🤖 AI Summary
This work addresses the challenge of achieving compliant buffering during high-speed aerial object capture by mobile manipulators. Methodologically, it introduces an end-to-end compliant grasping framework integrating optimization and learning: (1) joint optimization of capture-point planning and pre-grasp motion; (2) a position-encoded LSTM (P-LSTM) to model spatiotemporal compliance policies, enabling effective imitation of human demonstrations; and (3) real-time collision-aware post-grasp trajectory tracking. To the best of our knowledge, this is the first framework achieving closed-loop compliant capture—from planning to execution—on mobile manipulators. Evaluations show a 98.70% success rate in simulation and 92.59% on physical hardware, with a 28.7% reduction in impact torque. The implementation is publicly available.
📝 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 will be released for the reference of the community.