Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration

TL;DR

This paper introduces a control framework combining learning and model-based control for accurate whole-body throwing with legged robots, achieving high precision and success rates surpassing humans in target hitting tasks.

Contribution

It presents a novel hybrid control system with a high-frequency residual policy and optimization module for improved throwing accuracy on hardware.

Findings

Achieved 0.28 m landing error at 6 m distance.

System success rate of 56.8% at 3-5 m targets.

Outperformed humans with a 15.2% success rate.

Abstract

Throwing is a fundamental skill that enables robots to manipulate objects in ways that extend beyond the reach of their arms. We present a control framework that combines learning and model-based control for prehensile whole-body throwing with legged mobile manipulators. Our framework consists of three components: a nominal tracking policy for the end-effector, a high-frequency residual policy to enhance tracking accuracy, and an optimization-based module to improve end-effector acceleration control. The proposed controller achieved the average of 0.28 m landing error when throwing at targets located 6 m away. Furthermore, in a comparative study with university students, the system achieved a velocity tracking error of 0.398 m/s and a success rate of 56.8%, hitting small targets randomly placed at distances of 3-5 m while throwing at a specified speed of 6 m/s. In contrast, humans have a success rate of only 15.2%. This work provides an early demonstration of prehensile throwing with quantified accuracy on hardware, contributing to progress in dynamic whole-body manipulation.