Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments

TL;DR

This paper introduces PRELUDE, a hierarchical learning framework enabling quadrupedal robots to navigate dynamically cluttered environments by combining imitation learning for high-level decisions and reinforcement learning for gait control, demonstrated in simulation and hardware.

Contribution

The novel hierarchical framework PRELUDE integrates imitation and reinforcement learning for perceptive quadrupedal locomotion in dynamic environments.

Findings

Effective in simulation and hardware experiments

Learns complex navigation behaviors from human demonstrations

Discover versatile gaits through trial and error

Abstract

We tackle the problem of perceptive locomotion in dynamic environments. In this problem, a quadrupedal robot must exhibit robust and agile walking behaviors in response to environmental clutter and moving obstacles. We present a hierarchical learning framework, named PRELUDE, which decomposes the problem of perceptive locomotion into high-level decision-making to predict navigation commands and low-level gait generation to realize the target commands. In this framework, we train the high-level navigation controller with imitation learning on human demonstrations collected on a steerable cart and the low-level gait controller with reinforcement learning (RL). Therefore, our method can acquire complex navigation behaviors from human supervision and discover versatile gaits from trial and error. We demonstrate the effectiveness of our approach in simulation and with hardware experiments. Videos and code can be found at the project page: https://ut-austin-rpl.github.io/PRELUDE.