Publications (45)
Pricing Traffic Networks with Mixed Vehicle Autonomy
Negar Mehr, Roberto Horowitz
In a traffic network, vehicles normally select their routes selfishly. Consequently, traffic networks normally operate at an equilibrium characterized by Wardrop conditions. Howeve…
Active Inverse Learning in Stackelberg Trajectory Games
William Ward, Yue Yu, Jacob Levy +3
Game-theoretic inverse learning is the problem of inferring a player's objectives from their actions. We formulate an inverse learning problem in a Stackelberg game between a leade…
RAT iLQR: A Risk Auto-Tuning Controller to Optimally Account for Stochastic Model Mismatch
Haruki Nishimura, Negar Mehr, Adrien Gaidon +1
Successful robotic operation in stochastic environments relies on accurate characterization of the underlying probability distributions, yet this is often imperfect due to limited…
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
Dayi Dong, Maulik Bhatt, Seoyeon Choi +1
As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. Such be…
DDAT: Diffusion Policies Enforcing Dynamically Admissible Robot Trajectories
Jean-Baptiste Bouvier, Kanghyun Ryu, Kartik Nagpal +3
Diffusion models excel at creating images and videos thanks to their multimodal generative capabilities. These same capabilities have made diffusion models increasingly popular in…
When Should a Leader Act Suboptimally? The Role of Inferability in Repeated Stackelberg Games
Mustafa O. Karabag, Sophia Smith, Negar Mehr +2
When interacting with other decision-making agents in non-adversarial scenarios, it is critical for an autonomous agent to have inferable behavior: The agent's actions must convey…
RAMEN: Real-time Asynchronous Multi-agent Neural Implicit Mapping
Hongrui Zhao, Boris Ivanovic, Negar Mehr
Multi-agent neural implicit mapping allows robots to collaboratively capture and reconstruct complex environments with high fidelity. However, existing approaches often rely on syn…
Adaptive Teaching in Heterogeneous Agents: Balancing Surprise in Sparse Reward Scenarios
Emma Clark, Kanghyun Ryu, Negar Mehr
Learning from Demonstration (LfD) can be an efficient way to train systems with analogous agents by enabling ``Student'' agents to learn from the demonstrations of the most experie…
POLICEd RL: Learning Closed-Loop Robot Control Policies with Provable Satisfaction of Hard Constraints
Jean-Baptiste Bouvier, Kartik Nagpal, Negar Mehr
In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. To encourage constraint satisfaction, existing RL algorithms typically rely on Constrained M…
Learning to Provably Satisfy High Relative Degree Constraints for Black-Box Systems
Jean-Baptiste Bouvier, Kartik Nagpal, Negar Mehr
In this paper, we develop a method for learning a control policy guaranteed to satisfy an affine state constraint of high relative degree in closed loop with a black-box system. Pr…
Potential iLQR: A Potential-Minimizing Controller for Planning Multi-Agent Interactive Trajectories
Talha Kavuncu, Ayberk Yaraneri, Negar Mehr
Many robotic applications involve interactions between multiple agents where an agent's decisions affect the behavior of other agents. Such behaviors can be captured by the equilib…
An Extended Game-Theoretic Model for Aggregate Lane Choice Behavior of Vehicles at Traffic Diverges with a Bifurcating Lane
Ruolin Li, Negar Mehr, Roberto Horowitz
Road network junctions, such as merges and diverges, often act as bottlenecks that initiate and exacerbate congestion. More complex junction configurations lead to more complex dri…
Efficient Constrained Multi-Agent Trajectory Optimization using Dynamic Potential Games
Maulik Bhatt, Yixuan Jia, Negar Mehr
Although dynamic games provide a rich paradigm for modeling agents' interactions, solving these games for real-world applications is often challenging. Many real-world interactive…
MultiNash-PF: A Particle Filtering Approach for Computing Multiple Local Generalized Nash Equilibria in Trajectory Games
