SmoothTurn: Learning to Turn Smoothly for Agile Navigation with Quadrupedal Robots

TL;DR

This paper introduces SmoothTurn, a learning-based control framework enabling quadrupedal robots to navigate sequential goals smoothly and agilely, improving their ability to change directions rapidly while maintaining momentum in real-world scenarios.

Contribution

The paper presents a novel framework with a sequential goal-reaching reward, lookahead observation space, and automatic curriculum for smooth, agile navigation in quadrupedal robots.

Findings

Robust real-world deployment on quadrupedal robots.

Enhanced smooth turning and momentum control during goal switches.

Improved path planning and agility in simulation and real-world tests.

Abstract

Quadrupedal robots show great potential for valuable real-world applications such as fire rescue and industrial inspection. Such applications often require urgency and the ability to navigate agilely, which in turn demands the capability to change directions smoothly while running in high speed. Existing approaches for agile navigation typically learn a single-goal reaching policy by encouraging the robot to stay at the target position after reaching there. As a result, when the policy is used to reach sequential goals that require changing directions, it cannot anticipate upcoming maneuvers or maintain momentum across the switch of goals, thereby preventing the robot from fully exploiting its agility potential. In this work, we formulate the task as sequential local navigation, extending the single-goal-conditioned local navigation formulation in prior work. We then introduce SmoothTurn, a learning-based control framework that learns to turn smoothly while running rapidly for agile sequential local navigation. The framework adopts a novel sequential goal-reaching reward, an expanded observation space with a lookahead window for future goals, and an automatic goal curriculum that progressively expands the difficulty of sampled goal sequences based on the goal-reaching performance. The trained policy can be directly deployed on real quadrupedal robots with onboard sensors and computation. Both simulation and real-world empirical results show that SmoothTurn learns an agile locomotion policy that performs smooth turning across goals, with emergent behaviors such as controlling momentum when switching goals, facing towards the future goal in advance, and planning efficient paths. We have provided video demos of the learned motions in the supplementary materials. The source code and trained policies will be made available upon acceptance.