首页|Research and Development Center Reports Findings in Robotics (Fall prediction, c ontrol, and recovery of quadruped robots)
Research and Development Center Reports Findings in Robotics (Fall prediction, c ontrol, and recovery of quadruped robots)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics is the subjec t of a report. According to news reporting out of Beijing, People's Republic of China, by NewsRx editors, research stated, "When legged robots perform complex t asks in unstructured environments, falls are inevitable due to unknown external disturbances. However, current research mainly focuses on the locomotion control of legged robots without falling." Our news journalists obtained a quote from the research from Research and Develo pment Center, "This paper proposes a comprehensive decision-making and control f ramework to address the falling over of quadruped robots. First, a capturability -based fall prediction algorithm is derived for planar singlecontact and 3D mul ti-contact locomotion with a predefined gait sequence. For safe fall control, a novel contact-implicit trajectory optimization method is proposed to generate bo th state and input trajectories and contact mode sequences. Specifically, incorp orating uncertainty into the system and terrain models enables mitigating the no n-smoothness of contact dynamics while improving the robustness of the resulting trajectories. Furthermore, a model-free deep reinforcement learning-based appro ach is presented to achieve fall recovery after the robot completes a fall. Expe rimental results demonstrate that the proposed fall prediction algorithm accurat ely predicts robot falls with up to 95% accuracy approximately 395 ms in advance. Compared to classical locomotion controllers, which often struggl e to maintain balance under significant pushes or terrain perturbations, the pre sented framework can autonomously switch to the fall controller approximately 0. 06s after the perturbation, effectively preventing falls or achieving recovery w ith a threefold reduction in touchdown impact velocity."
BeijingPeople's Republic of ChinaAsi aEmerging TechnologiesMachine LearningNano-robotRisk and PreventionRob otRobotics
NETL
NSTL
