Extreme Motion Generation via Hybrid Null-Space Control for Straight-Line Path Following

2026-06-02

AI Summary

This work addresses the challenge of simultaneously optimizing Cartesian path length and ensuring joint safety for fixed-base robotic arms moving along prescribed straight-line trajectories within constrained workspaces. The authors propose a step-level hybrid controller that employs reinforcement learning for long-horizon decision-making to maximize path length when operating far from joint limits, and dynamically switches to a model-based controller near boundary regions to guarantee safety. A conditional diffusion model is introduced to sample high-potential initial configurations, and a novel switching criterion based on normalized joint-limit distance enables adaptive fusion between learning- and model-based control for the first time. Evaluated over 10,000 trials on a Franka Emika FR3 manipulator, the approach achieves a 27% average improvement in path length over a purely model-based baseline, closely approaching kinematic limits.

Abstract

This work studies ``extreme motion generation'', which aims to maximize the Cartesian path length along a pre-defined trajectory within the manipulator's workspace. This objective is important in industry as long as path-following is fundamental to a large variety of tasks such as surface coating and welding. More critically, extreme motion enables a fixed-base manipulator to exploit the kinematic capability under limited reachability. However, such exploitation is challenging in practice, as the manipulator must actively avoid the safety boundary through execution, which is inherently a long-horizon problem. Accordingly, we claim that long-horizon decision-making should be delegated to a learning-based policy to maximize exploitation, while a classical model-based controller covers the near-boundary region, where the learning policy degrades sharply due to sparse data coverage. In detail, our proposed method is a step-level hybrid controller that switches between an RL-based and a model-based controller according to the normalized joint-limit distance. The initial joint configuration is sampled through conditional diffusion-based sampling, which improves the achievable path length based on the learned motion prior. We evaluate the proposed framework on 10,000 straight-line path-following tasks with a 7-DoF Franka FR3, extending the average rollout length by 27\% over the model-based baseline. Notably, certain tasks yield a pronounced extension toward the motion extreme, as reflected in the maximum improvement reported in the statistical results. The project website and related videos of this paper can be found at https://yuan-xinyi.github.io/extreme-motion-generation/.

Problem

• extreme motion generation
• path following
• manipulator workspace
• safety boundary avoidance
• Cartesian path length

Innovation

• hybrid control
• extreme motion generation
• reinforcement learning
• diffusion-based sampling
• path following