Peter Stone

• PhD
• Professor at University of Texas at Austin

Developing AI agents that can robustly adapt to dramatically different strategic landscapes without retraining is a central challenge for multi-agent learning. Pok\'emon Video Game Championships (VGC) is a domain with an extraordinarily large space of possible team configurations of approximately $10^{139}$ - far larger than those of Dota or Starcr...

N-agent ad hoc teamwork (NAHT) is a newly introduced challenge in multi-agent reinforcement learning, where controlled subteams of varying sizes must dynamically collaborate with varying numbers and types of unknown teammates without pre-coordination. The existing learning algorithm (POAM) considers only independent learning for its flexibility in...

Developing AI agents capable of collaborating with previously unseen partners is a fundamental generalization challenge in multi-agent learning, known as Ad Hoc Teamwork (AHT). Existing AHT approaches typically adopt a two-stage pipeline, where first, a fixed population of teammates is generated with the idea that they should be representative of t...

We present an approach to ensure safe and deadlock-free navigation for decentralized multi-robot systems operating in constrained environments, including doorways and intersections. Although many solutions have been proposed that ensure safety and resolve deadlocks, optimally preventing deadlocks in a minimally invasive and decentralized fashion re...

Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assuming, implicitly or explicitly, a model of human preferences. A preference model that poorly describes how humans generate preferences risks learning a poor approximation of the human's reward function. In this...

A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred to as social robot navigation . While the field of social navigation has advanced tremendously in recent years, the fair evaluation of algorithms that tackle social navigation remains hard because it involves not just robotic agents moving...

The high cost of real-world data for robotics Reinforcement Learning (RL) leads to the wide usage of simulators. Despite extensive work on building better dynamics models for simulators to match with the real world, there is another, often-overlooked mismatch between simulations and the real world, namely the distribution of available training task...

The third Benchmark Autonomous Robot Navigation (BARN) Challenge took place at the 2024 IEEE International Conference on Robotics and Automation (ICRA 2024) in Yokohama, Japan and continued to evaluate the performance of state-of-the-art autonomous ground navigation systems in highly constrained environments. Similar to the trend in the first and s...

The most fundamental capability of modern AI methods such as Large Language Models (LLMs) is the ability to predict the next token in a long sequence of tokens, known as ``sequence modeling." Although the Transformers model is the current dominant approach to sequence modeling, its quadratic computational cost with respect to sequence length is a s...

The 3rd BARN (Benchmark Autonomous Robot Navigation) Challenge took place at the 2024 IEEE International Conference on Robotics and Automation (ICRA 2024) in Yokohama, Japan and continued to evaluate the performance of state-of-the-art autonomous ground navigation systems in highly constrained environments. Similar to the trend in The 1st and 2nd B...

Imitation Learning (IL) strategies are used to generate policies for robot motion planning and navigation by learning from human trajectories. Recently, there has been a lot of excitement in applying IL in social interactions arising in urban environments such as university campuses, restaurants, grocery stores, and hospitals. However, obtaining nu...

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for le...

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their partial return. Recent work casts doubt on the v...

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse teammate policies obtained through maximizing specific diversity metrics. Howe...

This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics more generally. To diagnose common errors, we develop 8 simple sanity checks for identifying flaws in reward functions. We survey research that is published in top-tier ven...

A major goal in robotics is to enable intelligent mobile robots to operate smoothly in shared human-robot environments. One of the most fundamental capabilities in service of this goal is competent navigation in this “social” context. As a result, there has been a recent surge of research on social navigation; and especially as it relates to the ha...

What is the optimal penalty for errors in infant skill learning? Behavioral analyses indicate that errors are frequent but trivial as infants acquire foundational skills. In learning to walk, for example, falling is commonplace but appears to incur only a negligible penalty. Behavioral data, however, cannot reveal whether a low penalty for falling...

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse teammate policies obtained through maximizing specific diversity metrics. Howe...

The 2nd BARN (Benchmark Autonomous Robot Navigation) Challenge took place at the 2023 IEEE International Conference on Robotics and Automation (ICRA 2023) in London, UK and continued to evaluate the performance of state-of-the-art autonomous ground navigation systems in highly constrained environments. Compared to The 1st BARN Challenge at ICRA 202...

In existing task and motion planning (TAMP) research, it is a common assumption that experts manually specify the state space for task-level planning. A well-developed state space enables the desirable distribution of limited computational resources between task planning and motion planning. However, developing such task-level state spaces can be n...

A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred to as social robot navigation. While the field of social navigation has advanced tremendously in recent years, the fair evaluation of algorithms that tackle social navigation remains hard because it involves not just robotic agents moving i...

