Pith. sign in

REVIEW 4 cited by

Model-Based Diffusion for Trajectory Optimization

Not yet reviewed by Pith; the record is open.

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 2407.01573 v1 pith:Q7ROAMKM submitted 2024-05-28 cs.RO cs.LGcs.SYeess.SYmath.OC

classification cs.ROcs.LGcs.SYeess.SYmath.OC
keywords diffusiondataoptimizationmodel-basedmodelsprocessapproachbeyond
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in diffusion models have demonstrated their strong capabilities in generating high-fidelity samples from complex distributions through an iterative refinement process. Despite the empirical success of diffusion models in motion planning and control, the model-free nature of these methods does not leverage readily available model information and limits their generalization to new scenarios beyond the training data (e.g., new robots with different dynamics). In this work, we introduce Model-Based Diffusion (MBD), an optimization approach using the diffusion process to solve trajectory optimization (TO) problems without data. The key idea is to explicitly compute the score function by leveraging the model information in TO problems, which is why we refer to our approach as model-based diffusion. Moreover, although MBD does not require external data, it can be naturally integrated with data of diverse qualities to steer the diffusion process. We also reveal that MBD has interesting connections to sampling-based optimization. Empirical evaluations show that MBD outperforms state-of-the-art reinforcement learning and sampling-based TO methods in challenging contact-rich tasks. Additionally, MBD's ability to integrate with data enhances its versatility and practical applicability, even with imperfect and infeasible data (e.g., partial-state demonstrations for high-dimensional humanoids), beyond the scope of standard diffusion models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Stochastic Multiple Shooting Trajectory Optimization via Sequential Local Policy Evaluation

    cs.RO 2026-08 conditional novelty 6.0 of 10

    A stochastic multiple-shooting optimizer that links short sampled control segments with local LQR feedback policies reaches terminal sets with fewer rollouts than MPPI and CEM on cartpole and VTOL landing benchmarks.

  2. Locomotion on Constrained Footholds via Layered Architectures and Model Predictive Control

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A layered controller that samples footholds and runs parallel fixed-mode MPC evaluates terrain options in real time, enabling a quadruped and a simulated humanoid to traverse stepping stones.

  3. Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement

    cs.LG 2025-02 conditional novelty 6.0 of 10

    DiOpt combines a supervised warm-start with weighted bootstrapped self-training, achieving high feasibility and near-optimality on constrained nonconvex optimization benchmarks including AC optimal power flow and moti...

  4. Dual Control for Interactive Autonomous Merging with Model Predictive Diffusion

    cs.RO 2025-02 reject novelty 4.0 of 10

    An active-learning dual controller with model predictive diffusion is validated on F1-Tenth hardware, merging in 4.3 m on average versus 7.1 m for the prior dual MPPI method.

Pith tools