Legged Robot State Estimation using Invariant Kalman Filtering and Learned Contact Events
This enables robust proprioceptive odometry for legged robots in perceptually degraded environments, though it is incremental as it builds on existing invariant Kalman filtering methods.
The paper tackles the problem of legged robot state estimation without physical contact sensors by developing a learning-based contact estimator using multi-modal proprioceptive data, and shows that it generates accurate odometry trajectories comparable to a state-of-the-art visual SLAM system.
This work develops a learning-based contact estimator for legged robots that bypasses the need for physical sensors and takes multi-modal proprioceptive sensory data as input. Unlike vision-based state estimators, proprioceptive state estimators are agnostic to perceptually degraded situations such as dark or foggy scenes. While some robots are equipped with dedicated physical sensors to detect necessary contact data for state estimation, some robots do not have dedicated contact sensors, and the addition of such sensors is non-trivial without redesigning the hardware. The trained network can estimate contact events on different terrains. The experiments show that a contact-aided invariant extended Kalman filter can generate accurate odometry trajectories compared to a state-of-the-art visual SLAM system, enabling robust proprioceptive odometry.