Quadrupedal Robot
Quadrupedal robots are increasingly studied for their potential in diverse applications, from assisting humans in various settings to exploring challenging environments. Current research emphasizes developing robust locomotion controllers, often employing reinforcement learning (RL) algorithms, including model-based and model-free approaches, and incorporating advanced sensor fusion techniques for obstacle avoidance and terrain adaptation. This work is significant because it advances the capabilities of legged robots, leading to improved performance in complex tasks and expanding their potential impact across various fields, including search and rescue, construction, and healthcare.
Papers
Probabilistic approach to feedback control enhances multi-legged locomotion on rugged landscapes
Juntao He, Baxi Chong, Jianfeng Lin, Zhaochen Xu, Hosain Bagheri, Esteban Flores, Daniel I. Goldman
Multi-Objective Algorithms for Learning Open-Ended Robotic Problems
Martin Robert, Simon Brodeur, Francois Ferland
Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
Hongbo Zhang, Zhongyu Li, Xuanqi Zeng, Laura Smith, Kyle Stachowicz, Dhruv Shah, Linzhu Yue, Zhitao Song, Weipeng Xia, Sergey Levine, Koushil Sreenath, Yun-hui Liu
Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives
Maurya Gurram, Prakash Kumar Uttam, Shantipal S. Ohol