Reid Simmons

Michelle Zhao, Reid Simmons, Henny Admoni

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.

Michael S. Lee, Henny Admoni, Reid Simmons

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 learner'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 a 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.

Patrick Callaghan, Reid Simmons, Henny Admoni

Discrepancies between an agent's actual knowledge and what a person thinks the agent knows can hinder interactions. If an agent could detect such discrepancies, it could provide feedback to account for them and improve current and future interactions. Using the I-POMDP as a framework for a second-order Theory of Mind (ToM-2), this work endows an agent with the ability to model the evolution of a person's erroneous beliefs about an agent and the cognitive biases and heuristics (CBH) from which they arise. In doing so, the agent can detect when CBH might be at play during an interaction and adaptively generate feedback that accounts for them. An in-person user study shows how a ToM-2 learner can account for the effects of a teacher's CBH to significantly improve the informativeness of teacher actions, and subjective results suggest people find the ToM-2 learner's feedback more useful.

Feiyu Gavin Zhu, Jean Oh, Reid Simmons

Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are challenging for a layperson when they want to teach the agent new skills. To lower the barrier of teaching AI agents, we propose Interactive Policy Restructuring and Training (InterPReT), which takes user instructions to continually update the policy structure and optimize its parameters to fit user demonstrations. This enables end-users to interactively give instructions and demonstrations, monitor the agent's performance, and review the agent's decision-making strategies. A user study (N=34) on teaching an AI agent to drive in a racing game confirms that our approach yields more robust policies without impairing system usability, compared to a generic imitation learning baseline, when a layperson is responsible for both giving demonstrations and determining when to stop. This shows that our method is more suitable for end-users without much technical background in machine learning to train a dependable policy

Feiyu Zhu, Reid Simmons · cmu

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.

Michelle Zhao, Reid Simmons, Henny Admoni et al.

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.

Mouad Abrini, Omri Abend, Dina Acklin et al. · cambridge

This volume includes a selection of papers presented at the Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2025 in Philadelphia US on 3rd March 2025. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research community.

Feiyu Zhu, Jean Oh, Reid Simmons · cmu

Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios. One approach to these problems is to introduce general domain knowledge, such that the policy can focus on the essential features and may generalize to unseen states by applying that knowledge. Although this knowledge is easy to acquire from the experts, it is hard to be combined with learning from individual examples due to the lack of semantic structure in neural networks and the time-consuming nature of feature engineering. To enable learning from both general knowledge and specific demonstration trajectories, we use a large language model's coding capability to instantiate a policy structure based on expert domain knowledge expressed in natural language and tune the parameters in the policy with demonstrations. We name this approach the Knowledge Informed Model (KIM) as the structure reflects the semantics of expert knowledge. In our experiments with lunar lander and car racing tasks, our approach learns to solve the tasks with as few as 5 demonstrations and is robust to action noise, outperforming the baseline model without domain knowledge. This indicates that with the help of large language models, we can incorporate domain knowledge into the structure of the policy, increasing sample efficiency for behavior cloning.

Michelle Zhao, Reid Simmons, Henny Admoni et al.

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.

Michael S. Lee, Reid Simmons, Henny Admoni

Demonstrations are a powerful way of increasing the transparency of AI policies. Though informative demonstrations may be selected a priori through the machine teaching paradigm, student learning may deviate from the preselected curriculum in situ. This paper thus explores augmenting a curriculum with a closed-loop teaching framework inspired by principles from the education literature, such as the zone of proximal development and the testing effect. We utilize tests accordingly to close to the loop and maintain a novel particle filter model of human beliefs throughout the learning process, allowing us to provide demonstrations that are targeted to the human's current understanding in real time. A user study finds that our proposed closed-loop teaching framework reduces the regret in human test responses by 43% over a baseline.

Roykrong Sukkerd, Reid Simmons, David Garlan

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.

Maxim Makatchev, Reid Simmons, Majd Sakr et al.

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.

Trey Smith, Reid Simmons

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.

Trey Smith, Reid Simmons

Existing complexity bounds for point-based POMDP value iteration algorithms focus either on the curse of dimensionality or the curse of history. We derive a new bound that relies on both and uses the concept of discounted reachability; our conclusions may help guide future algorithm design. We also discuss recent improvements to our (point-based) heuristic search value iteration algorithm. Our new implementation calculates tighter initial bounds, avoids solving linear programs, and makes more effective use of sparsity.

Maxim Makatchev, Reid Simmons, Majd Sakr

We present the first annotated corpus of nonverbal behaviors in receptionist interactions, and the first nonverbal corpus (excluding the original video and audio data) of service encounters freely available online. Native speakers of American English and Arabic participated in a naturalistic role play at reception desks of university buildings in Doha, Qatar and Pittsburgh, USA. Their manually annotated nonverbal behaviors include gaze direction, hand and head gestures, torso positions, and facial expressions. We discuss possible uses of the corpus and envision it to become a useful tool for the human-robot interaction community.