A robust and compliant robotic assembly control strategy for batch precision assembly task with uncertain fit types and fit amounts

2025-08-17

AI Summary

In high-precision batch assembly, machining tolerances induce uncertainty in fit type (clearance/transition/interference) and fit magnitude, rendering conventional control strategies insufficient in robustness and compliance. To address this, we propose a robust and compliant control method based on multi-teacher policy distillation: the uncertain assembly task is decomposed into multiple deterministic subtasks, and heterogeneous policy knowledge is fused into a unified control network. Furthermore, we design a force-vision fusion controller-driven multi-task reinforcement learning framework (FVFC-MTRL) to enable joint training. Experiments demonstrate that our method achieves over 98% assembly success rate across diverse fit scenarios, improves force control accuracy by 40%, and accelerates training efficiency by 2.3×, significantly enhancing policy generalizability and engineering applicability.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Machine Learning: Adversarial Learning & Robustness
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In some high-precision industrial applications, robots are deployed to perform precision assembly tasks on mass batches of manufactured pegs and holes. If the peg and hole are designed with transition fit, machining errors may lead to either a clearance or an interference fit for a specific pair of components, with uncertain fit amounts. This paper focuses on the robotic batch precision assembly task involving components with uncertain fit types and fit amounts, and proposes an efficient methodology to construct the robust and compliant assembly control strategy. Specifically, the batch precision assembly task is decomposed into multiple deterministic subtasks, and a force-vision fusion controller-driven reinforcement learning method and a multi-task reinforcement learning training method (FVFC-MTRL) are proposed to jointly learn multiple compliance control strategies for these subtasks. Subsequently, the multi-teacher policy distillation approach is designed to integrate multiple trained strategies into a unified student network, thereby establishing a robust control strategy. Real-world experiments demonstrate that the proposed method successfully constructs the robust control strategy for high-precision assembly task with different fit types and fit amounts. Moreover, the MTRL framework significantly improves training efficiency, and the final developed control strategy achieves superior force compliance and higher success rate compared with many existing methods.

Problem

• Robotic assembly control for uncertain fit types and amounts
• Force-vision fusion and reinforcement learning for compliance
• Multi-teacher policy distillation for robust control strategy

Innovation

• Force-vision fusion controller-driven reinforcement learning
• Multi-task reinforcement learning for compliance control
• Multi-teacher policy distillation for unified strategy