Building Gradient by Gradient: Decentralised Energy Functions for Bimanual Robot Assembly

2025-10-06

AI Summary

For high-precision, contact-intensive assembly tasks with dual-arm robots, challenges include strong task-sequence dependency, slow replanning under dynamic disturbances, and difficulty in multi-robot coordination. This paper proposes a decentralized, gradient-driven planning framework that eliminates explicit task-sequence modeling. Instead, it constructs piecewise-continuous energy fields via adaptive composition of potential functions, enabling distributed gradient-based optimization to generate sub-goals and drive coordinated motion. The framework inherently supports millisecond-scale reactive replanning and autonomously emergent behaviors—including retrying, handover, and rich-contact coordination—without centralized supervision. Evaluated on a physical dual-arm robotic platform, the method demonstrates robust performance in tight-tolerance assembly tasks, achieving millisecond-level dynamic response and significantly enhancing autonomy and adaptability for complex assembly operations.

Technology Category

• Intelligent Robots: Motion and Path Planning
• 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
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

There are many challenges in bimanual assembly, including high-level sequencing, multi-robot coordination, and low-level, contact-rich operations such as component mating. Task and motion planning (TAMP) methods, while effective in this domain, may be prohibitively slow to converge when adapting to disturbances that require new task sequencing and optimisation. These events are common during tight-tolerance assembly, where difficult-to-model dynamics such as friction or deformation require rapid replanning and reattempts. Moreover, defining explicit task sequences for assembly can be cumbersome, limiting flexibility when task replanning is required. To simplify this planning, we introduce a decentralised gradient-based framework that uses a piecewise continuous energy function through the automatic composition of adaptive potential functions. This approach generates sub-goals using only myopic optimisation, rather than long-horizon planning. It demonstrates effectiveness at solving long-horizon tasks due to the structure and adaptivity of the energy function. We show that our approach scales to physical bimanual assembly tasks for constructing tight-tolerance assemblies. In these experiments, we discover that our gradient-based rapid replanning framework generates automatic retries, coordinated motions and autonomous handovers in an emergent fashion.

Problem

• Addresses bimanual robot assembly challenges with high-level sequencing and coordination
• Solves slow convergence in task planning when adapting to disturbances
• Eliminates need for explicit task sequences in tight-tolerance assembly operations

Innovation

• Decentralized gradient-based framework for bimanual assembly
• Piecewise continuous energy function composition
• Myopic optimization generates emergent coordinated motions