analiza aiqbench
This research introduces Structured-Diffuser, a novel diffusion planner that integrates task-conditioned structured priors directly into the noise model to enhance motion planning efficiency. By leveraging Gaussian Process Motion Planning (GPMP) to define non-isotropic corruption, the method concentrates probability mass on semantically relevant trajectories, yielding measurable gains in success rates and data efficiency for robotic tasks. The approach demonstrates practical viability through deployment on a physical G1 humanoid robot, bridging advanced probabilistic modeling with real-world actuation.
Structured-Diffuser: Diffusion with Task-Conditioned Structured Priors for Motion Planning
arXiv:2509.25685v3 Announce Type: replace Abstract: We propose Structured-Diffuser, a diffusion planner that embeds task and motion structure directly into the noise model. Unlike standard diffusion-based planners that rely on zero-mean, isotropic Gaussian corruption, we introduce task-conditioned structured Gaussians whose means and covariances are derived from Gaussian Process Motion Planning (GPMP), explicitly encoding trajectory smoothness and task semantics in the prior. We first formulate diffusion under a task-conditioned, non-isotropic Gaussian prior with closed-form forward and posterior expressions. Building on this formulation, our hierarchical design separates prior instantiation from trajectory denoising. At the upper level, sparse task-centric key states and timings are obtained, which instantiate a structured Gaussian prior (mean and covariance). At the lower level, the full trajectory is denoised under this prior, treating the upper-level outputs as noisy observations. Experiments across three motion-planning tasks show improved task success and training efficiency, with additional gains in data efficiency, trajectory smoothness, and position--velocity consistency where evaluated. Ablation studies further show that explicitly structuring the corruption process provides benefits beyond neurally conditioning the denoising network alone. Overall, our approach concentrates the prior's probability mass around task-relevant, temporally structured trajectories. We additionally demonstrate deployment on a physical G1 humanoid.
Abstract:We propose Structured-Diffuser, a diffusion planner that embeds task and motion structure directly into the noise model. Unlike standard diffusion-based planners that rely on zero-mean, isotropic Gaussian corruption, we introduce task-conditioned structured Gaussians whose means and covariances are derived from Gaussian Process Motion Planning (GPMP), explicitly encoding trajectory smoothness and task semantics in the prior. We first formulate diffusion under a task-conditioned, non-isotropic Gaussian prior with closed-form forward and posterior expressions. Building on this formulation, our hierarchical design separates prior instantiation from trajectory denoising. At the upper level, sparse task-centric key states and timings are obtained, which instantiate a structured Gaussian prior (mean and covariance). At the lower level, the full trajectory is denoised under this prior, treating the upper-level outputs as noisy observations. Experiments across three motion-planning tasks show improved task success and training efficiency, with additional gains in data efficiency, trajectory smoothness, and position--velocity consistency where evaluated. Ablation studies further show that explicitly structuring the corruption process provides benefits beyond neurally conditioning the denoising network alone. Overall, our approach concentrates the prior's probability mass around task-relevant, temporally structured trajectories. We additionally demonstrate deployment on a physical G1 humanoid.
Robotics (cs.RO)
arXiv:2509.25685 [cs.RO]
(or arXiv:2509.25685v3 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2509.25685 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 281 cuvinte
Subiecte conexe
[AINews] Here are 6 Clones of Jev in 2 days
Latent Space · 19 sept. 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
arXiv · 12 iun. 2026
InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation
arXiv · 29 iul. 2026