Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback

In interactive imitation learning (IL), uncertainty quantification offers a way for the learner (i.e. robot) to contend with distribution shifts encountered during deployment by actively seeking additional feedback from an expert (i.e. human) online. Prior works use mechanisms like ensemble disagreement or Monte Carlo dropout to quantify when black-box IL policies are uncertain; however, these approaches can lead to overconfident estimates when faced with deployment-time distribution shifts. Instead, we contend that we need uncertainty quantification algorithms that can leverage the expert human feedback received during deployment time to adapt the robot's uncertainty online. To tackle this, we draw upon online conformal prediction, a distribution-free method for constructing prediction intervals online given a stream of ground-truth labels. Human labels, however, are intermittent in the interactive IL setting. Thus, from the conformal prediction side, we introduce a novel uncertainty quantification algorithm called intermittent quantile tracking (IQT) that leverages a probabilistic model of intermittent labels, maintains asymptotic coverage guarantees, and empirically achieves desired coverage levels. From the interactive IL side, we develop ConformalDAgger, a new approach wherein the robot uses prediction intervals calibrated by IQT as a reliable measure of deployment-time uncertainty to actively query for more expert feedback. We compare ConformalDAgger to prior uncertainty-aware DAgger methods in scenarios where the distribution shift is (and isn't) present because of changes in the expert's policy. We find that in simulated and hardware deployments on a 7DOF robotic manipulator, ConformalDAgger detects high uncertainty when the expert shifts and increases the number of interventions compared to baselines, allowing the robot to more quickly learn the new behavior.

Conformalized Teleoperation: Confidently Mapping Human Inputs to High-Dimensional Robot Actions

Assistive robotic arms often have more degrees-of-freedom than a human teleoperator can control with a low-dimensional input, like a joystick. To overcome this challenge, existing approaches use data-driven methods to learn a mapping from low-dimensional human inputs to high-dimensional robot actions. However, determining if such a black-box mapping can confidently infer a user's intended high-dimensional action from low-dimensional inputs remains an open problem. Our key idea is to adapt the assistive map at training time to additionally estimate high-dimensional action quantiles, and then calibrate these quantiles via rigorous uncertainty quantification methods. Specifically, we leverage adaptive conformal prediction which adjusts the intervals over time, reducing the uncertainty bounds when the mapping is performant and increasing the bounds when the mapping consistently mis-predicts. Furthermore, we propose an uncertainty-interval-based mechanism for detecting high-uncertainty user inputs and robot states. We evaluate the efficacy of our proposed approach in a 2D assistive navigation task and two 7DOF Kinova Jaco tasks involving assistive cup grasping and goal reaching. Our findings demonstrate that conformalized assistive teleoperation manages to detect (but not differentiate between) high uncertainty induced by diverse preferences and induced by low-precision trajectories in the mapping's training dataset. On the whole, we see this work as a key step towards enabling robots to quantify their own uncertainty and proactively seek intervention when needed.

Understanding Robot Minds: Leveraging Machine Teaching for Transparent Human-Robot Collaboration Across Diverse Groups

In this work, we aim to improve transparency and efficacy in human-robot collaboration by developing machine teaching algorithms suitable for groups with varied learning capabilities. While previous approaches focused on tailored approaches for teaching individuals, our method teaches teams with various compositions of diverse learners using team belief representations to address personalization challenges within groups. We investigate various group teaching strategies, such as focusing on individual beliefs or the group's collective beliefs, and assess their impact on learning robot policies for different team compositions. Our findings reveal that team belief strategies yield less variation in learning duration and better accommodate diverse teams compared to individual belief strategies, suggesting their suitability in mixed-proficiency settings with limited resources. Conversely, individual belief strategies provide a more uniform knowledge level, particularly effective for homogeneously inexperienced groups. Our study indicates that the teaching strategy's efficacy is significantly influenced by team composition and learner proficiency, highlighting the importance of real-time assessment of learner proficiency and adapting teaching approaches based on learner proficiency for optimal teaching outcomes.

Bootstrapping Cognitive Agents with a Large Language Model

Large language models contain noisy general knowledge of the world, yet are hard to train or fine-tune. On the other hand cognitive architectures have excellent interpretability and are flexible to update but require a lot of manual work to instantiate. In this work, we combine the best of both worlds: bootstrapping a cognitive-based model with the noisy knowledge encoded in large language models. Through an embodied agent doing kitchen tasks, we show that our proposed framework yields better efficiency compared to an agent based entirely on large language models. Our experiments indicate that large language models are a good source of information for cognitive architectures, and the cognitive architecture in turn can verify and update the knowledge of large language models to a specific domain.

