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

Long Xu; Choilam Wong; Yuhang Zhong; Junxiao Lin; Jialiang Hou; Fei Gao

cs.ROApr 5, 2026

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

Authors: Long Xu, Choilam Wong, Yuhang Zhong, Junxiao Lin, Jialiang Hou, Fei Gao

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 & tables

Fig. 1 : 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)).

Fig. 2 : 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.

Fig. 3 : An example of key point sequence generation for DDMoMa consisting of a 7-DoF manipulator and a mobile base.

Fig. 4 : Robot configuration and simulation environments. Two examples are provided for each environment here, with trajectories generated by the proposed planning framework.

Fig. 5 : 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 TopAY [ 4 ] in Cuboids , Mixed , and Replica , respectively.

Fig. 6 : Ablation study on task encoders: success rate (S.R.) and path ratio (P.R.) in three types of environments. The red , blue , and green dashed lines in subfigure (a) represent the average S.R. of TopAY [ 4 ] in Cuboids , Mixed , and Replica , respectively.

Diffusion-Based Planning

Diffusion-based planning generates diverse action sequences or trajectories by progressively denoising candidates conditioned on goals, scenes, and constraints.

See all 136 papers

Muninn: Your Trajectory Diffusion Model But Faster
May 11, 2026Gokul Puthumanaillam, Hao Jiang, Ruben Hernandez +4Trajectory Generation Diffusion-Based Planning
University of Illinois Urbana-Champaign. · Florida International University. · Providence College.
Training-Free Diffusion Planning with Analytical Local Scores
Oct 1, 2026Michael Y. Fatemi, Jinhao Liang, Ferdinando FiorettoMulti-Robot Motion Planning Constrained Motion Planning
University of Virginia
Function-Space Diffusion for Motion Planning
Jul 3, 2026Zinuo Chang, Yipu Chen, Byoungwoo Park +2Trajectory Generation Diffusion-Based Planning
School of Electrical and Computer Engineering · School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA · Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

May 11, 2026J/K move · Enter open · S save

Muninn: Your Trajectory Diffusion Model But Faster

Gokul Puthumanaillam, Hao Jiang, Ruben Hernandez, Jose Fuentes+3

University of Illinois Urbana-Champaign. · Florida International University. · Providence College.

Trajectory Generation Diffusion-Based Planning Diffusion Model Caching Robot Motion Planning Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

Diffusion-based trajectory planners can synthesize rich, multimodal robot motions, but their iterative denoising makes online planning and control prohibitively slow. Existing accelerations either modify the sampler or compress the network--sacrificing plan quality or requiring retraining without accounting for downstream control risk. We address the problem of making diffusion-based trajectory planners fast enough for real-time robot use without retraining the model or sacrificing trajectory quality, and in a way that works across diverse state-space diffusion architectures. Our key insight is that diffusion trajectory planners expose two signals we can exploit: a cheap probe of how their internal trajectory representation changes across steps, and analytic coefficients that describe how denoiser errors affect the sampler's state update. By calibrating the first signal against the second on offline runs, we obtain a per-step score that upper-bounds how far the final trajectory can deviate when we reuse a cached denoiser output, and we treat this bound as an uncertainty budget that we can spend over the denoising process. Building on this insight, we present Muninn, a training-free caching wrapper that tracks this uncertainty budget during sampling and, at each diffusion step, chooses between reusing a cached denoiser output when the predicted deviation is small and recomputing the denoiser when it is not. Across standard benchmarks Muninn delivers up to 4.6x wall-clock speedups across several trajectory diffusion models by reducing denoiser evaluations, while preserving task performance and safety metrics. Muninn further certifies that cached rollouts remain within a specified distance of their full-compute counterparts, and we validate these gains in real-time closed-loop navigation and manipulation hardware deployments. Project page: https://github.com/gokulp01/Muninn.

Abstract

Diffusion-Based Planning

Explore similar work

Muninn: Your Trajectory Diffusion Model But Faster

Training-Free Diffusion Planning with Analytical Local Scores

Function-Space Diffusion for Motion Planning