{"ID":2859658,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04436","arxiv_id":"2510.04436","title":"PAD-TRO: Projection-Augmented Diffusion for Direct Trajectory Optimization","abstract":"Recently, diffusion models have gained popularity and attention in trajectory optimization due to their capability of modeling multi-modal probability distributions. However, addressing nonlinear equality constraints, i.e, dynamic feasibility, remains a great challenge in diffusion-based trajectory optimization. Recent diffusion-based trajectory optimization frameworks rely on a single-shooting style approach where the denoised control sequence is applied to forward propagate the dynamical system, which cannot explicitly enforce constraints on the states and frequently leads to sub-optimal solutions. In this work, we propose a novel direct trajectory optimization approach via model-based diffusion, which directly generates a sequence of states. To ensure dynamic feasibility, we propose a gradient-free projection mechanism that is incorporated into the reverse diffusion process. Our results show that, compared to a recent state-of-the-art baseline, our approach leads to zero dynamic feasibility error and approximately 4x higher success rate in a quadrotor waypoint navigation scenario involving dense static obstacles.","short_abstract":"Recently, diffusion models have gained popularity and attention in trajectory optimization due to their capability of modeling multi-modal probability distributions. However, addressing nonlinear equality constraints, i.e, dynamic feasibility, remains a great challenge in diffusion-based trajectory optimization. Recent...","url_abs":"https://arxiv.org/abs/2510.04436","url_pdf":"https://arxiv.org/pdf/2510.04436v3","authors":"[\"Jushan Chen\",\"Santiago Paternain\"]","published":"2025-10-06T02:06:58Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"eess.SY\"]","methods":"[\"Diffusion Model\"]","has_code":false}