Leg ODOmetry
Leg odometry, the process of estimating a robot's position and orientation using leg movement data, is a crucial component of autonomous navigation, particularly in challenging environments where GPS is unavailable. Current research emphasizes improving accuracy and robustness through sensor fusion (e.g., combining leg odometry with LiDAR, radar, IMUs, and cameras), advanced algorithms like Kalman filters and Gaussian processes, and the development of novel neural network architectures for kinematic model learning and point cloud processing. These advancements are significant for enhancing the reliability and precision of robotic systems in various applications, including autonomous driving, exploration, and search and rescue.
Papers
Multi-Camera Visual-Inertial Simultaneous Localization and Mapping for Autonomous Valet Parking
Marcus Abate, Ariel Schwartz, Xue Iuan Wong, Wangdong Luo, Rotem Littman, Marc Klinger, Lars Kuhnert, Douglas Blue, Luca Carlone
AdaLIO: Robust Adaptive LiDAR-Inertial Odometry in Degenerate Indoor Environments
Hyungtae Lim, Daebeom Kim, Beomsoo Kim, Hyun Myung