activity
20182026
most citedWhen Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans

57 citations · 170 across the 34 of their papers we have counts for

collaborators
Showing cs.ROShow all

27 papers · 1 filter

cs.RO2026

ITA-LaCAM: A Complete and Scalable TAPF Solver via Assignment-Aware Configuration-Space Search

Yimin Tang, Han Zhang, Shao-Hung Chan +4

Combined Target Assignment and Path Finding (TAPF) requires assigning targets for agents while simultaneously planning collision-free paths. We present ITA-LaCAM, a complete and sc…

cs.RO2026

From LLM-Generated Specifications to Learned Quadruped Locomotion

Merve Atasever, Keyan Azbijari, Cagan Bakirci +5

Quadruped robot locomotion policies are often trained using reinforcement learning, which in turn relies heavily on hand-crafted reward functions. Designing reward functions requir…

cs.RO2026

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

Anthony Liang, Yigit Korkmaz, Jiahui Zhang +14

General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations, providing only local, frame-level supervision. While effecti…

cs.RO2026

SyncTwin: Fast Digital Twin Construction and Synchronization for Safe Robotic Manipulation

Ruopeng Huang, Boyu Yang, Wenlong Gui +3

Accurate and safe robotic manipulation under dynamic and visually occluded conditions remains a core challenge in real-world deployment. We introduce SyncTwin, a novel digital twin…

cs.RO2026

Judgelight: Trajectory-Level Post-Optimization for Multi-Agent Path Finding via Closed-Subwalk Collapsing

Yimin Tang, Sven Koenig, Erdem Bıyık

Multi-Agent Path Finding (MAPF) is an NP-hard problem with applications in warehouse automation and multi-robot coordination. Learning-based MAPF solvers offer fast and scalable pl…

cs.RO2025

AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations

Litian Gong, Fatemeh Bahrani, Yutai Zhou +3

AutoFocus-IL is a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rat…