Advancing Robot Autonomy: Active Robot Learning and Perception

  • A+

:纪赜(英国卡迪夫大学)
:2024-09-23 15:00
:海韵园行政楼C503

报告人:纪赜(英国卡迪夫大学)

 间:202492315:00

 点:海韵园行政楼C503

内容摘要:

This talk explores the fusion of robotics and reinforcement learning, for autonomous robot manipulation and navigation. A critical focus of the talk revolves around the application of reinforcement learning in robotics. Specifics of employing reinforcement learning for manipulation tasks and navigation challenges are detailed. This paradigm enables robots to acquire complex skills, navigate intricate environments, and execute multifaceted manipulation tasks effectively. Specific application cases include using a robot arm for manipulating long-horizon tasks or handling entangled objects, as well as autonomous navigation problems. This talk aims to ignite some discussions about the advancements in merging robot perception and robot learning to bolster higher-level robot autonomy. These advancements promise a future where robots or humans seamlessly integrate into diverse domains, from manufacturing to healthcare, achieving intricate objectives in harmony.  

人简介

纪赜, 卡迪夫大学工程学院高级讲师(副教授),皇家工程院工业奖学金获得者。纪博士领导机器人和自主智能机器 (RAIM) 研究小组,也是由 ERDF/WEFO 资助的 IROHMS(人工智能、机器人和人机系统研究中心)的联合研究员。纪博士获得了卡迪夫大学的博士学位。他最近担任 EPSRCBBSRC、皇家工程院、EU H2020、皇家学会、工业等资助的多个项目的 PI Co-I。他还曾在工业界(戴森、ASV、联想)从事机器人和自主系统领域的工作。他在机器人方面拥有丰富的经验,包括室内移动机器人、工业机器人操纵器和自主地面车辆。他目前的研究重点是机器人视觉、强化学习、机器学习、同步定位和地图绘制(SLAM)、触觉感知及其在自主机器人导航、操作和智能制造中的应用。

 

联系人:宋宇萍