In reinforcement learning (RL), a reward function that aligns exactly with a task's true performance metric is often necessarily sparse. For example, a true task metric might encode a reward of 1 upon success and 0 otherwise. The sparsity of these true task metrics can make them hard to learn from, so in practice they are often replaced with altern...

Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost importance for GCRL since, by default, the agent is only rewarded when it reaches its goal. While several methods have...

Current approaches to multi-agent cooperation rely heavily on centralized mechanisms or explicit communication protocols to ensure convergence. This paper studies the problem of distributed multi-agent learning without resorting to centralized components or explicit communication. It examines the use of distribution matching to facilitate the coord...

Robots frequently need to perceive object attributes, such as red, heavy, and empty, using multimodal exploratory behaviors, such as look, lift, and shake. One possible way for robots to do so is to learn a classifier for each perceivable attribute given an exploratory behavior. Once the attribute classifiers are learned, they can be used by robots...

Ad hoc teamwork is the research problem of designing agents that can collaborate with new teammates without prior coordination. This survey makes a two-fold contribution: First, it provides a structured description of the different facets of the ad hoc teamwork problem. Second, it discusses the progress that has been made in the field so far, and i...

The Benchmark Autonomous Robot Navigation (BARN) Challenge took place at the 2022 IEEE International Conference on Robotics and Automation (ICRA), in Philadelphia, PA, USA. The aim of the challenge was to evaluate state-of-the-art autonomous ground navigation systems for moving robots through highly constrained environments in a safe and efficient...

This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics more generally. To diagnose common errors, we develop 8 simple sanity checks for identifying flaws in reward functions. We survey research that is published in top-tier ven...

Given a dataset of expert agent interactions with an environment of interest, a viable method to extract an effective agent policy is to estimate the maximum likelihood policy indicated by this data. This approach is commonly referred to as behavioral cloning (BC). In this work, we describe a key disadvantage of BC that arises due to the maximum li...

Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches lack safety guarantees; and learned navigation systems may not generalize well to unseen environments. Despit...

Machine learning approaches have recently enabled autonomous navigation for mobile robots in a data-driven manner. Since most existing learning-based navigation systems are trained with data generated in artificially created training environments, during real-world deployment at scale, it is inevitable that robots will encounter unseen scenarios, w...

Social navigation is the capability of an autonomous agent, such as a robot, to navigate in a “socially compliant” manner in the presence of other intelligent agents such as humans. With the emergence of autonomously navigating mobile robots in human-populated environments (e.g., domestic service robots in homes and restaurants and food delivery ro...

The BARN (Benchmark Autonomous Robot Navigation) Challenge took place at the 2022 IEEE International Conference on Robotics and Automation (ICRA 2022) in Philadelphia, PA. The aim of the challenge was to evaluate state-of-the-art autonomous ground navigation systems for moving robots through highly constrained environments in a safe and efficient m...

Learning dynamics models accurately is an important goal for Model-Based Reinforcement Learning (MBRL), but most MBRL methods learn a dense dynamics model which is vulnerable to spurious correlations and therefore generalizes poorly to unseen states. In this paper, we introduce Causal Dynamics Learning for Task-Independent State Abstraction (CDL),...

Accurate control of robots in the real world requires a control system that is capable of taking into account the kinodynamic interactions of the robot with its environment. At high speeds, the dependence of the movement of the robot on these kinodynamic interactions becomes more pronounced, making high-speed, accurate robot control a challenging p...

The utility of reinforcement learning is limited by the alignment of reward functions with the interests of human stakeholders. One promising method for alignment is to learn the reward function from human-generated preferences between pairs of trajectory segments. These human preferences are typically assumed to be informed solely by partial retur...

While current autonomous navigation systems allow robots to successfully drive themselves from one point to another in specific environments, they typically require extensive manual parameter re-tuning by human robotics experts in order to function in new environments. Furthermore, even for just one complex environment, a single set of fine-tuned p...

One of the key challenges in high speed off road navigation on ground vehicles is that the kinodynamics of the vehicle terrain interaction can differ dramatically depending on the terrain. Previous approaches to addressing this challenge have considered learning an inverse kinodynamics (IKD) model, conditioned on inertial information of the vehicle...

Social navigation is the capability of an autonomous agent, such as a robot, to navigate in a 'socially compliant' manner in the presence of other intelligent agents such as humans. With the emergence of autonomously navigating mobile robots in human populated environments (e.g., domestic service robots in homes and restaurants and food delivery ro...

