of generating safe robot motion and outperforms baselines on metrics of teaching efficiency, success rate, and path quality.@inproceedings{quintero2022human, author = {Quintero-Peña, Carlos and Chamzas, Constantinos and Sun, Zhanyi and Unhelkar, Vaibhav and Kavraki, Lydia}, title = {Human-Guided Motion Planning in Partially Observable Environments}, booktitle = {International Conference on Robotics and Automation (ICRA)}, pages = {7226--7232}, year = {2022}, doi = {10.1109/ICRA46639.2022.9811893} }
2021
- Learning Dense Rewards for Contact-Rich Manipulation Tasks
Intl. Conf. on Robotics and Automation (ICRA), 2021Rewards play a crucial role in reinforcement learning. To arrive at the desired policy, the design of a suitable reward function often requires significant domain expertise as well as trial-and-error. Here, we aim to minimize the effort involved in designing reward functions for contact-rich manipulation tasks. In particular, we provide an approach capable of extracting dense reward functions algorithmically from robots' high-dimensional observations, such as images and tactile feedback. In contrast to state-of-the-art high-dimensional reward learning methodologies, our approach does not leverage adversarial training, and is thus less prone to the associated training instabilities. Instead, our approach learns rewards by estimating task progress in a self-supervised manner. We demonstrate the effectiveness and efficiency of our approach on two contact-rich manipulation tasks, namely, peg-in-hole and USB insertion. The experimental results indicate that the policies trained with the learned reward function achieves better performance and faster convergence compared to the baselines.@inproceedings{wu2021learning, author = {Wu, Zheng and Lian, Wenzhao and Unhelkar, Vaibhav and Tomizuka, Masayoshi and Schaal, Stefan}, title = {Learning Dense Rewards for Contact-Rich Manipulation Tasks}, booktitle = {International Conference on Robotics and Automation (ICRA)}, pages = {6214--6221}, year = {2021}, doi = {10.1109/ICRA48506.2021.9561891} } - Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare
Intl. Conf. on Cognitive and Computational Aspects of Situation Management (CogSIMA), 2021Shared mental models are critical to team success; however, in practice, team members may have misaligned models due to a variety of factors. In safety-critical domains (e.g., aviation, healthcare), lack of shared mental models can lead to preventable errors and harm. Towards the goal of mitigating such preventable errors, here, we present a Bayesian approach to infer misalignment in team members' mental models during complex healthcare task execution. As an exemplary application, we demonstrate our approach using two simulated team-based scenarios, derived from actual teamwork in cardiac surgery. In these simulated experiments, our approach inferred model misalignment with over 75% recall, thereby providing a building block for enabling computer-assisted interventions to augment human cognition in the operating room and improve teamwork.@inproceedings{seo2021aicoach, author = {Seo, Sangwon and Kennedy-Metz, Lauren and Zenati, Marco and Shah, Julie and Dias, Roger and Unhelkar, Vaibhav}, title = {Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare}, booktitle = {International Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)}, pages = {39--44}, year = {2021}, doi = {10.1109/CogSIMA51574.2021.9475925} }
Prior Publications
Note:
The following research was conducted at the Interactive Robotics Group, MIT before PI Vaibhav Unhelkar founded the Human-AI Teaming Lab at Rice University.
- Effective Information Sharing for Human-Robot Collaboration
Ph.D. Thesis, Massachusetts Institute of Technology, 2020@phdthesis{unhelkar2020effective, author = {Unhelkar, Vaibhav V.}, title = {Effective Information Sharing for Human-Robot Collaboration}, school = {Massachusetts Institute of Technology}, year = {2020} } - Decision-Making for Bidirectional Communication in Sequential Human-Robot Collaborative Tasks
ACM/IEEE Intl. Conf. on Human-Robot Interaction (HRI), 2020@inproceedings{unhelkar2020decision, author = {Unhelkar, Vaibhav and Li, Shen and Shah, Julie}, title = {Decision-Making for Bidirectional Communication in Sequential Human-Robot Collaborative Tasks}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, year = {2020} } - Learning Models of Sequential Decision-Making with Partial Specification of Agent Behavior
AAAI Conf. on Artificial Intelligence (AAAI), 2019@inproceedings{unhelkar2019learning, author = {Unhelkar, Vaibhav V. and Shah, Julie A.}, title = {Learning Models of Sequential Decision-Making with Partial Specification of Agent Behavior}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2019} } - Semi-Supervised Learning of Decision-Making Models for Human-Robot Collaboration
