FAST Lab’s recent work “EGO-Swarm” made frontpage news of Science Magazine
On December 16, 2020, the FAST Lab’s recent work “EGO-Swarm” made the frontpage news of Science (www.ScienceMag.org).Led by Prof. XU Chao and Dr. GAO Fei, the FAST (Field Autonomous System & compuTing) Lab is part of the Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University. It is mainly engaged in the fields of Autonomous Systems (navigation, control, motion planning, perception, SLAM, etc.), AI (imaging, vision, machine learning, control, etc.) for Turbulent Flows, Data-driven Science and Engineering, and Synergy of AI and Control.The recent work of the lab, EGO-Swarm, is a decentralized and asynchronous systematic solution for multi-robot autonomous navigation in unknown obstacle-rich scenes using merely onboard resources. The planning system is formulated under gradient-based local planning framework, where collision avoidance is achieved by formulating the collision risk as a penalty of a nonlinear optimization problem. In order to improve robustness and escape local minima, the team incorporates a lightweight topological trajectory generation method. Then agents generate safe, smooth, and dynamically feasible trajectories in only several milliseconds using an unreliable trajectory sharing network. Relative localization drift among agents is corrected by using agent detection in depth images. The method is demonstrated in both simulation and real-world experiments.The first author of the paper is ZHOU Xin, a first-year graduate student, and the corresponding author is Dr. GAO Fei.To read the Science news: https://www.sciencemag.org/news/2020/12/watch-swarm-drones-fly-through-heavy-forest-while-staying-formationTo watch the video: https://www.youtube.com/watch?v=IujQzSQtaTU&ab_channel=ScienceMagazineTo read the preprint: https://arxiv.org/abs/2011.04183Reporter: WANG ZhichengEditor: WANG Jing
MORE >CSE loved “dog” Jueying shows up on Science Robotics Cover
Jueying, the dog-like bionic quadruped robot, shows up on the cover of Science Robotics, December 2020 for its agile motor skill newly learned with machine learning methods. The related paper “Multi expert learning of adaptive legged localization” is published online in this issue as a long research article and is selected as the cover paper.Jueying is developed by researchers from the College of Control Science and Engineering, Zhejiang University, working as a platform for pioneer research on applications of deep learning on robot control. In cooperation with researchers from the University of Edinburg, a multi expert learning architecture (MELA) based on deep reinforcement learning is proposed to train robots to achieve fast and flexible motion response in unknown environment. During training, MELA is initialized by pretrained neural network (DNN) and trained under the construction of a gating neural network that allows MELA to learn about transitional skills across various modes. During runtime, MELA constantly blends multiple DNNs and dynamically synthesizes a new one to produce adaptive behaviors in response to changing situations. This approach leverages the advantages of trained expert skills and the fast online synthesis of adaptive policies to generate responsive motor skills during the changing tasks. Using one unified MELA framework, the team demonstrated successful multiskill locomotion on a real quadruped robot Jueying that performed coherent trotting, steering, and fall recovery autonomously.To read the paper, please visit: https://robotics.sciencemag.org/content/5/49/eabb2174Reporter: WANG ZhichengEditor: WANG Jing
MORE >