# Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control

arXiv: https://arxiv.org/abs/2410.13586 · HTML: https://mlsanity.com/paper/2410.13586/

## Key facts

- Cited by 7 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 32 of its 36 references that are in the map.
- First posted on arXiv 17 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, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior](https://mlsanity.com/paper/2212.03238/) (2022)
- [Diffusion Models for Reinforcement Learning: A Survey](https://mlsanity.com/paper/2311.01223/) (2023)
- [Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions](https://mlsanity.com/paper/2203.15103/) (2022)
- [DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets](https://mlsanity.com/paper/2404.19264/) (2024)
- [Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots](https://mlsanity.com/paper/2405.01792/) (2024)
- [Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects](https://mlsanity.com/paper/2312.10008/) (2023)
- [CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making](https://mlsanity.com/paper/2406.09509/) (2024)
- [Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models](https://mlsanity.com/paper/2308.15143/) (2023)
- [Direct Preference-based Policy Optimization without Reward Modeling](https://mlsanity.com/paper/2301.12842/) (2023)
- [ReorientDiff: Diffusion Model based Reorientation for Object Manipulation](https://mlsanity.com/paper/2303.12700/) (2023)
- [Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning](https://mlsanity.com/paper/2309.14246/) (2023)
- [SEABO: A Simple Search-Based Method for Offline Imitation Learning](https://mlsanity.com/paper/2402.03807/) (2024)
- [Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data](https://mlsanity.com/paper/2210.08642/) (2022)

## Built on by (most cited first, 7 of 7)

- [Online Preference Alignment for Language Models via Count-based Exploration](https://mlsanity.com/paper/2501.12735/) (2025)
- [Radiology Report Generation via Multi-objective Preference Optimization](https://mlsanity.com/paper/2412.08901/) (2024)
- [VDT-Auto: End-to-end Autonomous Driving with VLM-Guided Diffusion Transformers](https://mlsanity.com/paper/2502.20108/) (2025)
- [DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion](https://mlsanity.com/paper/2505.18780/) (2025)
- [LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning](https://mlsanity.com/paper/2504.15472/) (2025)
- [Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation](https://mlsanity.com/paper/2602.09583/) (2026)
- [NeurRAFT: Robot Motion Planning via Anchor-Level Flow Matching with Clearance-Aware Preference Tuning](https://mlsanity.com/paper/2608.24026/) (2026)

## Abstract (arXiv)

Diffusion models demonstrate superior performance in capturing complex distributions from large-scale datasets, providing a promising solution for quadrupedal locomotion control. However, the robustness of the diffusion planner is inherently dependent on the diversity of the pre-collected datasets. To mitigate this issue, we propose a two-stage learning framework to enhance the capability of the diffusion planner under limited dataset (reward-agnostic). Through the offline stage, the diffusion planner learns the joint distribution of state-action sequences from expert datasets without using reward labels. Subsequently, we perform the online interaction in the simulation environment based on the trained offline planner, which significantly diversified the original behavior and thus improves the robustness. Specifically, we propose a novel weak preference labeling method without the ground-truth reward or human preferences. The proposed method exhibits superior stability and velocity tracking accuracy in pacing, trotting, and bounding gait under different speeds and can perform a zero-shot transfer to the real Unitree Go1 robots. The project website for this paper is at https://shangjaven.github.io/preference-aligned-diffusion-legged.