Pith. sign in

REVIEW 8 cited by

DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.16727 v1 pith:CIFZAZ3R submitted 2024-10-22 cs.RO

Huang Huang , Balakumar Sundaralingam , Arsalan Mousavian , Adithyavairavan Murali , Ken Goldberg , Dieter Fox This is my paper · ORCID
classification cs.RO
keywords motionoptimizationdiffusionseederplanningrobotdiffusionrateseeds
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Running optimization across many parallel seeds leveraging GPU compute have relaxed the need for a good initialization, but this can fail if the problem is highly non-convex as all seeds could get stuck in local minima. One such setting is collision-free motion optimization for robot manipulation, where optimization converges quickly on easy problems but struggle in obstacle dense environments (e.g., a cluttered cabinet or table). In these situations, graph-based planning algorithms are used to obtain seeds, resulting in significant slowdowns. We propose DiffusionSeeder, a diffusion based approach that generates trajectories to seed motion optimization for rapid robot motion planning. DiffusionSeeder takes the initial depth image observation of the scene and generates high quality, multi-modal trajectories that are then fine-tuned with a few iterations of motion optimization. We integrate DiffusionSeeder to generate the seed trajectories for cuRobo, a GPU-accelerated motion optimization method, which results in 12x speed up on average, and 36x speed up for more complicated problems, while achieving 10% higher success rate in partially observed simulation environments. Our results show the effectiveness of using diverse solutions from a learned diffusion model. Physical experiments on a Franka robot demonstrate the sim2real transfer of DiffusionSeeder to the real robot, with an average success rate of 86% and planning time of 26ms, improving on cuRobo by 51% higher success rate while also being 2.5x faster.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Differentiable GPU-Parallelized Task and Motion Planning

    cs.RO 2024-11 conditional novelty 7.0 of 10

    cuTAMP combines GPU-parallelized sampling and differentiable optimization to solve long-horizon task and motion planning problems on constrained manipulation tasks, outperforming serial baselines.

  2. Diffusion-Guided Multi-Arm Motion Planning

    cs.RO 2025-09 conditional novelty 6.0 of 10

    A MAPF-inspired search guided by single-arm and dual-arm diffusion models plans collision-free motions for many arms without higher-order training data.

  3. Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments

    cs.RO 2025-09 conditional novelty 6.0 of 10

    DRP couples a transformer policy pretrained on 10M cuRobo trajectories and refined by student-teacher finetuning with a point-cloud reactive goal proposer (DCP-RMP) to outperform prior planners in dynamic manipulation.

  4. Dynamics-Compliant Trajectory Diffusion for Super-Nominal Payload Manipulation

    cs.RO 2025-08 conditional novelty 6.0 of 10

    A payload-conditioned diffusion model generates dynamically feasible joint trajectories in about 10 ms, allowing a 7-DoF arm to handle loads over three times its nominal payload across much of its workspace.

  5. TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching

    cs.RO 2025-05 conditional novelty 6.0 of 10

    A GNN-encoded flow matching model learns to generate STL-satisfying trajectories across five robot simulation domains, with a 200K-specification dataset, reporting best-of-1024 satisfaction rates.

  6. GASP: GPU-Accelerated Safe Planner for Real-Time Collision-Aware Motion Generation with Latent Trajectory Sampling

    cs.RO 2026-08 conditional novelty 5.0 of 10

    A learned B-spline planner with latent sampling generates collision-aware joint trajectories on the GPU in near-millisecond time, matching analytical planners and outperforming a GPU optimization baseline.

  7. Model Tensor Planning

    cs.RO 2025-05 conditional novelty 5.0 of 10

    Model Tensor Planning uses random multipartite graph sampling with spline interpolation to increase exploration in sampling-based MPC, outperforming several baselines in simulated robot tasks.

  8. Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation

    cs.RO 2026-08 conditional novelty 4.0 of 10

    A consistency-distilled diffusion model generates 150 collision-aware joint trajectories for a 6-DoF HRI manipulator in about 95 ms, with a jerk penalty improving smoothness.

Pith tools