A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation

2026-01-16

AI Summary

This work proposes a framework based on adaptive affordance learning to address the challenges of dual-arm robotic coordination in furniture assembly, particularly the difficulties in adapting to diverse geometric shapes and dynamically adjusting support strategies. By leveraging dense point clouds for fine-grained geometric modeling of parts, the method identifies optimal support and stable regions, and dynamically refines bimanual collaboration through interactive feedback. Integrated with sim-to-real transfer techniques, the system is trained in a simulated environment encompassing eight furniture categories and fifty distinct components, and successfully generalizes to real-world tasks. The approach significantly improves assembly success rates, demonstrating strong generalization across complex geometries and robust adaptability in long-horizon manipulation tasks.

Technology Category

• Intelligent Robots: Manipulation
• Multiagent Systems: Coordination and Collaboration
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Furniture assembly is a crucial yet challenging task for robots, requiring precise dual-arm coordination where one arm manipulates parts while the other provides collaborative support and stabilization. To accomplish this task more effectively, robots need to actively adapt support strategies throughout the long-horizon assembly process, while also generalizing across diverse part geometries. We propose A3D, a framework which learns adaptive affordances to identify optimal support and stabilization locations on furniture parts. The method employs dense point-level geometric representations to model part interaction patterns, enabling generalization across varied geometries. To handle evolving assembly states, we introduce an adaptive module that uses interaction feedback to dynamically adjust support strategies during assembly based on previous interactions. We establish a simulation environment featuring 50 diverse parts across 8 furniture types, designed for dual-arm collaboration evaluation. Experiments demonstrate that our framework generalizes effectively to diverse part geometries and furniture categories in both simulation and real-world settings.

Problem

• dual-arm manipulation
• furniture assembly
• adaptive support
• affordance learning
• geometric generalization

Innovation

• adaptive affordance
• dual-arm manipulation
• geometric generalization
• interactive feedback
• furniture assembly