mlsanityData to 13 Oct 2026

Can Predicted Dynamics Exist in the Physical World?

arXiv 2606.00089 ↗First posted 23 May 2026cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Can learned state-action proposals exist in the physical world? Before executing a proposed action sequence, a robot can inspect empirical variation and disagreement with a learned transition model. However, aggregating these diagnostic signals obscures whether a proposal is inconsistent with the predictor or merely departs from recorded behavior. We formalize this prediction-control interface, separate the scalar trigger from its channel-wise diagnostic log, and establish that an all-pairs displacement term is redundant within a maximum that already contains the corresponding one-step term. We evaluate the monitors on 700 nominal and 5,250 synthetically perturbed 32-transition PushT windows, observing only planar pusher positions and goals. The transition-RMSE baseline achieves a ROC-AUC of 0.982, compared with 0.957 for a heterogeneous maximum and 0.972 for a spread-scaled residual.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 42 of its 56 references that are in the map. First posted on arXiv 23 May 2026.

Builds on

42 of 56 references.

References · 42

  1. 2017On Calibration of Modern Neural Networkscited by 4,902
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,902
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,022
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,823
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,760
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,344
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,028
  8. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,620
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,512
  10. 2018World Modelscited by 1,481
  11. 2024Octo: An Open-Source Generalist Robot Policycited by 1,450
  12. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,368
30 more
  1. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,334
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,241
  3. 2023Mastering Diverse Domains through World Modelscited by 1,224
  4. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,197
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,175
  6. 2017Constrained Policy Optimizationcited by 931
  7. 2020Learning to Simulate Complex Physics with Graph Networkscited by 873
  8. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 756
  9. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 754
  10. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 742
  11. 2019Hamiltonian Neural Networkscited by 705
  12. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 704
  13. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 676
  14. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 571
  15. 2017Safe Reinforcement Learning via Shieldingcited by 431
  16. 2020Lagrangian Neural Networkscited by 392
  17. 2019Control Barrier Functions: Theory and Applicationscited by 334
  18. 2022Behavior Transformers: Cloning k modes with one stonecited by 300
  19. 2016Deep Visual Foresight for Planning Robot Motioncited by 281
  20. 2018Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Controlcited by 224
  21. 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 130
  22. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 94
  23. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  24. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 79
  25. 2026LeRobot: An Open-Source Library for End-to-End Robot Learningcited by 70
  26. 2020TLIO: Tight Learned Inertial Odometrycited by 53
  27. 2021Run Time Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systemscited by 25
  28. 2022A Hybrid Model and Learning-Based Adaptive Navigation Filtercited by 12
  29. 2022Learning Car Speed Using Inertial Sensors for Dead Reckoning Navigationcited by 7
  30. 2025Safety Evaluation of Motion Plans Using Trajectory Predictors as Forward Reachable Set Estimatorscited by 3

Built on by

Not cited yet.