Diffusion-Based Optimization for Accelerated Convergence of Redundant Dual-Arm Minimum Time Problems

2026-04-17

AI Summary

This study addresses the minimum-time trajectory planning problem for redundant dual-arm robots executing a prescribed relative Cartesian path, where existing methods struggle to efficiently enforce global L∞ error constraints. To overcome this challenge, this work introduces diffusion mechanisms into time-optimal control for the first time, proposing a model-based diffusion optimization framework that integrates probabilistic sampling with a bilevel optimization architecture. This approach effectively handles high-level non-convexities and mitigates gradient sparsity limitations, while explicitly accommodating L∞ error bounds throughout the trajectory. Compared to prior methods, the proposed framework achieves a 35-fold improvement in computational efficiency and reduces path-tracking error by 34%.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present a framework leveraging a novel variant of the model-based diffusion algorithm to minimize the time required for a redundant dual-arm robot configuration to follow a desired relative Cartesian path. Our prior work proposed a bi-level optimization approach for the dual-arm problem, where we derived the analytical solution to the lower-level convex sub-problem and solved the high-level nonconvex problem using a primal-dual approach. However, the gradient-based nature leads to a large computation overhead, and it prohibits directly imposing an $L_{\infty}$ Cartesian error constraint along the joint trajectory due to the sparsity of the gradient. In this work, we propose a diffusion-based framework that relies on probabilistic sampling to tackle the aforementioned challenges in the nonconvex high-level problem, leading to a 35x reduction in the runtime and 34\% less Cartesian error compared to our prior work.

Problem

• dual-arm robot
• minimum time trajectory
• nonconvex optimization
• Cartesian error constraint
• redundant manipulators

Innovation

• diffusion-based optimization
• dual-arm robot
• minimum-time trajectory
• probabilistic sampling
• Cartesian error constraint