Hall of Fame

Robots trained in RaiSim have run a marathon on one battery charge, raced across beach sand and hiked alpine trails. These papers report results obtained with RaiSim, newest first. To cite RaiSim itself, see Acknowledgement.

Published work that used RaiSim? Tell us at raisim@raionrobotics.com and we will add it.

Nature

1. 2026
   A quadruped robot designed to complete a marathon on a single battery charge

   C. Lee, D. Youm, J. Park, J. Lee, S. Choi, G. Ji, J. Mun, M. Jung, H. C. Choi, H. Kim, H. Oh, K. Nam, M. Lee, J. Hur, D. Choi, D. Kim, Y. An, J. Hwangbo. Nature 658(8135), 372–379, 2026. KAIST.

   RAIBO2 ran a full marathon on one battery charge, in 4 hours 19 minutes.

Science Robotics

1. 2025
   High-speed control and navigation for quadrupedal robots on complex and discrete terrain

   H. Kim, H. Oh, J. Park, Y. Kim, D. Youm, M. Jung, M. Lee, J. Hwangbo. Science Robotics 10(102), eads6192, 2025. KAIST.

   Raibo runs on vertical walls, jumps a 1.3 m gap and crosses stepping stones at 4 m/s.

2. 2023
   Learning quadrupedal locomotion on deformable terrain

   S. Choi, G. Ji, J. Park, H. Kim, J. Mun, J. H. Lee, J. Hwangbo. Science Robotics 8(74), eade2256, 2023. KAIST.

   Raibo runs on soft beach sand at 3.03 m/s, its feet buried at every step.

3. 2022
   Learning robust perceptive locomotion for quadrupedal robots in the wild

   T. Miki, J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, M. Hutter. Science Robotics 7(62), eabk2822, 2022. ETH Zurich, KAIST and Intel.

   ANYmal fuses vision and proprioception with zero falls in alpine, forest, underground and urban terrain.

4. 2020
   Learning quadrupedal locomotion over challenging terrain

   J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, M. Hutter. Science Robotics 5(47), eabc5986, 2020. ETH Zurich, KAIST and Intel.

   Without vision, ANYmal trots through mud, sand, rubble, thick vegetation, snow and running water.

5. 2019
   Learning agile and dynamic motor skills for legged robots

   J. Hwangbo, J. Lee, A. Dosovitskiy, D. Bellicoso, V. Tsounis, V. Koltun, M. Hutter. Science Robotics 4(26), eaau5872, 2019. ETH Zurich and Intel.

   ANYmal runs faster than ever before and recovers from falls, with policies trained in simulation.

Other venues

1. 2022
   Concurrent training of a control policy and a state estimator for dynamic and robust legged locomotion

   G. Ji, J. Mun, H. Kim, J. Hwangbo. IEEE Robotics and Automation Letters 7(2), 2022. KAIST.

   The policy and its state estimator learn together, for dynamic and robust locomotion.

2. 2021
   RMA: Rapid Motor Adaptation for Legged Robots

   A. Kumar, Z. Fu, D. Pathak, J. Malik. Robotics: Science and Systems XVII, 011, 2021. UC Berkeley, CMU and Meta AI.

   An A1 adapts to new terrain in a fraction of a second, with no fine-tuning on the robot.

3. 2021
   Circus ANYmal: A quadruped learning dexterous manipulation with its limbs

   F. Shi, T. Homberger, J. Lee, T. Miki, M. Zhao, F. Farshidian, K. Okada, M. Inaba, M. Hutter. IEEE International Conference on Robotics and Automation pp. 2316–2323, 2021. The University of Tokyo and ETH Zurich.

   ANYmal balances and manipulates a light ball with its limbs, transferred zero-shot from simulation.

4. 2020
   DeepGait: Planning and control of quadrupedal gaits using deep reinforcement learning

   V. Tsounis, M. Alge, J. Lee, F. Farshidian, M. Hutter. IEEE Robotics and Automation Letters, 2020. ETH Zurich.

   A learned gait planner and controller cross narrow bridges, gaps and stepping stones in simulation.