Event
TRAIN: A Reinforcement Learning-Based Terrain-Aware Navigation Framework for Quadruped Robots
1 reports · 1 sources
An arXiv paper proposes TRAIN, a two-stage deep reinforcement learning framework that enables quadruped robots to achieve terrain-aware navigation in unstructured terrain and populated environments through two pipelines, TRAIN-Loco and TRAIN-Nav. Benchmarks compare against quadruped locomotion and robot navigation baselines, and hardware experiments validate its sim-to-real transfer potential.
Report timeline
- TRAIN: A reinforcement learning framework for terrain-aware interactive navigation for quadruped robots
TRAIN proposes a two-stage deep reinforcement learning framework that, through the TRAIN-Loco and TRAIN-Nav pipelines, enables quadruped robots to achieve terrain-aware navigation in unstructured terrain and human-populated environments. Benchmarks compared quadruped locomotion and robot navigation baselines, and hardware experiments verified its sim-to-real transfer potential.
arXiv cs.RO ·