Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation

• URL: http://arxiv.org/abs/2602.09583v1
• Date: Tue, 10 Feb 2026 09:35:22 GMT
• Title: Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation
• Abstract summary: Humans naturally develop preferences for how manipulation tasks should be performed, which are often subtle, personal, and difficult to articulate.<n>We introduce RKO, a novel preference-alignment method that combines the benefits of two recent frameworks: RPO and KTO.<n>We show that preference-aligned policies (particularly RKO) achieve superior performance and sample efficiency compared to standard diffusion policy fine-tuning.
• Score: 13.739688454304863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans naturally develop preferences for how manipulation tasks should be performed, which are often subtle, personal, and difficult to articulate. Although it is important for robots to account for these preferences to increase personalization and user satisfaction, they remain largely underexplored in robotic manipulation, particularly in the context of deformable objects like garments and fabrics. In this work, we study how to adapt pretrained visuomotor diffusion policies to reflect preferred behaviors using limited demonstrations. We introduce RKO, a novel preference-alignment method that combines the benefits of two recent frameworks: RPO and KTO. We evaluate RKO against common preference learning frameworks, including these two, as well as a baseline vanilla diffusion policy, on real-world cloth-folding tasks spanning multiple garments and preference settings. We show that preference-aligned policies (particularly RKO) achieve superior performance and sample efficiency compared to standard diffusion policy fine-tuning. These results highlight the importance and feasibility of structured preference learning for scaling personalized robot behavior in complex deformable object manipulation tasks.

Related papers

• Steering Generative Robot Policies with Lexicographic Preferences [17.61600932655699]
  We show that a frozen generative robot policy can be steered at inference time to respect deployment objectives.<n>We demonstrate that our method improves success, traversability, and preference compliance over tuned weighted-sum baselines.<n>A controlled manipulation study further shows that, in settings where a fixed weight can match the desired ordering, the dynamic barrier reaches comparable best performance.
  arXiv  Detail & Related papers  (2026-09-14T04:27:07Z)
• PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning [50.63196995993855]
  We propose a novel framework leveraging Multi-Objective Reinforcement Learning (MORL) to achieve Preference-Conditioned Humanoid Control (PCHC)<n>Our framework enables a single, preference-conditioned policy to exhibit a wide spectrum of diverse behaviors.
  arXiv  Detail & Related papers  (2026-03-25T07:55:37Z)
• ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation [46.06124092071133]
  We propose a novel Chain of Moving Oriented Keypoints (CoMOK) formulation for robotic manipulation.<n>Our formulation is used as the action representation of a neural policy, which can be trained in an end-to-end fashion.
  arXiv  Detail & Related papers  (2025-09-25T07:29:07Z)
• On-the-fly Preference Alignment via Principle-Guided Decoding [27.50204023448716]
  We introduce On-the-fly Preference Alignment via Principle-Guided Decoding (OPAD) to align model outputs with human preferences during inference.<n>OPAD achieves competitive or superior performance in both general and personalized alignment tasks.
  arXiv  Detail & Related papers  (2025-02-20T02:23:09Z)
• FDPP: Fine-tune Diffusion Policy with Human Preference [57.44575105114056]
  Fine-tuning Diffusion Policy with Human Preference learns a reward function through preference-based learning.<n>This reward is then used to fine-tune the pre-trained policy with reinforcement learning.<n>Experiments demonstrate that FDPP effectively customizes policy behavior without compromising performance.
  arXiv  Detail & Related papers  (2025-01-14T17:15:27Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment [73.14105098897696]
  We propose Representation-Aligned Preference-based Learning (RAPL) to learn visual rewards from significantly less human preference feedback.<n>RAPL focuses on fine-tuning pre-trained vision encoders to align with the end-user's visual representation and then constructs a dense visual reward via feature matching.<n>We show that RAPL can learn rewards aligned with human preferences, more efficiently uses preference data, and generalizes across robot embodiments.
  arXiv  Detail & Related papers  (2024-12-06T08:04:02Z)
• Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences [53.353022588751585]
  We present Promptable Behaviors, a novel framework that facilitates efficient personalization of robotic agents to diverse human preferences. We introduce three distinct methods to infer human preferences by leveraging different types of interactions. We evaluate the proposed method in personalized object-goal navigation and flee navigation tasks in ProcTHOR and RoboTHOR.
  arXiv  Detail & Related papers  (2023-12-14T21:00:56Z)
• Off-Policy Evaluation for Large Action Spaces via Policy Convolution [60.6953713877886]
  Policy Convolution family of estimators uses latent structure within actions to strategically convolve the logging and target policies. Experiments on synthetic and benchmark datasets demonstrate remarkable mean squared error (MSE) improvements when using PC.
  arXiv  Detail & Related papers  (2023-10-24T01:00:01Z)
• Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients [54.98496284653234]
  We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We solve this problem by introducing a regularizer based on the mutual information between the sensitive state and the actions. We develop a model-based estimator for optimization of privacy-constrained policies.
  arXiv  Detail & Related papers  (2020-12-30T03:22:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.