mlsanityData to 7 Oct 2026

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

arXiv 2302.04659 ↗First posted 9 Feb 2023cs.RO cs.AIcited by 313

Not on the map. Why?

Cited by 59 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generalizable manipulation skills, which can be composed to tackle long-horizon and complex daily chores, are one of the cornerstones of Embodied AI. However, existing benchmarks, mostly composed of a suite of simulatable environments, are insufficient to push cutting-edge research works because they lack object-level topological and geometric variations, are not based on fully dynamic simulation, or are short of native support for multiple types of manipulation tasks. To this end, we present ManiSkill2, the next generation of the SAPIEN ManiSkill benchmark, to address critical pain points often encountered by researchers when using benchmarks for generalizable manipulation skills. ManiSkill2 includes 20 manipulation task families with 2000+ object models and 4M+ demonstration frames, which cover stationary/mobile-base, single/dual-arm, and rigid/soft-body manipulation tasks with 2D/3D-input data simulated by fully dynamic engines. It defines a unified interface and evaluation protocol to support a wide range of algorithms (e.g., classic sense-plan-act, RL, IL), visual observations (point cloud, RGBD), and controllers (e.g., action type and parameterization). Moreover, it empowers fast visual input learning algorithms so that a CNN-based policy can collect samples at about 2000 FPS with 1 GPU and 16 processes on a regular workstation. It implements a render server infrastructure to allow sharing rendering resources across all environments, thereby significantly reducing memory usage. We open-source all codes of our benchmark (simulator, environments, and baselines) and host an online challenge open to interdisciplinary researchers.

Key facts. Cited by 313 papers in the map (data through 7 Oct 2026). Builds on 33 of its 57 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

33 of 57 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  7. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  8. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  9. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  10. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  11. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  12. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
21 more
  1. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  2. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  3. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  4. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249
  5. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
  6. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  7. 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 161
  8. 2021Tianshou: a Highly Modularized Deep Reinforcement Learning Librarycited by 139
  9. 2020SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulationcited by 118
  10. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 115
  11. 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 101
  12. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 100
  13. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 64
  14. 2020EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulationcited by 61
  15. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  16. 2022EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Enginecited by 58
  17. 2019Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Taskscited by 56
  18. 2019S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenescited by 51
  19. 2022Multi-skill Mobile Manipulation for Object Rearrangementcited by 46
  20. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 31
  21. 2022Improving Policy Optimization with Generalist-Specialist Learningcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 26; 2024: 79; 2025: 97; 2026: 111.

313 papers.

Sort:

By area:

  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  3. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  4. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  5. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  6. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  7. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  8. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  9. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 216
  10. 2024VideoPhy: Evaluating Physical Commonsense for Video Generationcited by 215
  11. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 206
  12. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
38 more
  1. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 168
  2. 2023Text2Reward: Reward Shaping with Language Models for Reinforcement Learningcited by 153
  3. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 146
  4. 2025Unified Vision-Language-Action Modelcited by 128
  5. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  6. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 117
  7. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
  8. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  9. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 104
  10. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 83
  11. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  12. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  13. 2024Simplifying Deep Temporal Difference Learningcited by 71
  14. 2023ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenescited by 68
  15. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 68
  16. 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robotscited by 65
  17. 2023DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objectscited by 64
  18. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 64
  19. 2024SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splattingcited by 63
  20. 2024Policy Decorator: Model-Agnostic Online Refinement for Large Policy Modelcited by 60
  21. 2025EnerVerse: Envisioning Embodied Future Space for Robotics Manipulationcited by 59
  22. 2025Embodied AI Agents: Modeling the Worldcited by 57
  23. 2024PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigatorscited by 55
  24. 2024GRUtopia: Dream General Robots in a City at Scalecited by 54
  25. 2024A Survey on Robotics with Foundation Models: toward Embodied AIcited by 53
  26. 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priorscited by 53
  27. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrationscited by 51
  28. 2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 48
  29. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 48
  30. 2025VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulationcited by 46
  31. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 46
  32. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  33. 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learningcited by 45
  34. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  35. 2024VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulationcited by 43
  36. 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Modelscited by 43
  37. 2024From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessonscited by 42
  38. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 42

50 most cited of 313 All 313 (JSON)