Maulik Bhatt, Iman Askari, Yue Yu +3
Modern robotic systems frequently engage in complex multi-agent interactions, many of which are inherently multi-modal, i.e., they can lead to multiple distinct outcomes. To intera…
Distributed Potential iLQR: Scalable Game-Theoretic Trajectory Planning for Multi-Agent Interactions
Zach Williams, Jushan Chen, Negar Mehr
In this work, we develop a scalable, local trajectory optimization algorithm that enables robots to interact with other robots. It has been shown that agents' interactions can be s…
Congestion-aware Bi-modal Delivery Systems Utilizing Drones
Mark Beliaev, Negar Mehr, Ramtin Pedarsani
Bi-modal delivery systems are a promising solution to the challenges posed by the increasing demand of e-commerce. Due to the potential benefit drones can have on logistics network…
Stackelberg Routing of Autonomous Cars in Mixed-Autonomy Traffic Networks
Maxwell Kolarich, Negar Mehr
As autonomous cars are becoming tangible technologies, road networks will soon be shared by human-driven and autonomous cars. However, humans normally act selfishly which may resul…
Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Masking
Alex Beaudin, Hanna Krasowski, Kartik Nagpal +3
Ensuring safety of learning-enabled robotic manipulation across diverse embodiments and tasks still requires significant manual engineering. Existing approaches typically rely on h…
Strategic Decision-Making in Multi-Agent Domains: A Weighted Constrained Potential Dynamic Game Approach
Maulik Bhatt, Yixuan Jia, Negar Mehr
In interactive multi-agent settings, decision-making and planning are challenging mainly due to the agents' interconnected objectives. Dynamic game theory offers a formal framework…
Pricing for Multi-modal Pickup and Delivery Problems with Heterogeneous Users
Mark Beliaev, Negar Mehr, Ramtin Pedarsani
In this paper, we study the pickup and delivery problem with multiple transportation modalities, and address the challenge of efficiently allocating transportation resources while…
Learning Contraction Policies from Offline Data
Navid Rezazadeh, Maxwell Kolarich, Solmaz S. Kia +1
This paper proposes a data-driven method for learning convergent control policies from offline data using Contraction theory. Contraction theory enables constructing a policy that…
A Game Theoretic Macroscopic Model of Bypassing at Traffic Diverges with Applications to Mixed Autonomy Networks
Negar Mehr, Ruolin Li, Roberto Horowitz
Vehicle bypassing is known to negatively affect delays at traffic diverges. However, due to the complexities of this phenomenon, accurate and yet simple models of such lane change…
RAPID: Autonomous Multi-Agent Racing using Constrained Potential Dynamic Games
Yixuan Jia, Maulik Bhatt, Negar Mehr
In this work, we consider the problem of autonomous racing with multiple agents where agents must interact closely and influence each other to compete. We model interactions among…
Learning to Influence Vehicles' Routing in Mixed-Autonomy Networks by Dynamically Controlling the Headway of Autonomous Cars
Xiaoyu Ma, Negar Mehr
It is known that autonomous cars can increase road capacities by maintaining a smaller headway through vehicle platooning. Recent works have shown that these capacity increases can…
Decentralized Role Assignment in Multi-Agent Teams via Empirical Game-Theoretic Analysis
Fengjun Yang, Negar Mehr, Mac Schwager
We propose a method, based on empirical game theory, for a robot operating as part of a team to choose its role within the team without explicitly communicating with team members,…
Understanding and Imitating Human-Robot Motion with Restricted Visual Fields
Maulik Bhatt, HongHao Zhen, Monroe Kennedy +1
When working around other agents such as humans, it is important to model their perception capabilities to predict and make sense of their behavior. In this work, we consider agent…
How Will the Presence of Autonomous Vehicles Affect the Equilibrium State of Traffic Networks?
