Online LiDAR-SLAM for Legged Robots with Robust Registration and Deep-Learned Loop Closure
This work addresses localization and mapping for legged robots in poorly lit, indistinct industrial settings, representing an incremental improvement by integrating deep learning into existing SLAM frameworks for specific deployment constraints.
The paper tackled the problem of enabling legged robots to localize and map in challenging industrial environments using only LiDAR sensing, by developing a factor-graph LiDAR-SLAM system with a deeply learned loop closure detector that runs in real-time on the robot's CPU, resulting in demonstrated robustness and flexibility in autonomous path following.
In this paper, we present a factor-graph LiDAR-SLAM system which incorporates a state-of-the-art deeply learned feature-based loop closure detector to enable a legged robot to localize and map in industrial environments. These facilities can be badly lit and comprised of indistinct metallic structures, thus our system uses only LiDAR sensing and was developed to run on the quadruped robot's navigation PC. Point clouds are accumulated using an inertial-kinematic state estimator before being aligned using ICP registration. To close loops we use a loop proposal mechanism which matches individual segments between clouds. We trained a descriptor offline to match these segments. The efficiency of our method comes from carefully designing the network architecture to minimize the number of parameters such that this deep learning method can be deployed in real-time using only the CPU of a legged robot, a major contribution of this work. The set of odometry and loop closure factors are updated using pose graph optimization. Finally we present an efficient risk alignment prediction method which verifies the reliability of the registrations. Experimental results at an industrial facility demonstrated the robustness and flexibility of our system, including autonomous following paths derived from the SLAM map.