IMA-Catcher: An IMpact-Aware Nonprehensile Catching Framework based on Combined Optimization and Learning

2025-06-25

AI Summary

High-impact forces during aerial object capture often cause task failure and hardware damage—especially when the object-to-robot mass ratio increases. Method: This paper proposes a non-grasping, compliant capture framework that jointly addresses pre- and post-contact phases. It innovatively integrates implicit impact-aware real-time optimal trajectory planning with human-demonstration-based impedance learning, using reflected inertia minimization as a secondary optimization objective to achieve end-effector velocity matching and adaptive stiffness modulation. The approach combines dynamics-constrained modeling with hierarchical quadratic programming control. Results: Experiments in 1D and multi-axis settings demonstrate significant reductions in joint torque and rebound effects. The method achieves stable high-impact capture even without prior knowledge of object velocity, thereby enhancing system robustness, generalizability, and safety.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robotic catching of flying objects typically generates high impact forces that might lead to task failure and potential hardware damages. This is accentuated when the object mass to robot payload ratio increases, given the strong inertial components characterizing this task. This paper aims to address this problem by proposing an implicitly impact-aware framework that accomplishes the catching task in both pre- and post-catching phases. In the first phase, a motion planner generates optimal trajectories that minimize catching forces, while in the second, the object's energy is dissipated smoothly, minimizing bouncing. In particular, in the pre-catching phase, a real-time optimal planner is responsible for generating trajectories of the end-effector that minimize the velocity difference between the robot and the object to reduce impact forces during catching. In the post-catching phase, the robot's position, velocity, and stiffness trajectories are generated based on human demonstrations when catching a series of free-falling objects with unknown masses. A hierarchical quadratic programming-based controller is used to enforce the robot's constraints (i.e., joint and torque limits) and create a stack of tasks that minimizes the reflected mass at the end-effector as a secondary objective. The initial experiments isolate the problem along one dimension to accurately study the effects of each contribution on the metrics proposed. We show how the same task, without velocity matching, would be infeasible due to excessive joint torques resulting from the impact. The addition of reflected mass minimization is then investigated, and the catching height is increased to evaluate the method's robustness. Finally, the setup is extended to catching along multiple Cartesian axes, to prove its generalization in space.

Problem

• Minimize impact forces during robotic catching of flying objects
• Smoothly dissipate object energy post-catching to reduce bouncing
• Handle varying object masses with real-time optimal motion planning

Innovation

• Impact-aware motion planner minimizes catching forces
• Hierarchical controller enforces constraints and tasks
• Learning from human demonstrations for post-catching