# Compositional Diffusion Models for Powered Descent Trajectory Generation with Flexible Constraints

arXiv: https://arxiv.org/abs/2410.04261 · HTML: https://mlsanity.com/paper/2410.04261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC](https://mlsanity.com/paper/2302.11552/) (2023)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [CoCo: Online Mixed-Integer Control via Supervised Learning](https://mlsanity.com/paper/2107.08143/) (2021)
- [Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous](https://mlsanity.com/paper/2310.13831/) (2023)
- [Constraint-Informed Learning for Warm Starting Trajectory Optimization](https://mlsanity.com/paper/2312.14336/) (2023)
- [Improving Computational Efficiency for Powered Descent Guidance via Transformer-based Tight Constraint Prediction](https://mlsanity.com/paper/2311.05135/) (2023)
- [Successive Convexification for 6-DoF Mars Rocket Powered Landing with Free-Final-Time](https://mlsanity.com/paper/1802.03827/) (2018)
- [Diffusion Models for Generating Ballistic Spacecraft Trajectories](https://mlsanity.com/paper/2405.11738/) (2024)
- [Successive Convexification for 6-DoF Powered Descent Guidance with Compound State-Triggered Constraints](https://mlsanity.com/paper/1901.02181/) (2019)

## Built on by (most cited first, 2 of 2)

- [Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers](https://mlsanity.com/paper/2510.03544/) (2025)
- [Spacecraft Rendezvous Trajectory Generation with Modular Constraints via Diffusion Model Composition](https://mlsanity.com/paper/2610.05642/) (2026)

## Abstract (arXiv)

This work introduces TrajDiffuser, a compositional diffusion-based flexible and concurrent trajectory generator for 6 degrees of freedom powered descent guidance. TrajDiffuser is a statistical model that learns the multi-modal distributions of a dataset of simulated optimal trajectories, each subject to only one or few constraints that may vary for different trajectories. During inference, the trajectory is generated simultaneously over time, providing stable long-horizon planning, and constraints can be composed together, increasing the model's generalizability and decreasing the training data required. The generated trajectory is then used to initialize an optimizer, increasing its robustness and speed.