RAIBERT M H , BLANKESPOOR K , NELSON G , et al. Bigdog, the rough-terrain quadruped robot [C ] //Proceedings of the 17th IFAC World Congress. Seoul, Korea:IFAC , 2008 , 41 ( 2 ): 10822 - 10825 .

BLEDT G , POWELL M J , KATZ B , et al. MIT Cheetah 3: Design and control of a robust, dynamic quadruped robot [C ] // Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, D. C. , US : IEEE , 2018 : 2245 - 2252 .

KATZ B , CARLO J D , KIM S . Mini Cheetah: a platform for pushing the limits of dynamic quadruped control [C ] // Proceedings of the 2019 International Conference on Robotics and Automation. Montreal , Canada : IEEE , 2019 : 6295 - 6301 .

bostondynamics . Atlas and beyond: the world’s most dynamic robots [EB/OL ] . [ 2023-12-07 ] . https://bostondynamics.com/atlas/ https://bostondynamics.com/atlas/ https://bostondynamics.com/atlas/.

SHIGEMI S . ASIMO and humanoid robot research at Honda [J ] . Humanoid Robotics: A Reference. Berlin, Germany: Springer , 2018 : 55 - 90 .

KRISHNA L , CASTILLO G A , MISHRA U A , et al. Linear policies are sufficient to realize robust bipedal walking on challenging terrains [J ] . IEEE Robotics and Automation Letters , 2022 , 7 ( 2 ): 2047 - 2054 DOI: 10.1109/LRA.2022.3143227 http://doi.org/10.1109/LRA.2022.3143227 https://ieeexplore.ieee.org/document/9682564/ https://ieeexplore.ieee.org/document/9682564/

AHN M S . Development and real-time optimization-based control of a full-sized humanoid for dynamic walking and running [D ] . Los Angeles,CA , US : University of California , 2023 .

REHER J , COUSINEAU E A , HEREID A , et al. Realizing dynamic and efficient bipedal locomotion on the humanoid robot DURUS [C ] // Proceedings of the 2016 IEEE International Conference on Robotics and Automation. Stockholm , Sweden : IEEE , 2016 : 1794 - 1801 .

RAIBERT M H . Legged robots that balance [M ] . Cambridge, MA , US : MIT Press , 1986 .

MICHAEL K . Meet Boston dynamics’ LS3 — the latest robotic war machine [J ] . TEDxUWollongong Talk , 2012 .

ANGLE M . Modeling, design and optimization of permanent magnet synchronous machines [R ] . Cambridge,MA , US : MIT , 2016 .

KATZ B G . A low cost modular actuator for dynamic robots [R ] . Cambridge,MA , US : MIT , 2018 .

CARLO J D , WENSING P M , KATZ B , et al. Dynamic locomotion in the mit cheetah 3 through convex model-predictive control [C ] // Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems.Madrid, Spain:IEEE , 2018 .

KIM D , CARLO J D , KATZ B , et al. Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control: arXiv:1909.06586v1 [R ] . Ithaca,NY , US : Cornell University , 2019 : 1909 .06586v1.

HWANGBO J , LEE J , DOSOVITSKIY A , et al. Learning agile and dynamic motor skills for legged robots [J ] . Science Robotics , 2019 , 4 ( 26 ): 1 - 20 .

LEE J , HWANGBO J , WELLHAUSEN L , et al. Learning quadrupedal locomotion over challenging terrain [J ] . Science Robotics , 2020 , 5 ( 47 ): eabc5986 . DOI: 10.1126/scirobotics.abc5986 http://doi.org/10.1126/scirobotics.abc5986 https://www.science.org/doi/10.1126/scirobotics.abc5986 https://www.science.org/doi/10.1126/scirobotics.abc5986 A learning-based locomotion controller enables a quadrupedal ANYmal robot to traverse challenging natural environments.

MIKI T , LEE J , HWANGBO J , et al. Learning robust perceptive locomotion for quadrupedal robots in the wild [J ] . Science Robotics , 2022 , 7 ( 62 ): eabk2822 . DOI: 10.1126/scirobotics.abk2822 http://doi.org/10.1126/scirobotics.abk2822 https://www.science.org/doi/10.1126/scirobotics.abk2822 https://www.science.org/doi/10.1126/scirobotics.abk2822 Legged robots that can operate autonomously in remote and hazardous environments will greatly increase opportunities for exploration into underexplored areas. Exteroceptive perception is crucial for fast and energy-efficient locomotion: Perceiving the terrain before making contact with it enables planning and adaptation of the gait ahead of time to maintain speed and stability. However, using exteroceptive perception robustly for locomotion has remained a grand challenge in robotics. Snow, vegetation, and water visually appear as obstacles on which the robot cannot step or are missing altogether due to high reflectance. In addition, depth perception can degrade due to difficult lighting, dust, fog, reflective or transparent surfaces, sensor occlusion, and more. For this reason, the most robust and general solutions to legged locomotion to date rely solely on proprioception. This severely limits locomotion speed because the robot has to physically feel out the terrain before adapting its gait accordingly. Here, we present a robust and general solution to integrating exteroceptive and proprioceptive perception for legged locomotion. We leverage an attention-based recurrent encoder that integrates proprioceptive and exteroceptive input. The encoder is trained end to end and learns to seamlessly combine the different perception modalities without resorting to heuristics. The result is a legged locomotion controller with high robustness and speed. The controller was tested in a variety of challenging natural and urban environments over multiple seasons and completed an hour-long hike in the Alps in the time recommended for human hikers.

KUMAR A , FU Z , PATHAK D , et al. RMA: rapid motor adaptation for legged robot: arXiv:2107.04034v1 [R ] . Ithaca,NY , US : Cornell University , 2021 : 2107 .04034v1.

MARGOLIS G B , YANG G , PAIGWAR K , et al. Rapid locomotion via reinforcement learning [C ] // Proceedings of Robotics : Science and Systems . New York,NY, US : Amazon Robotics ,2022. 2205 . 02824 .

MARGOLIS G B , AGRAWAL P . Walk these ways: tuning obot control for generalization with multiplicity of behavior [C ] // Proceedings of the Conference on Robot Learning. Atlanta, GA , US : PMLR , 2023 : 22 - 31 .

KRISHNA L , CASTILLO G A , MISHRA U A , et al. Linear policies are sufficient to realize robust bipedal walking on challenging terrains [J ] . IEEE Robotics and Automation Letters , 2022 , 7 ( 2 ): 2047 - 2054 . DOI: 10.1109/LRA.2022.3143227 http://doi.org/10.1109/LRA.2022.3143227 https://ieeexplore.ieee.org/document/9682564/ https://ieeexplore.ieee.org/document/9682564/

HAN L , ZHU Q X , SHENG J P , et al. Lifelike agility and play on quadrupedal robots using reinforcement learning and generative pre-trained models: arXiv:2308.15143 [R ] . Ithaca,NY , US : Cornell University , 2023 : 2308 .15143.