Preprint
Aug 2026
Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids
A reinforcement-learning-based perceptive control system that operates directly on observations from a head-mounted solid-state lidar, consuming the raw lidar scan through an attention-based encoder with recurrent memory to extract task-relevant geometry from the sparse returns.
Efe Ongan, Chong Zhang, Bo-Yang Sun et al.
· 0 citations