Overview

The field studies how to make models and control policies trained in simulation work reliably when they encounter real sensors, physics, objects, and environments. Common approaches include domain randomization, system identification and simulator calibration, real-to-sim-to-real data loops, and shared representations that align simulated and real visual, tactile, or proprioceptive inputs. Researchers apply these methods to tasks such as robotic manipulation, locomotion, navigation, and vehicle control, often testing zero-shot deployment alongside adaptation with limited real-world data. A central tension is that more realistic simulation can improve transfer but is costly to build, while broad randomization may not capture important mismatches; high simulation scores therefore do not always predict real-world performance.

Latest papers

CardsList

354 papers43 papers in the last four weeks, down 43% on the four weeks before. 0.3% of all new papers.

  1. Cyber-Physical RSI for AI-RAN: A Case Study

    Nov 19, 2026Binghan Wu, Kai Zeng, Zhiqi Li +5Recursive Self-ImprovementWireless Communications

  2. Learning Ankle Exoskeleton Control for Reactive Standing Balance Through Neuromusculoskeletal Simulation

    Nov 19, 2026Maria T. Tagliaferri, Inseung KangAnkle Exoskeleton ControlFeedback Control

  3. Planner-Controller Interaction for Ackermann Navigation: A Matched Simulation and Hardware Benchmark

    Nov 18, 2026Moaiz Saeed, Marah Saleh, Mounis Shawgi +1Sim-to-Real TransferRobot Navigation Benchmarks

  4. RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop

    Nov 18, 2026Ghadi Nehme, Dahyun Nam, Akshay Govind Srinivasan +1Agentic AI for RoboticsRobot Morphology-Control Co-Design

  5. Deep Reinforcement Learning for Heat Pump and Underfloor Heating Control: An End-to-End Case Study

    Nov 17, 2026Antonio Manjavacas, David Suárez-Caro, Alejandro Campoy-Nieves +3Heating, Ventilation, and Air Conditioning ControlBuilding Energy Management

  6. SeasonRainBench: Global Seasonal Precipitation

    Nov 17, 2026Qiuyan Sun, Mengxuan Chen, Haoyuan Liang +5Precipitation ForecastingForecasting Benchmarks

  7. UrbanTwin Sim2Real LiDAR Challenge 2026: Site-Calibrated Synthetic Data and Multi-Detector Fusion for Roadside 3D Detection

    Nov 16, 2026Arnav Kumar, Brijesh SoniLidar-Based 3D Object Detection3D Object Detection

  8. Sim-to-Real Room-Mediated Object-Goal Navigation with ROS 2 and Nav2

    Nov 15, 2026Matthew Chua, Adam Scicluna, Gavin PaulObject-Goal NavigationIndoor Robot Navigation

  9. Residual Reinforcement Learning for Visual Servo Control with Zero-Shot Sim-to-Real Transfer

    Nov 14, 2026Mahdi Nobar, Alisa Rupenyan, John Lygeros +1Robot Trajectory TrackingVision-Based Robot Control

  10. Third-Place Solution for the UCF UrbanTwin V2X-Real Track at ECCV 2026: Synthetic Point Cloud Generation and Sim-to-Real 3D Object Detection

    Nov 12, 2026Antong Deng, Yuxin Zhang, Zhongxiang Xing +2Lidar-Based 3D Object DetectionSim-to-Real Transfer

  11. Embedded Sim-to-Real Visual Servoing: Learned Reaching and Force-Guided Placement

    Nov 11, 2026Dezhi Sun, Duy Khang Banh, Kenan NiuVision-Based Robot ControlReal-Time Robot Control

  12. Reading the Table: Sim-to-Real Game State Detection for the Chef's Hat Card Game

    Nov 11, 2026Connor Gäde, Matthias Kerzel, Hauke Bünning +3Robotic PerceptionState Tracking

  13. MiniPose: Miniature-Based Real Data Collection for 6D Pose Estimation of Large Industrial Pipe Segments

    Nov 11, 2026Hyunjun Kim, Youngjin Seo, Sungwon Seo +4Object Pose EstimationRobotic Data Collection

  14. VLA Adaptation with Real and Simulated Data: A Case Study on Robotic Chess

    Nov 9, 2026Matěj Kripner, Milan StrakaVLA AdaptationData-Efficient Robot Learning

  15. GAP: Generalized Adaptation Prior for Dexterous Piano Playing

    Nov 9, 2026Jinyi Chen, Hongyi Li, Lei Jiang +6Robot Policy AdaptationData-Efficient Robot Learning

  16. Probably Safe Sim-to-Real Transfer with Lifetime Validity

    Nov 6, 2026Rohan Tangri, Jan-Peter CalliessSim-to-Real TransferSafe RL

  17. 4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering

    Nov 5, 2026Adnan Armouti, Guanyue Qian, Rajalakshmi NandakumarmmWave Radar SensingDifferentiable Rendering

  18. Educational robotics beyond ROS: a custom library for direct transfer of Webots controllers in the Turtlebot3

    Nov 5, 2026Jaime P. Pérez-Moro, Alejandro Romero, Hector Quintian +1Robotics EducationSim-to-Real Transfer

  19. TactileLab: Sim-to-Real Dexterous Robot Manipulation with Efficient Shear-Sensitive Tactile Simulation

    Nov 5, 2026Yijiong Lin, Wenhao He, Toby Jack +3Tactile SimulationContact-Rich Robotic Manipulation

  20. Training-Independent Validation of a Learning-Based Controller for Stunt Maneuvers

    Nov 5, 2026Kiruthiga Chandra Shekar, Aliasghar Arab, Jingang YiAutonomous Driving Safety EvaluationSim-to-Real Transfer

  21. An Empirical Study of Reinforcement Learning for Keypoint Positioning of Deformable Linear Objects

    Nov 5, 2026Vinay Rodrigues, Sara Zeynalpour, Gokhan Solak +2Deformable Object ManipulationRL for Robotics

  22. Perceptive Humanoid Motion from Simulation

    Nov 4, 2026Siyuan Hu, Abulikemu Abuduweili, Yue Meng +5Humanoid RoboticsSim-to-Real Transfer

  23. TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics

    Nov 4, 2026Shu'ang Sun, Yibo Qiu, Haoliang Ye +5Robotic RLSim-to-Real Transfer

  24. A Practical Causal Framework for Autonomous Mobile Robots: From Simulation to Real-World Human Environments

    Nov 2, 2026Luca Castri, Gloria Beraldo, Nicola BellottoSim-to-Real TransferCausal Inference

  25. Clinician-AI Collaboration in Endovascular Neurointerventions: In-Vitro User Study of Copilot Assistance Modes for Robotic Navigation Across the Autonomy Spectrum

    Nov 2, 2026Nikola Fischer, Harry Robertshaw, S. M. Hadi Sadati +16Human-AI CollaborationRobotic Endovascular Intervention

  26. KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL

    Nov 2, 2026Aswin Ramachandran, Jona Schulz, Maurus Derungs +3Embodied Agent BenchmarksMulti-Agent Reinforcement Learning