Multi-Agent Strategy Explanations for Human-Robot Collaboration

As robots are deployed in human spaces, it's important that they are able to coordinate their actions with the people around them. Part of such coordination involves ensuring that people have a good understanding of how a robot will act in the environment. This can be achieved through explanations of the robot's policy. Much prior work in explainable AI and RL focuses on generating explanations for single-agent policies, but little has been explored in generating explanations for collaborative policies. In this work, we investigate how to generate multi-agent strategy explanations for human-robot collaboration. We formulate the problem using a generic multi-agent planner, show how to generate visual explanations through strategy-conditioned landmark states and generate textual explanations by giving the landmarks to an LLM. Through a user study, we find that when presented with explanations from our proposed framework, users are able to better explore the full space of strategies and collaborate more efficiently with new robot partners.

Coordination with Humans via Strategy Matching

Human and robot partners increasingly need to work together to perform tasks as a team. Robots designed for such collaboration must reason about how their task-completion strategies interplay with the behavior and skills of their human team members as they coordinate on achieving joint goals. Our goal in this work is to develop a computational framework for robot adaptation to human partners in human-robot team collaborations. We first present an algorithm for autonomously recognizing available task-completion strategies by observing human-human teams performing a collaborative task. By transforming team actions into low dimensional representations using hidden Markov models, we can identify strategies without prior knowledge. Robot policies are learned on each of the identified strategies to construct a Mixture-of-Experts model that adapts to the task strategies of unseen human partners. We evaluate our model on a collaborative cooking task using an Overcooked simulator. Results of an online user study with 125 participants demonstrate that our framework improves the task performance and collaborative fluency of human-agent teams, as compared to state of the art reinforcement learning methods.

Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning

To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement learning (IRL). Thus, robots can convey their beliefs and desires by providing demonstrations that are informative for a human's IRL. An informative demonstration is one that differs strongly from the learner's expectations of what the robot will do given their current understanding of the robot's decision making. However, standard IRL does not model the learner's existing expectations, and thus cannot do this counterfactual reasoning. We propose to incorporate the learner's current understanding of the robot's decision making into our model of human IRL, so that our robot can select demonstrations that maximize the human's understanding. We also propose a novel measure for estimating the difficulty for a human to predict instances of a robot's behavior in unseen environments. A user study finds that our test difficulty measure correlates well with human performance and confidence. Interestingly, considering human beliefs and counterfactuals when selecting demonstrations decreases human performance on easy tests, but increases performance on difficult tests, providing insight on how to best utilize such models.

Tradeoff-Focused Contrastive Explanation for MDP Planning

End-users' trust in automated agents is important as automated decision-making and planning is increasingly used in many aspects of people's lives. In real-world applications of planning, multiple optimization objectives are often involved. Thus, planning agents' decisions can involve complex tradeoffs among competing objectives. It can be difficult for the end-users to understand why an agent decides on a particular planning solution on the basis of its objective values. As a result, the users may not know whether the agent is making the right decisions, and may lack trust in it. In this work, we contribute an approach, based on contrastive explanation, that enables a multi-objective MDP planning agent to explain its decisions in a way that communicates its tradeoff rationale in terms of the domain-level concepts. We conduct a human subjects experiment to evaluate the effectiveness of our explanation approach in a mobile robot navigation domain. The results show that our approach significantly improves the users' understanding, and confidence in their understanding, of the tradeoff rationale of the planning agent.

Expressing Ethnicity through Behaviors of a Robot Character

Achieving homophily, or association based on similarity, between a human user and a robot holds a promise of improved perception and task performance. However, no previous studies that address homophily via ethnic similarity with robots exist. In this paper, we discuss the difficulties of evoking ethnic cues in a robot, as opposed to a virtual agent, and an approach to overcome those difficulties based on using ethnically salient behaviors. We outline our methodology for selecting and evaluating such behaviors, and culminate with a study that evaluates our hypotheses of the possibility of ethnic attribution of a robot character through verbal and nonverbal behaviors and of achieving the homophily effect.

Heuristic Search Value Iteration for POMDPs

We present a novel POMDP planning algorithm called heuristic search value iteration (HSVI).HSVI is an anytime algorithm that returns a policy and a provable bound on its regret with respect to the optimal policy. HSVI gets its power by combining two well-known techniques: attention-focusing search heuristics and piecewise linear convex representations of the value function. HSVI's soundness and convergence have been proven. On some benchmark problems from the literature, HSVI displays speedups of greater than 100 with respect to other state-of-the-art POMDP value iteration algorithms. We also apply HSVI to a new rover exploration problem 10 times larger than most POMDP problems in the literature.