mlsanityData to 7 Oct 2026

Posterior-driven Heuristic Support Adaptation in a Probabilistic Treatment of Real2Sim2Real for Vision-Driven Deformable Linear Object Manipulation

arXiv 2510.26656 ↗First posted 30 Oct 2025cs.RO cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Likelihood-free inference (LFI) enables system identification in complex tasks via black-box modelling, abstracting nonlinearity and stochasticity, and infers a domain distribution for adapting agents to parametric deployment conditions. LFI assumes an arbitrary support for sampling, which remains fixed as the initial generic prior is refined to increasingly descriptive posteriors. Misspecified support can therefore yield suboptimal yet overconfident posteriors. We address this issue by using the posterior of an inference step to guide the adaptation of the support using three illustrative heuristics: EDGE, MODE, and CENTRE. Each heuristic interprets the updated belief and enables support adaptation alongside posterior inference. For illustrative purposes, we first study misspecified support in LFI and evaluate the utility of our heuristics using stochastic dynamical benchmarks. We then evaluate posterior-driven heuristic support adaptation for parameter inference and policy learning in a dynamic deformable linear object (DLO) manipulation task. Inference results in a finer length and stiffness classification for a parametric set of DLOs. When the resulting posteriors are used as domain distributions for sim-based policy learning, they lead to more robust object-centric agent performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 71 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

45 of 71 references.

References · 45

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  5. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  6. 2019Solving Rubik's Cube with a Robot Handcited by 699
  7. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  8. 2019The frontier of simulation-based inferencecited by 490
  9. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 265
  10. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  11. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  12. 2019Active Domain Randomizationcited by 161
33 more
  1. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 136
  2. 2023Modern Bayesian Experimental Designcited by 121
  3. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 113
  4. 2019Unsupervised Learning of Object Keypoints for Perception and Controlcited by 109
  5. 2020On Contrastive Learning for Likelihood-free Inferencecited by 96
  6. 2019BayesSim: adaptive domain randomization via probabilistic inference for robotics simulatorscited by 78
  7. 2020Causal Discovery in Physical Systems from Videoscited by 77
  8. 2021DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cuttingcited by 62
  9. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  10. 2024AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulationcited by 52
  11. 2025Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulationcited by 42
  12. 2021Planar Robot Casting with Real2Sim2Real Self-Supervised Learningcited by 38
  13. 2022Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objectscited by 36
  14. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 27
  15. 2024sbi reloaded: a toolkit for simulation-based inference workflowscited by 23
  16. 2020Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshopcited by 22
  17. 2025The Reality Gap in Robotics: Challenges, Solutions, and Best Practicescited by 22
  18. 2020Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cablescited by 21
  19. 2024AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometriescited by 20
  20. 2020Inferring the Material Properties of Granular Media for Robotic Taskscited by 18
  21. 2021Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulationcited by 17
  22. 2023AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfercited by 17
  23. 2023Active Learning and Bayesian Optimization: a Unified Perspective to Learn with a Goalcited by 17
  24. 2020STReSSD: Sim-To-Real from Sound for Stochastic Dynamicscited by 12
  25. 2022Robust Expected Information Gain for Optimal Bayesian Experimental Design Using Ambiguity Setscited by 12
  26. 2020Learning Active Task-Oriented Exploration Policies for Bridging the Sim-to-Real Gapcited by 11
  27. 2021A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulationcited by 11
  28. 2023Real-to-Sim Deformable Object Manipulation: Optimizing Physics Models with Residual Mappings for Robotic Surgerycited by 11
  29. 2017Automatic Rule Extraction from Long Short Term Memory Networkscited by 10
  30. 2020DISCO: Double Likelihood-free Inference Stochastic Controlcited by 8
  31. 2024Continual Domain Randomizationcited by 7
  32. 2023Generalizable whole-body global manipulation of deformable linear objects by dual-arm robot in 3-D constrained environmentscited by 6
  33. 2025A Distributional Treatment of Real2Sim2Real for Object-Centric Agent Adaptation in Vision-Driven Deformable Linear Object Manipulationcited by 1

Built on by

Not cited yet.