paper-with-me

Papers

Learning agile and dynamic motor skills for legged robots

2019-01-24 · Jemin Hwangbo, JoonHo Lee, Alexey Dosovitskiy, Dario Bellicoso, Vassilios Tsounis, Vladlen Koltun, Marco Hutter

Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations.

📄 PDF Abstract BibTeX arXiv:1901.08652

Code (2)

junja94/anymal_science_robotics_supplementary 공식 구현
awesomericky/complex-env-navigation pytorch

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion

2024-01-31 · Tairan He, Chong Zhang, Wenli Xiao, Guanqi He 외

Legged robots navigating cluttered environments must be jointly agile for efficient task execution and safe to avoid collisions with obstacles or humans. Existing studies either develop conservative controllers (< 1.0 m/…

MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots

2026-05-13 · Yuqi Li, Peng Zhai, Yueqi Zhang, Xiaoyi Wei 외 arxiv

Wheeled-legged robots hold promise for traversing complex terrains and offer superior mobility compared to legged robots. However, wheeled-legged robots must effectively balance both wheeled driving and legged control. F…

Learning and Adapting Agile Locomotion Skills by Transferring Experience

2023-04-19 · Laura Smith, J. Chase Kew, Tianyu Li, Linda Luu 외

Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running. However, designing robust controllers for highly agile dynamic motions remains a substant…

Reinforcement Learning (RL)

Learning Highly Dynamic Skills Transition for Quadruped Jumping Through Constrained Space

2026-08-20 · Zeren Luo, Jiahui Zhang, Yimin Han, Ji Ma 외 arxiv

Although legged animals are capable of performing explosive motions while traversing confined spaces, replicating this behavior in quadrupedal robots has been a longstanding challenge. Here, we propose a hierarchical rei…

Hierarchical Reinforcement Learning

Learning Agile Robotic Locomotion Skills by Imitating Animals

2020-04-02 · Xue Bin Peng, Erwin Coumans, Tingnan Zhang, Tsang-Wei Lee 외

Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics. While manually-designed controllers have been able to emulate many complex behaviors, building such controller…

Domain AdaptationImitation LearningReinforcement Learning