Article

LSMM: Learning Spatial Memory for End-to-End Legged Robot Exploration

The authors propose Local Spatial Matrix Memory (LSMM) based on Hadamard memory, which lets reinforcement learning agents store task-relevant information in position-based memory cells. On an autonomous maze exploration task, LSMM's maze coverage is comparable to strong recurrent networks and finite-history baselines, and it is the only architecture that remembers the maze layout, reducing reconstruction error to one third. The work targets the problem that humanoid and legged robots in complex environments need to remember information long after it leaves their field of view before it is used.

Part of the event: LSMM Spatial Memory Architecture for Legged Robot Maze Exploration

This page provides a summary and source link only.