LaND: Learning to Navigate from Disengagements

TL;DR

LaND is a reinforcement learning method that enables autonomous robots to learn navigation by using disengagement signals as a learning signal, improving real-world sidewalk navigation safety and performance.

Contribution

This paper introduces LaND, a novel reinforcement learning approach that learns from disengagements to improve autonomous navigation in real-world environments.

Findings

LaND outperforms imitation learning and reinforcement learning baselines.

Successfully navigates diverse real-world sidewalk environments.

Uses disengagements as a direct learning signal for navigation improvement.

Abstract

Consistently testing autonomous mobile robots in real world scenarios is a necessary aspect of developing autonomous navigation systems. Each time the human safety monitor disengages the robot's autonomy system due to the robot performing an undesirable maneuver, the autonomy developers gain insight into how to improve the autonomy system. However, we believe that these disengagements not only show where the system fails, which is useful for troubleshooting, but also provide a direct learning signal by which the robot can learn to navigate. We present a reinforcement learning approach for learning to navigate from disengagements, or LaND. LaND learns a neural network model that predicts which actions lead to disengagements given the current sensory observation, and then at test time plans and executes actions that avoid disengagements. Our results demonstrate LaND can successfully learn to navigate in diverse, real world sidewalk environments, outperforming both imitation learning and reinforcement learning approaches. Videos, code, and other material are available on our website https://sites.google.com/view/sidewalk-learning