Primitive-based Truncated Diffusion for Efficient Trajectory Generation of Differential Drive Mobile Manipulators
This work addresses efficiency and success in motion planning for mobile manipulators, representing an incremental improvement over existing diffusion-based methods.
The paper tackles motion planning for differential drive mobile manipulators by proposing a learning-enhanced planner that uses a primitive-based truncated diffusion model and keypoint sequence extraction, achieving higher success rates, improved trajectory diversity, and competitive runtime in cluttered 3D simulations compared to baselines.
We present a learning-enhanced motion planner for differential drive mobile manipulators to improve efficiency, success rate, and optimality. For task representation encoder, we propose a keypoint sequence extraction module that maps boundary states to 3D space via differentiable forward kinematics. Point clouds and keypoints are encoded separately and fused with attention, enabling effective integration of environment and boundary states information. We also propose a primitive-based truncated diffusion model that samples from a biased distribution. Compared with vanilla diffusion model, this framework improves the efficiency and diversity of the solution. Denoised paths are refined by trajectory optimization to ensure dynamic feasibility and task-specific optimality. In cluttered 3D simulations, our method achieves higher success rate, improved trajectory diversity, and competitive runtime compared to vanilla diffusion and classical baselines. The source code is released at https://github.com/nmoma/nmoma .