SOURCE-LINKED INTELLIGENCE

SleepWalking: Privileged Representation Shaping for End-to-End Blind Locomotion in Legged Robots

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Partially observable locomotion requires a policy to act when task-relevant properties of the robot--environment state are not fully specified by instantaneous observations. Existing approaches often address this challenge by explicitly estimating missing physical variables or processing extended observation histories through structured architectures. We take a different view: partial observability is fundamentally an information-retention problem. The decisive question is not how task-relevant information enters the network, but whether the policy's internal state retains it. Guided by this p

Read original source ↗ Open in workspace

recordType

paper

region

Global