Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot

TL;DR

This paper presents a hierarchical reinforcement learning framework enabling a quadrupedal robot to perform precise soccer shooting in real-world conditions, addressing control, planning, and dynamic challenges.

Contribution

It introduces a novel hierarchical RL approach combining motion control and planning for legged robots to execute accurate soccer shots.

Findings

Successfully deployed on A1 robot in real-world tests.

Achieved accurate shooting to random targets.

Demonstrated robustness in dynamic and uncertain conditions.

Abstract

We address the problem of enabling quadrupedal robots to perform precise shooting skills in the real world using reinforcement learning. Developing algorithms to enable a legged robot to shoot a soccer ball to a given target is a challenging problem that combines robot motion control and planning into one task. To solve this problem, we need to consider the dynamics limitation and motion stability during the control of a dynamic legged robot. Moreover, we need to consider motion planning to shoot the hard-to-model deformable ball rolling on the ground with uncertain friction to a desired location. In this paper, we propose a hierarchical framework that leverages deep reinforcement learning to train (a) a robust motion control policy that can track arbitrary motions and (b) a planning policy to decide the desired kicking motion to shoot a soccer ball to a target. We deploy the proposed framework on an A1 quadrupedal robot and enable it to accurately shoot the ball to random targets in the real world.