講座題目：Towards agile robots in unstructured environments: decision, planning, and control

　　報(bào) 告 人：Zhao Ye 趙燁 教授

　　時(shí)　 間：2018年11月12日(周一)14:00

　　地　 點(diǎn)：中關(guān)村校區(qū)研究生教學(xué)樓5樓創(chuàng)新基地（電梯出口北側(cè)）

　　主辦單位：研究生院、自動(dòng)化學(xué)院

　　報(bào)名方式：登錄北京理工大學(xué)微信企業(yè)號(hào)---第二課堂---課程報(bào)名中選擇“百家大講堂第128期：Towards agile robots in unstructured environments: decision, planning, and control”

【主講人簡介】

  趙燁是哈佛大學(xué)John A. Paulson工程與應(yīng)用科學(xué)學(xué)院的博士后研究員，并將于2019年1月在佐治亞理工學(xué)院的George W. Woodruff機(jī)械工程學(xué)院擔(dān)任助理教授，任佐治亞理工學(xué)院機(jī)器人和智能機(jī)器研究所成員。他于2016年獲得德克薩斯大學(xué)奧斯汀分校的機(jī)械工程博士學(xué)位和UT機(jī)器人聯(lián)合學(xué)位。他于2011年獲得哈爾濱工業(yè)大學(xué)控制科學(xué)與工程學(xué)士學(xué)位。他的研究興趣主要集中在高動(dòng)態(tài)機(jī)器人的規(guī)劃、控制和優(yōu)化算法設(shè)計(jì)。

Ye Zhao is a postdoctoral fellow in the School of Engineering and Applied Science at Harvard University. He will start as an Assistant Professor in The George W. Woodruff School of Mechanical Engineering at Georgia Institute of Technology in January 2019. He will be a member of Institute for Robotics and Intelligent Machines at Georgia Tech. Dr. Zhao received his Ph.D. degree in Mechanical Engineering from The University of Texas at Austin in 2016, where he also obtained the UT Robotics Portfolio degree and was a member of the Human Centered Robotics Laboratory. He received his bachelor degree from Control Science and Engineering at Harbin Institute of Technology in 2011. His research interests lie broadly in planning, control, and optimization algorithms of highly dynamic, contact-rich, and human-centered robots. He is especially interested in challenging locomotion and manipulation problems with formal guarantees on robustness, agility, real-time, and autonomy. Ye's co-authored work has been recognized as the 2017 Thomson Reuters Highly Cited Paper and 2016 IEEE-RAS best whole-body control paper award finalist. He serves as an ICT Chair of IROS 2018 and was a Co-Chair of the IEEE-RAS Student Activities Committee in 2016.

【講座摘要】

  本報(bào)告將討論實(shí)現(xiàn)敏捷和以人為中心的機(jī)器人所必需的新計(jì)算方法，特別關(guān)注在粗糙地形上高度敏捷的腿部運(yùn)動(dòng)的穩(wěn)健最優(yōu)運(yùn)動(dòng)規(guī)劃。該規(guī)劃方法圍繞魯棒混合自動(dòng)機(jī)，由相空間流形定義的干擾度量，動(dòng)態(tài)編程恢復(fù)控制器以及在實(shí)際系統(tǒng)中執(zhí)行的在線運(yùn)動(dòng)規(guī)劃。將這種運(yùn)動(dòng)規(guī)劃方法擴(kuò)展到廣義多接觸運(yùn)動(dòng)行為，描述高層反應(yīng)任務(wù)規(guī)劃器綜合，用于與受約束環(huán)境相互作用的全身運(yùn)動(dòng)，以及如何整合形式化的任務(wù)能力運(yùn)動(dòng)方法。報(bào)告還將介紹偏置最大似然軌跡優(yōu)化算法的最新進(jìn)展，無需考慮接觸模式并能夠處理接觸和模型不確定性。這次報(bào)告將以趙燁教授在佐治亞理工學(xué)院實(shí)驗(yàn)室的未來發(fā)展方向結(jié)束。

This talk will discuss new computational approaches necessary to enable agile and human-centered robots with a special focus on robust optimal motion planning of highly agile legged locomotion over rough terrain. This planning approach revolves around robust hybrid automaton, disturbance metric defined by phase-space manifolds, dynamic programming recovery controller, and online foot placement re-planning for execution in real systems. Extending this motion planning approach to generalized multi-contact locomotion behaviors, I will describe high-level reactive task planner synthesis for whole-body locomotion interacting with constrained environments and how to integrate formal methods for mission-capable locomotion. This talk will also present recent progress on biased maximum likelihood trajectory optimization algorithm without enumerating contact modes and capable of handling contact and model uncertainties. Then it will outline my research on distributed whole-body operational space control and impedance control for latency-prone robotic systems. This talk will end with future directions in my lab at Georgia Tech. If you are interested in joining my lab as a graduate student or visiting scholar, please feel free to talk with me after the talk.