Conf. on Robot Learning (CoRL), 2019@inproceedings{unhelkar2019semi, author = {Unhelkar, Vaibhav V. and Li, Shen and Shah, Julie A.}, title = {Semi-Supervised Learning of Decision-Making Models for Human-Robot Collaboration}, booktitle = {Conference on Robot Learning (CoRL)}, year = {2019} } - Mobile Robots for Moving-Floor Assembly Lines
IEEE Robotics & Automation Magazine (RA-M), 2018@article{unhelkar2018mobile, author = {Unhelkar, Vaibhav V. and D{\"o}rr, Stefan and Bubeck, Alexander and Lasota, Przemyslaw A. and Perez, Jorge and Siu, Ho Chit and Boerkoel, James C. and Tyroller, Quirin and Bix, Johannes and Bartscher, Stefan and Shah, Julie A.}, title = {Mobile Robots for Moving-Floor Assembly Lines}, journal = {IEEE Robotics \& Automation Magazine (RA-M)}, year = {2018} } - Human-Aware Robotic Assistant for Collaborative Assembly: Integrating Human Motion Prediction with Planning in Time
IEEE Robotics and Automation Letters (RA-L), 2018@article{unhelkar2018human, author = {Unhelkar, Vaibhav V. and Lasota, Przemyslaw A. and Tyroller, Quirin and Buhai, Rares-Darius and Marceau, Laurie and Deml, Barbara and Shah, Julie A.}, title = {Human-Aware Robotic Assistant for Collaborative Assembly: Integrating Human Motion Prediction with Planning in Time}, journal = {IEEE Robotics and Automation Letters (RA-L)}, volume = {3}, number = {3}, pages = {2394--2401}, year = {2018} } - Learning and Communicating the Latent States of Human-Machine Collaboration
Intl. Joint Conferences on Artificial Intelligence (IJCAI), 2018@inproceedings{unhelkar2018learning, author = {Unhelkar, Vaibhav V. and Shah, Julie A.}, title = {Learning and Communicating the Latent States of Human-Machine Collaboration}, booktitle = {International Joint Conferences on Artificial Intelligence (IJCAI)}, pages = {5789--5790}, year = {2018} } - Evaluating Effects of User Experience and System Transparency on Trust in Automation
ACM/IEEE Intl. Conf. on Human-Robot Interaction (HRI), 2017@inproceedings{yang2017evaluating, author = {Yang, X. Jessie and Unhelkar, Vaibhav V. and Li, Kevin and Shah, Julie A.}, title = {Evaluating Effects of User Experience and System Transparency on Trust in Automation}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, pages = {408--416}, year = {2017}, doi = {10.1145/2909824.3020230} } - ConTaCT: Deciding to Communicate in Time-critical, Collaborative Tasks in Unknown, Deterministic Domains
AAAI Conf. on Artificial Intelligence (AAAI), 2016@inproceedings{unhelkar2016contact, author = {Unhelkar, Vaibhav V. and Shah, Julie A.}, title = {ConTaCT: Deciding to Communicate in Time-critical, Collaborative Tasks in Unknown, Deterministic Domains}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2016} } - Human-robot co-navigation using anticipatory indicators of human walking motion
Intl. Conf. on Robotics and Automation (ICRA), 2015@inproceedings{unhelkar2015human, author = {Unhelkar, Vaibhav V. and Perez-D'Arpino, Claudia and Stirling, Leia and Shah, Julie A.}, title = {Human-robot co-navigation using anticipatory indicators of human walking motion}, booktitle = {International Conference on Robotics and Automation (ICRA)}, pages = {6183--6190}, year = {2015}, doi = {10.1109/ICRA.2015.7140067} } - Challenges in Developing a Collaborative Robotic Assistant for Automotive Assembly Lines
ACM/IEEE Intl. Conf. on Human-Robot Interaction Extended Abstracts (HRI), 2015@inproceedings{unhelkar2015challenges, author = {Unhelkar, Vaibhav Vasant and Shah, Julie A.}, title = {Challenges in Developing a Collaborative Robotic Assistant for Automotive Assembly Lines}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts (HRI)}, pages = {239--240}, year = {2015}, doi = {10.1145/2701973.2702705} } - Comparative Performance of Human and Mobile Robotic Assistants in Collaborative Fetch-and-deliver Tasks
ACM/IEEE Intl. Conf. on Human-Robot Interaction (HRI), 2014@inproceedings{unhelkar2014comparative, author = {Unhelkar, Vaibhav V. and Siu, Ho Chit and Shah, Julie A.}, title = {Comparative Performance of Human and Mobile Robotic Assistants in Collaborative Fetch-and-deliver Tasks}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, pages = {82--89}, year = {2014}, doi = {10.1145/2559636.2559655} } - Towards control and sensing for an autonomous mobile robotic assistant navigating assembly lines
Intl. Conf. on Robotics and Automation (ICRA), 2014@inproceedings{unhelkar2014towards, author = {Unhelkar, Vaibhav V. and Perez, Jorge and Boerkoel, James C. and Bix, Johannes and Bartscher, Stefan and Shah, Julie A.}, title = {Towards control and sensing for an autonomous mobile robotic assistant navigating assembly lines}, booktitle = {International Conference on Robotics and Automation (ICRA)}, pages = {4161--4167}, year = {2014}, doi = {10.1109/ICRA.2014.6907464} }