Aerial GRIPPER: A Gradient-based Real-time Inverse-game Predictor and Planner

2026-09-28

AI Summary

This study addresses the challenge of real-time, precise capture of non-cooperative targets by developing an aerial grasping system that models human-robot interaction as a game with incomplete information. Methodologically, the target’s cost parameters are inferred online to iteratively optimize Nash equilibrium strategies. The core innovation lies in a Hessian-inverse-free gradient-based inverse game solver that integrates implicit differentiation, fast Hessian-vector products, and disturbance-rejecting receding horizon control, enabling high-frequency planning exceeding 50 Hz. Both simulation and hardware experiments demonstrate that the proposed system achieves superior computational efficiency while significantly enhancing robustness and adaptability in adversarial scenarios, successfully accomplishing precise capture and delivery tasks involving non-cooperative targets.

Abstract

Accurate capture of non-cooperative targets is critical. In an attempt to tackle this intractable challenge, an aerial gripper system integrated with a Gradient-based Real-time Inverse-game Predictor and PlannER (GRIPPER) framework is proposed. The interaction is formulated as a general-sum pursuit-evasion game under incomplete information. Specifically, underlying cost parameters of the target are inferred online, and the open-loop Nash equilibrium (OLNE) strategy is iteratively refined within a receding-horizon loop. To ensure high-frequency execution, a computationally friendly gradient-based inverse-game solver is developed. Without explicit computation of the Hessian inverse, the optimized solution is updated (> 50 Hz) based on implicit differentiation and fast Hessian-vector products. Meanwhile, an anti-disturbance controller is developed to overcome disturbances of uncertain payload and gripper actuation, enabling precise tracking of the planned trajectory and accurate grasping of the target. Simulations and real-world experiments illustrate the superior computational efficiency and task performance of GRIPPER. The task of capturing and delivering a non-cooperative target is accomplished, highlighting the robustness, adaptability, and real-time performance of the framework in highly adversarial scenarios.

Problem

• non-cooperative target capture
• pursuit-evasion game
• real-time planning
• aerial gripper
• anti-disturbance control

Innovation

• Inverse-game theory
• Pursuit-evasion game
• Implicit differentiation
• Real-time planning
• Anti-disturbance control