An Efficient Locally Reactive Controller for Safe Navigation in Visual Teach and Repeat Missions
This addresses the safety issue for mobile robots in dynamic or obstructed environments, though it is an incremental improvement on existing VT&R systems.
The paper tackles the problem of safe navigation for mobile robots in changing environments by developing a locally reactive controller for Visual Teach and Repeat systems, demonstrating that it keeps the robot safe in cluttered indoor spaces and underground mines with a runtime of <2 ms on a CPU.
To achieve successful field autonomy, mobile robots need to freely adapt to changes in their environment. Visual navigation systems such as Visual Teach and Repeat (VT&R) often assume the space around the reference trajectory is free, but if the environment is obstructed path tracking can fail or the robot could collide with a previously unseen obstacle. In this work, we present a locally reactive controller for a VT&R system that allows a robot to navigate safely despite physical changes to the environment. Our controller uses a local elevation map to compute vector representations and outputs twist commands for navigation at 10 Hz. They are combined in a Riemannian Motion Policies (RMP) controller that requires <2 ms to run on a CPU. We integrated our controller with a VT&R system onboard an ANYmal C robot and tested it in indoor cluttered spaces and a large-scale underground mine. We demonstrate that our locally reactive controller keeps the robot safe when physical occlusions or loss of visual tracking occur such as when walking close to walls, crossing doorways, or traversing narrow corridors. Video: https://youtu.be/G_AwNec5AwU