Publication

Robotics: Science and Systems (RSS) 2025

2025 IEEE International Conference on Robotics and Automation (ICRA)

Abstract Ergodic coverage effectively generates exploratory behaviors for embodied agents by aligning the spatial distribution of the agent's trajectory with a target distribution, where the difference between these two distributions is measured by the ergodic metric.

-- Abstract Game-theoretic models are effective tools for modeling multi-agent interactions, especially when robots need to coordinate with humans. However, applying these models requires inferring their specifications from observed behaviors---a challenging task known as the inverse game problem.

Abstract Ergodic search enables optimal exploration of an information distribution while guaranteeing the asymptotic coverage of the search space. However, current methods typically have exponential computation complexity in the search space dimension and are restricted to Euclidean space.

Update Recently, Katie Hughes, a master of science in robotics student at Northwestern University, deployed our social navigation algorithm on an untethered Unitree Go1 quadruped and tested it in a densely packed atrium.

IEEE Transactions on Robotics (T-RO), 2025

The International Journal of Robotics Research (IJRR), 2024

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Abstract Gait generation for soft robots is challenging due to the nonlinear dynamics and high dimensional input spaces of soft actuators. Limitations in soft robotic control and perception force researchers to hand-craft open loop controllers for gait sequences, which is a non-trivial process.