153 citations · 716 across the 39 of their papers we have counts for
39 papers
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
Andi Peng, Aviv Netanyahu, Mark Ho +4
Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness…
Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue
Cristian-Paul Bara, Ziqiao Ma, Yingzhuo Yu +2
Collaborative tasks often begin with partial task knowledge and incomplete initial plans from each partner. To complete these tasks, agents need to engage in situated communication…
Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence
Peter Stone, Rodney Brooks, Erik Brynjolfsson +14
In September 2016, Stanford's "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the first report of its planned long-term periodic assessment of artificial…
Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report
Michael L. Littman, Ifeoma Ajunwa, Guy Berger +14
In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intel…
Towards Human-Agent Communication via the Information Bottleneck Principle
Mycal Tucker, Julie Shah, Roger Levy +1
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficie…
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
Yanwei Wang, Nadia Figueroa, Shen Li +2
Learning from demonstration (LfD) has succeeded in tasks featuring a long time horizon. However, when the problem complexity also includes human-in-the-loop perturbations, state-of…
Prototype Based Classification from Hierarchy to Fairness
Mycal Tucker, Julie Shah
Artificial neural nets can represent and classify many types of data but are often tailored to particular applications -- e.g., for "fair" or "hierarchical" classification. Once an…
The Solvability of Interpretability Evaluation Metrics
Yilun Zhou, Julie Shah
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency. In this paper,…
ExSum: From Local Explanations to Model Understanding
Yilun Zhou, Marco Tulio Ribeiro, Julie Shah
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires bot…
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
Mycal Tucker, Tiwalayo Eisape, Peng Qian +2
Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models…
Probe-Based Interventions for Modifying Agent Behavior
Mycal Tucker, William Kuhl, Khizer Shahid +3
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influen…
Explaining Reward Functions to Humans for Better Human-Robot Collaboration
Lindsay Sanneman, Julie Shah
Explainable AI techniques that describe agent reward functions can enhance human-robot collaboration in a variety of settings. One context where human understanding of agent reward…
Set-based State Estimation with Probabilistic Consistency Guarantee under Epistemic Uncertainty
Shen Li, Theodoros Stouraitis, Michael Gienger +2
Consistent state estimation is challenging, especially under the epistemic uncertainties arising from learned (nonlinear) dynamic and observation models. In this work, we propose a…
The Irrationality of Neural Rationale Models
Yiming Zheng, Serena Booth, Julie Shah +1
Neural rationale models are popular for interpretable predictions of NLP tasks. In these, a selector extracts segments of the input text, called rationales, and passes these segmen…
Emergent Discrete Communication in Semantic Spaces
Mycal Tucker, Huao Li, Siddharth Agrawal +4
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do al…
Supervised Bayesian Specification Inference from Demonstrations
Ankit Shah, Pritish Kamath, Shen Li +4
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that ta…
Do Feature Attribution Methods Correctly Attribute Features?
Yilun Zhou, Serena Booth, Marco Tulio Ribeiro +1
Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no…
A Bayesian Approach to Identifying Representational Errors
Ramya Ramakrishnan, Vaibhav Unhelkar, Ece Kamar +1
Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand. Determining the root cause for these errors can improve future de…
Reactive Task and Motion Planning under Temporal Logic Specifications
Shen Li, Daehyung Park, Yoonchang Sung +2
We present a task-and-motion planning (TAMP) algorithm robust against a human operator's cooperative or adversarial interventions. Interventions often invalidate the current plan a…
Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare
Sangwon Seo, Lauren R. Kennedy-Metz, Marco A. Zenati +3
Shared 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., avia…
RoCUS: Robot Controller Understanding via Sampling
Yilun Zhou, Serena Booth, Nadia Figueroa +1
As robots are deployed in complex situations, engineers and end users must develop a holistic understanding of their behaviors, capabilities, and limitations. Some behaviors are di…
Experimental Assessment of Human-Robot Teaming for Multi-Step Remote Manipulation with Expert Operators
Claudia Pérez-D'Arpino, Rebecca P. Khurshid, Julie A. Shah
Remote robot manipulation with human control enables applications where safety and environmental constraints are adverse to humans (e.g. underwater, space robotics and disaster res…
The State of Industrial Robotics: Emerging Technologies, Challenges, and Key Research Directions
Lindsay Sanneman, Christopher Fourie, Julie A. Shah
Robotics and related technologies are central to the ongoing digitization and advancement of manufacturing. In recent years, a variety of strategic initiatives around the world inc…
Trust Considerations for Explainable Robots: A Human Factors Perspective
Lindsay Sanneman, Julie A. Shah
Recent advances in artificial intelligence (AI) and robotics have drawn attention to the need for AI systems and robots to be understandable to human users. The explainable AI (XAI…