Reproduce “Tightly-Coupled LiDAR-IMU-Leg Odometry with Online Learned Leg Kinematics Incorporating Foot Tactile Information” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Taku Okawara, Kenji Koide, Aoki Takanose, Shuji Oishi, Masashi Yokozuka, Kentaro Uno, Kazuya Yoshida

The authors present legged-robot odometry that adapts a learned motion model using foot-force cues, jointly optimizing it with LiDAR, IMU, and robot motion in a factor graph. On the Go2, joint torques proxy for reaction force. Campus ATE was 0.29 ± 0.12 m versus 0.63 ± 0.30 m without tactile input; on sand, accuracy nearly matched.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.