Primitive-based Truncated Diffusion for Efficient Trajectory Generation of Differential Drive Mobile Manipulators

Abstract

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 .

Figures (6)

• Figure A1: Process of the proposed planning framework during its deployment. Given the noise (subfigure (a)) and selected primitive (subfigure (b)), paths (subfigure (c)) are sampled via primitive-based truncated diffusion model (PTDM), subsequently post-processed to obtain the final optimized trajectory (subfigure (d)).
• Figure B1: Proposed planning framework. The neural network encodes the task and samples robot paths efficiently. The paths are then refined by a model-based trajectory optimizer to generate safe, dynamically feasible trajectories.
• Figure C1: An example of key point sequence generation for DDMoMa consisting of a 7-DoF manipulator and a mobile base.
• Figure C2: Robot configuration and simulation environments. Two examples are provided for each environment here, with trajectories generated by the proposed planning framework.
• Figure D1: Comparisons of diversity score (D.S., subfigure (a)) and planning time (T.P., subfigure (b)) across different diffusion strategies as the number of sampled paths varies in different environments. In most of cases, PTDM achieves lower planning time consuming and higher diversity than vanilla DDPM and anchor-based diffusion (ATDM). The red, blue, and green dashed lines in subfigure (b) represent the average T.P. of TopAYtopay in Cuboids, Mixed, and Replica, respectively.