BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can he insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience. Our reinforcement learning approach, which we call BADGR , is an end-to-end learning-based mobile robot navigation system that can be trained with autonomously-labeled off-policy data gathered in real-world environments, without any simulation or human supervision. BADGR can navigate in real-world urban and off-road environments with geometrically distracting obstacles. It can also incorporate terrain preferences, generalize to novel environments, and continue to improve autonomously by gathering more data. Videos, code, and other supplemental material are available on our website https://sites.google.com/view/badgr

Automated summary

Traditional mobile robot navigation solutions focus on the geometric structure of the environment, but this approach may not always be effective. BADGR utilizes a reinforcement learning approach to move beyond purely geometric navigation solutions, learning physical navigational affordances in order to navigate mobile robots without the need for simulation or human supervision.