CushionCatch: A Compliant Catching Mechanism for Mobile Manipulators via Combined Optimization and Learning

TL;DR

This paper introduces CushionCatch, a novel framework combining optimization and learning to enable mobile manipulators to catch flying objects with compliant strategies, achieving high success rates and reduced impact forces.

Contribution

It presents a new integrated approach with a high-level planner, a learning-based compliant catching strategy, and collision avoidance, advancing robotic catching capabilities.

Findings

98.70% success rate in simulation

92.59% success rate in real-world tests

28.7% reduction in impact torques

Abstract

Catching flying objects with a cushioning process is a skill commonly performed by humans, yet it remains a significant challenge for robots. In this paper, we present a framework that combines optimization and learning to achieve compliant catching on mobile manipulators (CCMM). First, we propose a high-level capture planner for mobile manipulators (MM) that calculates the optimal capture point and joint configuration. Next, the pre-catching (PRC) planner ensures the robot reaches the target joint configuration as quickly as possible. To learn compliant catching strategies, we propose a network that leverages the strengths of LSTM for capturing temporal dependencies and positional encoding for spatial context (P-LSTM). This network is designed to effectively learn compliant strategies from human demonstrations. Following this, the post-catching (POC) planner tracks the compliant sequence output by the P-LSTM while avoiding potential collisions due to structural differences between humans and robots. We validate the CCMM framework through both simulated and real-world ball-catching scenarios, achieving a success rate of 98.70% in simulation, 92.59% in real-world tests, and a 28.7% reduction in impact torques. The open source code has be released for the reference of the community.