activity
20242026
collaborators

6 papers

cs.RO2026

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…

cs.RO2025

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…

cs.MA2025

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…

eess.SY2024

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…

cs.RO2024

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…

eess.SY2024

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…