mlsanityData to 14 Oct 2026

Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies

arXiv 2609.35231 ↗First posted 28 Sep 2026cs.ROcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

We propose NUDGE (Nudge Update via Differentiable GEometry), a training-free obstacle-avoidance procedure that can be incorporated in any robot policy based on diffusion or flow matching, including diffusion policies and vision-language-action models. Our work injects gradients from a signed distance field, a function returning each point's distance to the nearest obstacle, into the policy at inference time to steer it away from obstacles. It supports any common action parameterization, from absolute or relative joint poses to end-effector poses, through a differentiable joint-trajectory decoder. Experiments show that NUDGE preserves the policy's task distribution and runs reactively in real time.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 40 of its 45 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

40 of 45 references.

Closest ancestors · 14

Same direction, newest first

  1. 2026Action-to-Action Flow Matching7 Feb
  2. 2026VLS: Steering Pretrained Robot Policies via Vision-Language Models3 Feb
  3. 2025SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions29 Sep
  4. 2025VITA: Vision-to-Action Flow Matching Policy17 Jul
  5. 2025DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance16 Jun
  6. 2025Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories28 May
  7. 2024Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models27 Dec
  8. 2024Diffusion Predictive Control with Constraints12 Dec
  9. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation10 Oct
  10. 2024PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation24 Sep
  11. 2024Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation29 Jun
  12. 2023EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning20 Sep
2 more
  1. 2023SafeDiffuser: Safe Planning with Diffusion Probabilistic Models31 May
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 26

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  7. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  8. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  11. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  12. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
14 more
  1. 2017Constrained Policy Optimizationcited by 983
  2. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  3. 2023Universal Guidance for Diffusion Modelscited by 437
  4. 2019Control Barrier Functions: Theory and Applicationscited by 372
  5. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  6. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  7. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 58
  8. 2021STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulationcited by 47
  9. 2023nvblox: GPU-Accelerated Incremental Signed Distance Field Mappingcited by 24
  10. 2025Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environmentscited by 9
  11. 2026cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robotscited by 8
  12. 2020Reachable Sets for Safe, Real-Time Manipulator Trajectory Designcited by 6
  13. 2026OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policiescited by 6
  14. 2024RAIL: Reachability-Aided Imitation Learning for Safe Policy Executioncited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance
  2. 2025Cascaded Diffusion Models for Neural Motion Planning
  3. 2025Exploration and Adaptation in Non-Stationary Tasks with Diffusion Policies
  4. 2026Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control
  5. 2026Safe Real-Time Policy Steering via Noise-Space Trajectory Optimization for One-Step Generative Policies ↗
  6. 2026Learning Foresight without Explicit Trajectories for 3D Diffusion Policies
  7. 2026ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations
  8. 2024LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance