Extreme Motion Generation via Hybrid Null-Space Control for Straight-Line Path Following
2026-06-02 • Robotics
Robotics
AI summaryⓘ
The authors study how to make robot arms move along given paths as much as possible within their reachable space, which is useful for tasks like painting or welding. They combine a learning-based method that plans long-term movements with a traditional controller that keeps the robot safe near its limits. To start, they use a special sampling technique to pick good starting positions for the robot. Testing on many tasks with a 7-joint robot showed their method could follow paths about 27% longer on average than just using the traditional controller. This helps the robot better use its full range of motion safely.
extreme motion generationrobot manipulatorpath-followinglong-horizon decision-makingreinforcement learningmodel-based controljoint limitsdiffusion-based sampling7-DoF Franka FR3kinematic reachability
Authors
Xinyi Yuan, Weiwei Wan, Kensuke Harada
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/.