mlsanityData to 14 Oct 2026

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

arXiv 2506.18088 ↗First posted 22 Jun 2025cs.RO cs.AI cs.CLcited by 518

Not on the map. Why?

Cited by 234 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation methods and (2) oversimplified simulation environments. We present RoboTwin 2.0, a scalable framework for automated, large-scale generation of diverse and realistic data, together with unified evaluation protocols for dual-arm manipulation. At its core is RoboTwin-OD, an object library of 731 instances across 147 categories with semantic and manipulation-relevant annotations. Building on this, we design an expert data synthesis pipeline that leverages multimodal language models (MLLMs) and simulation-in-the-loop refinement to automatically generate task-level execution code. To improve sim-to-real transfer, RoboTwin 2.0 applies structured domain randomization along five axes: clutter, lighting, background, tabletop height, and language, enhancing data diversity and policy robustness. The framework is instantiated across 50 dual-arm tasks and five robot embodiments. Empirically, it yields a 10.9% gain in code generation success rate. For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain. These results highlight the effectiveness of RoboTwin 2.0 in strengthening sim-to-real transfer and robustness to environmental variations. We release the data generator, benchmark, dataset, and code to support scalable research in robust bimanual manipulation. Project Page: https://robotwin-platform.github.io/, Code: https://github.com/robotwin-Platform/robotwin/.

Key facts. Cited by 518 papers in the map (data through 14 Oct 2026). Builds on 48 of its 52 references that are in the map. First posted on arXiv 22 Jun 2025.

Builds on

48 of 52 references.

References · 48

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  5. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  6. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  9. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  10. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  11. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  12. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
36 more
  1. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  2. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  3. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  4. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  5. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  6. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  7. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 479
  8. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 422
  9. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  10. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 405
  11. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  12. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 361
  13. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  14. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  15. 2024Latent Action Pretraining from Videoscited by 321
  16. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  17. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
  18. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 217
  19. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 195
  20. 2017DART: Noise Injection for Robust Imitation Learningcited by 191
  21. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 175
  22. 2023AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Plannerscited by 149
  23. 2016EPOpt: Learning Robust Neural Network Policies Using Model Ensemblescited by 138
  24. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 123
  25. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 121
  26. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 116
  27. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 106
  28. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 70
  29. 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 58
  30. 2025RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learningcited by 54
  31. 2024GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMscited by 52
  32. 2024RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effectivecited by 41
  33. 2024G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulationcited by 35
  34. 2025Text2World: Benchmarking Large Language Models for Symbolic World Model Generationcited by 26
  35. 2025AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratorycited by 16
  36. 2024DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulationcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 60; 2026: 458.

518 papers.

Sort:

By area:

  1. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 349
  2. 2026Causal World Modeling for Robot Controlcited by 321
  3. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
  4. 2025Motus: A Unified Latent Action World Modelcited by 251
  5. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  6. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 151
  7. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 139
  8. 2025Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulationcited by 137
  9. 2026A Pragmatic VLA Foundation Modelcited by 103
  10. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 103
  11. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  12. 2026WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Modelscited by 76
38 more
  1. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 75
  2. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 71
  3. 2025Vidar: Embodied Video Diffusion Model for Generalist Manipulationcited by 62
  4. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AIcited by 62
  5. 2026Motubrain: An Advanced World Action Model for Robot Controlcited by 57
  6. 2026LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policiescited by 52
  7. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Modelscited by 51
  8. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 50
  9. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 50
  10. 2026World Action Models: The Next Frontier in Embodied AIcited by 50
  11. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 50
  12. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Trainingcited by 49
  13. 2026World Model for Robot Learning: A Comprehensive Surveycited by 46
  14. 2026AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routingcited by 46
  15. 2025H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulationcited by 45
  16. 2026RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Designcited by 45
  17. 2025Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignmentcited by 41
  18. 2025Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulationcited by 40
  19. 2026RISE: Self-Improving Robot Policy with Compositional World Modelcited by 40
  20. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 40
  21. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 38
  22. 2026World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policycited by 37
  23. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 36
  24. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 36
  25. 2025FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Modelscited by 35
  26. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  27. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 33
  28. 2026RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Taskscited by 33
  29. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalizationcited by 30
  30. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 30
  31. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 30
  32. 2025RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Modelscited by 28
  33. 2026LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queriescited by 27
  34. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 26
  35. 2025Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Braincited by 25
  36. 2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variationscited by 24
  37. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planningcited by 24
  38. 2026JEPA-VLA: Video Predictive Embedding is Needed for VLA Modelscited by 24

50 most cited of 518 All 518 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026RoboTwin-Phys: Do WAMs and VLAs Understand the Physical World? ↗
  2. 2024PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation Tasks
  3. 2026ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning
  4. 2025RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence
  5. 2026RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation
  6. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
  7. 2025REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation
  8. 2024Manipulate-Anything: Automating Real-World Robots using Vision-Language Models