An Efficient Locally Reactive Controller for Safe Navigation in Visual Teach and Repeat Missions
Open Access
- 14 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 2353-2360
Abstract
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 $10 \,\mathrm{Hz}$ . They are combined in a Riemannian Motion Policies (RMP) controller that requires $< $ $2 \,\mathrm{m}\mathrm{s}$ 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.Keywords
All Related Versions
Funding Information
- ESPRC/UKRI ORCA Robotics Hub (EP/R026173/1)
- EU H2020 Project MEMMO (780684)
- Royal Society University Research Fellowship
- ANID/DOCTORADO BECAS CHILE (2019-72200291)
This publication has 33 references indexed in Scilit:
- Driving on Point Clouds: Motion Planning, Trajectory Optimization, and Terrain Assessment in Generic Nonplanar EnvironmentsJournal of Field Robotics, 2016
- Robust Constrained Learning-based NMPC enabling reliable mobile robot path trackingThe International Journal of Robotics Research, 2016
- A Universal Grid Map Library: Implementation and Use Case for Rough Terrain Navigation2016
- Scene understanding for a high-mobility walking robot2015
- Practice makes perfect? Managing and leveraging visual experiences for lifelong navigation2012
- Geodesic Methods in Computer Vision and GraphicsFoundations and Trends in Computer Graphics and Vision, 2010
- Visual teach and repeat for long‐range rover autonomyJournal of Field Robotics, 2010
- An Image Inpainting Technique Based on the Fast Marching MethodJournal of Graphics Tools, 2004
- A fast marching level set method for monotonically advancing fronts.Proceedings of the National Academy of Sciences, 1996
- Contrast Limited Adaptive Histogram Equalization1994