PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation

• URL: http://arxiv.org/abs/2607.07076v1
• Date: Wed, 08 Jul 2026 07:08:11 GMT
• Title: PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation
• Abstract summary: PriGo is a primitive-guided test-time adaptive framework for robust robotic manipulation.<n>We introduce PANet, a lightweight primitive prediction module that infers primitive distributions directly from observations.<n>Unlike prior primitive-conditioned approaches, PriGo operates entirely at test time and can be seamlessly integrated into pretrained diffusion and flow policies.
• Score: 28.358317763869664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Imitation learning has enabled remarkable progress in robotic manipulation, especially with diffusion and flow-based policies that generate complex visuomotor behaviors directly from demonstrations. Yet, despite their strong performance, these policies often fail to generalize across tasks and environments. A key reason is that existing policies tend to imitate superficial action correlations rather than the underlying intent. Inspired by the compositional structure of human behaviors, we propose PriGo, a primitive-guided test-time adaptive framework for robust robotic manipulation. PriGo introduces PANet, a lightweight primitive prediction module that infers primitive distributions directly from observations. We further propose a differentiable primitive guidance mechanism that refines generated actions during inference, steering trajectories toward semantically consistent behaviors. Unlike prior primitive-conditioned approaches, PriGo operates entirely at test time and can be seamlessly integrated into pretrained diffusion and flow policies without retraining. Extensive experiments on LIBERO, CALVIN, SIMPLER, and real-world robotic tasks demonstrate that PriGo consistently improves robustness, long-horizon execution, and generalization ability across both diffusion and flow-based policies.

Related papers

• FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space [15.351960740594201]
  FlowDAgger is a sample- and compute-efficient method for adapting frozen generative robot policies from human interventions in latent space.<n>Our key idea is action inversion: each human expert action is mapped to the noise that would have produced it under the frozen base policy.<n>We evaluate FlowDAgger in simulation and on real-world bimanual and single-arm manipulation.
  arXiv  Detail & Related papers  (2026-07-09T19:07:33Z)
• Adapting Generalist Robot Policies with Semantic Reinforcement Learning [59.009122725071386]
  Generalist robot policies learn a diverse repertoire of behaviors from large-scale pretraining.<n>We propose Semantic Action Reinforcement Learning (SARL) to learn to optimize this prompt space through online interaction.<n>We show SARL unlocks fundamentally new capabilities -- adapting VLA behavior to solve complex, long-horizon tasks.
  arXiv  Detail & Related papers  (2026-06-30T17:00:33Z)
• From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving [56.30087557121323]
  AlignADV is a learnability-guided closed-loop adversarial training framework.<n>It converts adversarial scenarios into resolvable and capability-aligned curricula.<n> Experiments show it reduces training steps by up to 40.6 percent.
  arXiv  Detail & Related papers  (2026-06-12T02:13:55Z)
• LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching [15.922360971421654]
  We propose Latent Action Flow Policy (LAFP) for scalable latent policy learning.<n>LAFP consistently outperforms prior methods on downstream imitation learning tasks.<n>LAFP incurs less than 1x additional inference overhead.
  arXiv  Detail & Related papers  (2026-06-09T07:49:49Z)
• Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation [91.20850436220267]
  We introduce the Referring-Aware Visuomotor Policy (ReV)<n>ReV incorporates sparse referring points provided by a human or a high-level reasoning planner.<n>It is trained only by applying targeted perturbations to expert demonstrations.
  arXiv  Detail & Related papers  (2026-04-07T07:41:11Z)
• Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy [1.1549572298362782]
  Striking a balance between efficiency and transparent motion is a core challenge in human-robot collaboration.<n>We propose Style-Conditioned Diffusion Policy (SCDP), a modular framework that constrains a pre-trained diffusion model toward either legibility or efficiency.<n>We evaluate SCDP on manipulation and navigation tasks, and results show that it enhances legibility in ambiguous settings while preserving optimal efficiency when legibility is unnecessary.
  arXiv  Detail & Related papers  (2026-03-17T10:55:44Z)
• GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion [44.168491831527355]
  This paper focuses on enhancing the grasping precision and generalization of manipulation policies learned via imitation learning.<n>Existing imitation learning techniques for grasping often suffer from imprecise grasp executions, limited spatial generalization, and poor object generalization.
  arXiv  Detail & Related papers  (2026-02-26T10:56:01Z)
• Flow Policy Gradients for Robot Control [67.61978635211048]
  Flow matching policy gradients can be made effective for training and fine-tuning more expressive policies.<n>We show how policies can exploit the flow representation for exploration when training from scratch, as well as improved fine-tuning robustness over baselines.
  arXiv  Detail & Related papers  (2026-02-02T18:56:49Z)
• Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation [28.95872004551021]
  Imitation learning with diffusion models has advanced robotic control by capturing multi-modal action distributions.<n>Existing approaches treat observations as high-level conditioning inputs to the denoising network, rather than integrating them into the dynamics of the diffusion process itself.<n>We introduce BridgePolicy, a generative visuomotor policy that embeds observations within the differential equation via a diffusion-bridge formulation.
  arXiv  Detail & Related papers  (2025-12-08T06:47:32Z)
• Dense Policy: Bidirectional Autoregressive Learning of Actions [51.60428100831717]
  This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction.<n>It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner.<n>Experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies.
  arXiv  Detail & Related papers  (2025-03-17T14:28:08Z)
• Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks [17.13584584844048]
  This work introduces MAnipulation Primitive-augmented reinforcement LEarning (MAPLE), a learning framework that augments standard reinforcement learning algorithms with a pre-defined library of behavior primitives. We develop a hierarchical policy that involves the primitives and instantiates their executions with input parameters. We demonstrate that MAPLE outperforms baseline approaches by a significant margin on a suite of simulated manipulation tasks.
  arXiv  Detail & Related papers  (2021-10-07T17:44:33Z)
• Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
  Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
  arXiv  Detail & Related papers  (2020-05-21T19:47:05Z)

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.