mlsanityData to 7 Oct 2026

The Reality Gap in Robotics: Challenges, Solutions, and Best Practices

arXiv 2510.20808 ↗First posted 23 Oct 2025cs.RO cs.AI cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Machine learning has facilitated significant advancements across various robotics domains, including navigation, locomotion, and manipulation. Many such achievements have been driven by the extensive use of simulation as a critical tool for training and testing robotic systems prior to their deployment in real-world environments. However, simulations consist of abstractions and approximations that inevitably introduce discrepancies between simulated and real environments, known as the reality gap. These discrepancies significantly hinder the successful transfer of systems from simulation to the real world. Closing this gap remains one of the most pressing challenges in robotics. Recent advances in sim-to-real transfer have demonstrated promising results across various platforms, including locomotion, navigation, and manipulation. By leveraging techniques such as domain randomization, real-to-sim transfer, state and action abstractions, and sim-real co-training, many works have overcome the reality gap. However, challenges persist, and a deeper understanding of the reality gap's root causes and solutions is necessary. In this survey, we present a comprehensive overview of the sim-to-real landscape, highlighting the causes, solutions, and evaluation metrics for the reality gap and sim-to-real transfer.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 123 of its 166 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

123 of 166 references.

References · 123

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  5. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  6. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  7. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  8. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  10. 2019Solving Rubik's Cube with a Robot Handcited by 699
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  12. 2018Learning Dexterous In-Hand Manipulationcited by 643
38 more
  1. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  2. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
  3. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  4. 2019The frontier of simulation-based inferencecited by 490
  5. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  6. 2017Robust Adversarial Reinforcement Learningcited by 439
  7. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  8. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  9. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  10. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  11. 2019Learning by Cheatingcited by 361
  12. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  13. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  14. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  15. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 277
  16. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  17. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  18. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
  19. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  20. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  21. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  22. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 203
  23. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 202
  24. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  25. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 161
  26. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  27. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  28. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 136
  29. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 135
  30. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
  31. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  32. 2025A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationcited by 125
  33. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 106
  34. 2022Navigating to Objects in the Real Worldcited by 104
  35. 2021Learning High-Speed Flight in the Wildcited by 98
  36. 2022Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotioncited by 98
  37. 2018Driving Policy Transfer via Modularity and Abstractioncited by 91
  38. 2017Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigationcited by 90

50 most cited of 123 All 123 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 20.

22 papers.

Sort:

By area:

  1. 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Modelcited by 5
  2. 2025House of Dextra: Cross-embodied Co-design for Dexterous Handscited by 4
  3. 2026Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulatorscited by 2
  4. 2026A testable framework for AI alignment: Simulation Theology as an engineered worldview for silicon-based agentscited by 1
  5. 2026Approximate Imitation Learning for Event-based Quadrotor Flight in Cluttered Environmentscited by 1
  6. 2025Posterior-driven Heuristic Support Adaptation in a Probabilistic Treatment of Real2Sim2Real for Vision-Driven Deformable Linear Object Manipulationcited by 0
  7. 2026RAPID: Reconfigurable, Adaptive Platform for Iterative Designcited by 0
  8. 2026aerial-autonomy-stack -- a Faster-than-real-time, Autopilot-agnostic, ROS2 Framework to Simulate and Deploy Perception-based Dronescited by 0
  9. 2026Deepmechanicscited by 0
  10. 2026Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Explorationcited by 0
  11. 2026When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisitedcited by 0
  12. 2026WorldString: Actionable World Representationcited by 0
10 more
  1. 2026Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deploymentcited by 0
  2. 2026Robustness of Robotic Manipulation: Foundations and Frontierscited by 0
  3. 2026Real-Time Source-Free Object Detectioncited by 0
  4. 2026Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learningcited by 0
  5. 2026Towards Illusions Awareness in Cyber-Physical System's Designcited by 0
  6. 2026A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policiescited by 0
  7. 2026A Deployment Study of Identity-Gated Drone Gesture Controlcited by 0
  8. 2026Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvagecited by 0
  9. 2026Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluationcited by 0
  10. 2026Domain generalization and synthetic data in object detection: the enabler, the probe, and the gapcited by 0