Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal

Abstract

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be prohibitively costly to obtain on robots in the real world. We present an approach for efficiently learning goal-directed navigation policies on a mobile robot, from only a single coverage traversal of recorded data. The navigation agent learns an effective policy over a diverse action space in a large heterogeneous environment consisting of more than 2km of travel, through buildings and outdoor regions that collectively exhibit large variations in visual appearance, self-similarity, and connectivity. We compare pretrained visual encoders that enable precomputation of visual embeddings to achieve a throughput of tens of thousands of transitions per second at training time on a commodity desktop computer, allowing agents to learn from millions of trajectories of experience in a matter of hours. We propose multiple forms of computationally efficient stochastic augmentation to enable the learned policy to generalise beyond these precomputed embeddings, and demonstrate successful deployment of the learned policy on the real robot without fine tuning, despite environmental appearance differences at test time. The dataset and code required to reproduce these results and apply the technique to other datasets and robots is made publicly available at rl-navigation.github.io/deployable.

References in corpus (7)

• Continuous control with deep reinforcement learning
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Neural SLAM: Learning to Explore with External Memory
• Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation
• Unifying Map and Landmark Based Representations for Visual Navigation
• One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

Cited by in corpus (7)

• ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints
• Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience
• Where are the Keys? -- Learning Object-Centric Navigation Policies on Semantic Maps with Graph Convolutional Networks
• Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation
• Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning
• Topological Navigation Graph Framework
• Sim-to-Real Transfer of Robot Learning with Variable Length Inputs