The imitation learning research community has recently made significant progress towards the goal of enabling artificial agents to imitate behaviors from video demonstrations alone. However, current state-of-the-art approaches developed for this problem exhibit high sample complexity due, in part, to the high-dimensional nature of video observation...

Reinforcement learning in simulation is a promising alternative to the prohibitive sample cost of reinforcement learning in the physical world. Unfortunately, policies learned in simulation often perform worse than hand-coded policies when applied on the target, physical system. Grounded simulation learning ( gsl ) is a general framework that promi...

Most current approaches to social navigation focus on the trajectory and position of participants in the interaction. Our current work on the topic focuses on integrating gaze into social navigation, both to cue nearby pedestrians as to the intended trajectory of the robot and to enable the robot to read the intentions of nearby pedestrians. This p...

This letter presents a learning-based approach to consider the effect of unobservable world states in kinodynamic motion planning in order to enable accurate high-speed off-road navigation on unstructured terrain. Existing kinodynamic motion planners either operate in structured and homogeneous environments and thus do not need to explicitly accoun...

With the approaching goal of having robots collaborate in shared human-robot environments, navigation in this context becomes both crucial and desirable. Recent developments in robotics have encountered and tackled some of the challenges of navigating in mixed human-robot environments, and in recent years we observe a surge of related work that spe...

In reinforcement learning, importance sampling is a widely used method for evaluating an expectation under the distribution of data of one policy when the data has in fact been generated by a different policy. Importance sampling requires computing the likelihood ratio between the action probabilities of a target policy and those of the data-produc...

A service robot accepting verbal commands from a human operator is likely to encounter requests that reference objects not currently represented in its knowledge base. In domestic or office settings, the construction of a complete knowledge base would be cumbersome and unlikely to succeed in most real-world deployments. The world that such a robot...

Human-robot shared autonomy techniques for vehicle navigation hold promise for reducing a human driver’s workload, ensuring safety, and improving navigation efficiency. However, because typical techniques achieve these improvements by effectively removing human control at critical moments, these approaches often exhibit poor responsiveness to human...

In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large amount of training experiences. Reward shaping is a common approach for incorporating domain knowledge into reinf...

A desirable goal for autonomous agents is to be able to coordinate on the fly with previously unknown teammates. Known as “ad hoc teamwork”, enabling such a capability has been receiving increasing attention in the research community. One of the central challenges in ad hoc teamwork is quickly recognizing the current plans of other agents and plann...

Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. An agent could leverage an understanding of such implicit human feedback to improve its task performance at no cost to the human. This approach contrasts with common agent teaching me...

People are proficient at communicating their intentions in order to avoid conflicts when navigating in narrow, crowded environments. Mobile robots, on the other hand, often lack both the ability to interpret human intentions and the ability to clearly communicate their own intentions to people sharing their space. This work addresses the second of...

In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large amount of training experiences. Reward shaping is a common approach for incorporating domain knowledge into reinf...

Coverage path planning is a well-studied problem in robotics in which a robot must plan a path that passes through every point in a given area repeatedly, usually with a uniform frequency. To address the scenario in which some points need to be visited more frequently than others, this problem has been extended to non-uniform coverage planning. Thi...

Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenar...

In this work, we present methods for using human-robot dialog to improve language understanding for a mobile robot agent. The agent parses natural language to underlying semantic meanings and uses robotic sensors to create multi-modal models of perceptual concepts like red and heavy. The agent can be used for showing navigation routes, delivering o...

Multi-robot planning (mrp) aims at computing plans, each in the form of a sequence of actions, for a team of robots to achieve their individual goals, while minimizing overall cost. Solving mrp problems requires modeling limited domain resources (e.g., corridors that allow at most one robot at a time), and the possibility of action synergy (e.g., m...

Efficiently guiding humans in indoor environments is a challenging open problem. Due to recent advances in mobile robotics and natural language processing, it has recently become possible to consider doing so with the help of mobile, verbally communicating robots. In the past, stationary verbal robots have been used for this purpose at Microsoft Re...

RoboCup@Home is an international robotics competition based on domestic tasks requiring autonomous capabilities pertaining to a large variety of AI technologies. Research challenges are motivated by these tasks both at the level of individual technologies and the integration of subsystems into a fully functional, robustly autonomous system. We desc...

People are proficient at communicating their intentions in order to avoid conflicts when navigating in narrow, crowded environments. In many situations mobile robots lack both the ability to interpret human intentions and the ability to clearly communicate their own intentions to people sharing their space. This work addresses the second of these p...

