Collision-inclusive Manipulation Planning for Occluded Object Grasping via Compliant Robot Motions

2024-12-09

arXiv.org

AI Summary

In robotic manipulation, initial feasible grasp poses are often unavailable due to object occlusion, while significant perception and physical uncertainties further impede reliable grasping. Method: This paper proposes a collision-inclusive adaptive planning framework. It innovatively models intentional collisions as exploitable planning resources—not merely obstacles to avoid—and integrates Cartesian impedance control to robustly absorb modeling errors during contact. Coupling environment constraints with operation funnel learning, the approach enables uncertainty-driven perception–action co-planning. Operation funnels are iteratively constructed through task repetition, effectively mitigating uncertainties in both physical modeling and visual perception. Contribution/Results: Evaluated on real-world single-arm and dual-arm robotic platforms, the method achieves substantially improved grasp success rates under severe occlusion and demonstrates strong generalization across diverse objects and configurations.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

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

Traditional robotic manipulation mostly focuses on collision-free tasks. In practice, however, many manipulation tasks (e.g., occluded object grasping) require the robot to intentionally collide with the environment to reach a desired task configuration. By enabling compliant robot motions, collisions between the robot and the environment are allowed and can thus be exploited, but more physical uncertainties are introduced. To address collision-rich problems such as occluded object grasping while handling the involved uncertainties, we propose a collision-inclusive planning framework that can transition the robot to a desired task configuration via roughly modeled collisions absorbed by Cartesian impedance control. By strategically exploiting the environmental constraints and exploring inside a manipulation funnel formed by task repetitions, our framework can effectively reduce physical and perception uncertainties. With real-world evaluations on both single-arm and dual-arm setups, we show that our framework is able to efficiently address various realistic occluded grasping problems where a feasible grasp does not initially exist.

Problem

• Planning compliant robot motions to exploit intentional collisions
• Reducing uncertainties in occluded object grasping tasks
• Enabling grasping via environmental constraints and impedance control

Innovation

• Compliant robot motions with Cartesian impedance control
• Collision-inclusive planning framework exploiting environmental constraints
• Manipulation funnel exploration to reduce physical uncertainties