Negar Mehr, Roberto Horowitz
It is known that connected and autonomous vehicles are capable of maintaining shorter headways and distances when they form platoons of vehicles. Thus, such technologies can result…
Congestion Games with Heterogeneous Valuations: An Optimal Transport Approach
Pan-Yang Su, Negar Mehr, Shankar Sastry
In emerging urban mobility and logistics applications, such as advanced air mobility, electric vehicle charging, and shared service systems, agents with heterogeneous valuations ch…
Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment
Kartik Nagpal, Dayi Dong, Jean-Baptiste Bouvier +1
Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared g…
Distributed NeRF Learning for Collaborative Multi-Robot Perception
Hongrui Zhao, Boris Ivanovic, Negar Mehr
Effective environment perception is crucial for enabling downstream robotic applications. Individual robotic agents often face occlusion and limited visibility issues, whereas mult…
Matching Multiple Experts: On the Exploitability of Multi-Agent Imitation Learning
Antoine Bergerault, Volkan Cevher, Negar Mehr
Multi-agent imitation learning (MA-IL) aims to learn optimal policies from expert demonstrations of interactions in multi-agent interactive domains. Despite existing guarantees on…
Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds
Kanghyun Ryu, Negar Mehr
Ensuring safe navigation in human-populated environments is crucial for autonomous mobile robots. Although recent advances in machine learning offer promising methods to predict hu…
Risk-Sensitive Orbital Debris Collision Avoidance using Distributionally Robust Chance Constraints
Kanghyun Ryu, Jean-Baptiste Bouvier, Shazaib Lalani +2
The exponential increase in orbital debris and active satellites will lead to congested orbits, necessitating more frequent collision avoidance maneuvers by satellites. To minimize…
To What Extent do Open-loop and Feedback Nash Equilibria Diverge in General-Sum Linear Quadratic Dynamic Games?
Chih-Yuan Chiu, Jingqi Li, Maulik Bhatt +1
Dynamic games offer a versatile framework for modeling the evolving interactions of strategic agents, whose steady-state behavior can be captured by the Nash equilibria of the game…
CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models
Kanghyun Ryu, Qiayuan Liao, Zhongyu Li +3
Curriculum learning is a training mechanism in reinforcement learning (RL) that facilitates the achievement of complex policies by progressively increasing the task difficulty duri…
Coordinated Science Laboratory 70th Anniversary Symposium: The Future of Computing
Klara Nahrstedt, Naresh Shanbhag, Vikram Adve +25
In 2021, the Coordinated Science Laboratory CSL, an Interdisciplinary Research Unit at the University of Illinois Urbana-Champaign, hosted the Future of Computing Symposium to cele…
Scaling Nonlinear Optimization: Many Problems One GPU
John Viljoen, Johanna Haffner, Masayoshi Tomizuka +1
Many robotics problems, including trajectory optimization, inverse kinematics, and contact-rich motion planning, reduce to nonlinear programs (NLPs). Mature NLP solvers such as IPO…
CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks
Seoyeon Choi, Kanghyun Ryu, Jonghoon Ock +1
Multi-Agent Reinforcement Learning (MARL) provides a powerful framework for learning coordination in multi-agent systems. However, applying MARL to robotics remains challenging due…
Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems
Aayushi Shrivastava, Kartik Nagpal, Sairam Jinkala +2
Ensuring safety for black-box hybrid dynamical systems presents significant challenges due to their instantaneous state jumps and unknown explicit nonlinear dynamics. Existing solu…
UDON: Uncertainty-weighted Distributed Optimization for Multi-Robot Neural Implicit Mapping under Extreme Communication Constraints
Hongrui Zhao, Xunlan Zhou, Boris Ivanovic +1
Multi-robot mapping with neural implicit representations enables the compact reconstruction of complex environments. However, it demands robustness against communication challenges…
Optimal Robotic Assembly Sequence Planning: A Sequential Decision-Making Approach
Kartik Nagpal, Negar Mehr
The optimal robot assembly planning problem is challenging due to the necessity of finding the optimal solution amongst an exponentially vast number of possible plans, all while sa…
TACO: Temporal Consensus Optimization for Continual Neural Mapping
Xunlan Zhou, Hongrui Zhao, Negar Mehr
Neural implicit mapping has emerged as a powerful paradigm for robotic navigation and scene understanding. However, real-world robotic deployment requires continual adaptation to c…
Weathering Ongoing Uncertainty: Learning and Planning in a Time-Varying Partially Observable Environment
Gokul Puthumanaillam, Xiangyu Liu, Negar Mehr +1
Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over tim…
Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds
Rohan Chandra, Haresh Karnan, Negar Mehr +2
Social robot navigation in crowded public spaces such as university campuses, restaurants, grocery stores, and hospitals, is an increasingly important area of research. One of the…
Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions
Negar Mehr, Mingyu Wang, Mac Schwager
In this paper, we study the problem of multiple stochastic agents interacting in a dynamic game scenario with continuous state and action spaces. We define a new notion of stochast…