General-purpose service robots are expected to undertake a broad range of tasks at the request of users. Knowledge representation and planning systems are essential to flexible autonomous robots, but the field lacks a unified perspective on which features are essential for general-purpose service robots. Progress towards planning and reasoning for...

Natural language understanding for robotics can require substantial domain- and platform-specific engineering. For example, for mobile robots to pick-and-place objects in an environment to satisfy human commands, we can specify the language humans use to issue such commands, and connect concept words like red can to physical object properties. One...

Task-motion planning (TMP) addresses the problem of efficiently generating executable and low-cost task plans in a discrete space such that the (initially unknown) action costs are determined by motion plans in a corresponding continuous space. However, a task-motion plan can be sensitive to unexpected domain uncertainty and changes, leading to sub...

When developing general purpose robots, the overarching software architecture can greatly affect the ease of accomplishing various tasks. Initial efforts to create unified robot systems in the 1990s led to hybrid architectures, emphasizing a hierarchy in which deliberative plans direct the use of reactive skills. However, since that time there has...

Efforts are underway at UT Austin to build autonomous robot systems that address the challenges of long-term deployments in office environments and of the more prescribed domestic service tasks of the RoboCup@Home competition. We discuss the contrasts and synergies of these efforts, highlighting how our work to build a RoboCup@Home Domestic Standar...

Intelligent robots frequently need to explore the objects in their working environments. Modern sensors have enabled robots to learn object properties via perception of multiple modalities. However, object exploration in the real world poses a challenging trade-off between information gains and exploration action costs. Mixed observability Markov d...

Although both infancy and artificial intelligence (AI) researchers are interested in developing systems that produce adaptive, functional behavior, the two disciplines rarely capitalize on their complementary expertise. Here, we used soccer-playing robots to test a central question about the development of infant walking. During natural activity, i...

A major goal of grounded language learning research is to enable robots to connect language predicates to a robot's physical interactive perception of the world. Coupling object exploratory behaviors such as grasping, lifting, and looking with multiple sensory modalities (e.g., audio, haptics, and vision) enables a robot to ground non-visual words...

General purpose planners enable AI systems to solve many different types of planning problems. However, many different planners exist, each with different strengths and weaknesses, and there are no general rules for which planner would be best to apply to a given problem. In this paper, we empirically compare the performance of state-of-the-art pla...

Transfer learning is a method where an agent reuses knowledge learned in a source task to improve learning on a target task. Recent work has shown that transfer learning can be extended to the idea of curriculum learning, where the agent incrementally accumulates knowledge over a sequence of tasks (i.e. a curriculum). In most existing work, such cu...

We consider the task of evaluating a policy for a Markov decision process (MDP). The standard unbiased technique for evaluating a policy is to deploy the policy and observe its performance. We show that the data collected from deploying a different policy, commonly called the behavior policy, can be used to produce unbiased estimates with lower mea...

In recent years, research has shown that transfer learning methods can be leveraged to construct curricula that sequence a series of simpler tasks such that performance on a final target task is improved. A major limitation of existing approaches is that such curricula are handcrafted by humans that are typically domain experts. To address this lim...

In recent years, there has been growing interest in the study of automated playlist generation — music recommender systems that focus on modeling preferences over song sequences rather than on individual songs in isolation. This paper addresses this problem by learning personalized models on the fly of both song and transition preferences, uniquely...

Recent progress in both AI and robotics have enabled the development of general purpose robot platforms that are capable of executing a wide variety of complex, temporally extended service tasks in open environments. This article introduces a novel, custom-designed multi-robot platform for research on AI, robotics, and especially human–robot intera...

Carsharing programs provide an alternative to private vehicle ownership. Combining car-sharing programs with autonomous vehicles would improve user access to vehicles thereby removing one of the main challenges to widescale adoption of these programs. While the ability to easily move cars to meet demand would be significant for carsharing programs,...

The Standard Platform League is one of the main competitions at the annual RoboCup world championships. In this competition, teams of five humanoid robots play soccer against each other. In 2013, the league began a new competition which serves as a testbed for cooperation without pre-coordination: the Drop-in Player Competition. Instead of homogene...

In this paper we study a bin-based estimation method of the amount of effort associated with code development. We investigate the following 3 variants to define the bins: (1) the same amount of data in a bin (SVM same #), (2) the same range for each bin (SVM same range) and (3) the bins made by Ward’s method (SVM Ward). We carry out evaluation expe...

Robots are being deployed in an increasing variety of environments for longer periods of time. As the number of robots grows, they will increasingly need to interact with other robots. Additionally, the number of companies and research laboratories producing these robots is increasing, leading to the situation where these robots may not share a com...