This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of actions of estimated the state-action trajectories, and then applies the optimal actions to maximize the reward. To achieve online model adaptation, our proposed method learns different latent vectors of each training condition, which are selected online given the newly collected data. Our work designs appropriate state space and reward functions, and optimizes feasible actions in an MPC fashion which are then sampled directly in the joint space considering constraints, hence requiring no prior design of specific walking gaits. We further demonstrate the robot's capability of detecting unexpected changes during interaction and adapting control policies quickly. The extensive validation on the SpotMicro robot in a physics simulation shows adaptive and robust locomotion skills under varying ground friction, external pushes, and different robot models including hardware faults and changes.
MotorFactory: A Blender Add-on for Large Dataset Generation of Small Electric Motors
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术与图像利用研究所IOSB）
Design and Implementation of Prosthetic Arm using Gear Motor Control Technique with Appropriate Testing
Durgapur Institute of Advanced Technology & Management（杜尔加布尔高级技术与管理学院）；Saroj Mohan Institute of Technology（萨罗吉·莫汉技术学院）；RCC Institute of Information Technology（RCC信息技术学院）；Kalyani Government Engineering College（卡利亚尼政府工程学院）；Jadavpur University（贾达普大学）
Collision Induced Binding and Transport of Shape Changing Robot Pairs
School of Physics, Georgia Institute of Technology（佐治亚理工学院物理系）；Apple Inc.（苹果公司）；Department of Mechanical Engineering, Stanford University（斯坦福大学机械工程系）；Department of Physics, Princeton University（普林斯顿大学物理系）；Department of Physics, Bar-Ilan University（巴伊兰大学物理系）；Institute for Robotics and Intelligent Machines, Georgia Institute of Technology（佐治亚理工学院机器人与智能机器研究所）；George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院乔治·W·伍德鲁夫机械工程学院）
Control of a commercially available vehicle by a tetraplegic human using a brain-computer interface
California Institute of Technology（加州理工学院）；Ford Motor Company（福特汽车公司）；Blackrock Neurotech（黑石神经技术公司）；Casa Colina Hospital and Centers for Healthcare（卡萨科利纳医院与医疗中心）；University of California Los Angeles（加州大学洛杉矶分校）；University of Southern California（南加州大学）；The University of Utah（犹他大学）
