6 papers
UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning
Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang +1
Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods…
OSCAR: Obstacle Survival Curves for Adaptive Robot Navigation
Hshmat Sahak, Aoran Jiao, Nicholas Rhinehart +1
A mobile robot following a graph of known routes can make costly navigation errors when a temporary obstacle blocks a critical edge: waiting too long behind a parked cart wastes ti…
AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models
Mozhgan Pourkeshavarz, Mozhgan Pourkeshavatz, Tianran Liu +1
Simulation with realistic traffic agents is essential for validating autonomous driving systems. Existing data-driven simulators learn agent behavior from higher-level abstractions…
OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models
Tianran Liu, Shengwen Zhao, Mozhgan Pourkeshavarz +2
Data-driven autonomous driving simulation has long been constrained by its heavy reliance on pre-recorded driving logs or spatial priors, such as HD maps. This fundamental dependen…
Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigation
James R. Han, Mithun Vanniasinghe, Hshmat Sahak +2
Scaling Reinforcement Learning to in-the-wild social robot navigation is both data-intensive and unsafe, since policies must learn through direct interaction and inevitably encount…
DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation
James R. Han, Hugues Thomas, Jian Zhang +2
How can a robot safely navigate around people with complex motion patterns? Deep Reinforcement Learning (DRL) in simulation holds some promise, but much prior work relies on simula…