AIRS in the AIR

• 

  林天麟

  AIRS 智能机器人中心主任、香港中文大学（深圳）助理教授

  执行主席

  嘉宾介绍

  个人简介
• 

  胡君杰

  AIRS 智能机器人中心助理研究员

  主持人

  嘉宾介绍

  个人简介
• 

  Martin Saska

  捷克理工大学研究员

  Research of Tightly Cooperating Aerial Vehicles in Real-world Environment

  嘉宾介绍

  Martin Saska received his MSc. degree at Czech Technical University in Prague, 2005, and his Ph.D. degree at University of Wuerzburg, Germany, within the PhD program of Elite Network of Bavaria, 2009. Since 2009, he is a research fellow at Czech Technical University in Prague, where he founded and heads the Multi-robot Systems lab and co-founded Center for Robotics and Autonomous Systems with more than 70 researchers cooperating in robotics. He was a visiting scholar at University of Illinois at Urbana-Champaign, USA in 2008, and at University of Pennsylvania, USA in 2012, 2014 and 2016, where he worked with Vijay Kumar's group within GRASP lab. He is an author or co-author of >150 publications in peer-reviewed conferences with multiple best paper awards and more >50 publications in impacted journals, including IJRR, AURO, JFR, ASC, EJC, with >5500 citations indexed by Scholar and H-index 41. His team won multiple robotic challenges in MBZIRC 2017, MBZIRC 2020 and DARPA SubT competitions.

  个人简介

  Using large teams of tightly cooperating Micro Aerial Vehicles (MAVs) in real-world (outdoor and indoor) environments without precise external localization such as GNSS and motion capture systems is the main motivation of this talk. I will present some insights into the research of fully autonomous, bio-inspired swarms of MAVs relying on onboard artificial intelligence. I will discuss the important research question of whether the MAV swarms can adapt better to localization failure than a single robot. In addition to the fundamental swarming research, I will be talking about real applications of multi-robot systems such as indoor documentation of large historical objects (cathedrals) by formations of cooperating MAVs, a cooperative inspection of underground mines inspired by the DARPA SubT competition, localization and interception of unauthorized drones, aerial firefighting, radiation sources localization, power line inspection, and marine teams of cooperating heterogeneous robots.

• 

  Luis Merino

  巴勃罗·德·奥拉维德大学副教授

  Active Perception for Exploration with Multiple Robots using Information Theory

  嘉宾介绍

  I am Associate Professor at the School of Engineering of the Universidad Pablo de Olavide (UPO), Seville, Spain, where I lead the Service Robotics Laboratory. I led the creation of the Systems Engineering and Automation division of UPO's School of Computer Science, where I have been Vice-Dean for five years.

  I hold a Ph.D. degree on Robotics, from the University of Seville. This thesis was awarded with the ABB Award to the Best Doctoral Dissertation on Robotics 2007 in Spain, given by the Spanish Committee of Automation (CEA, Robotics Group).

  My main research lines deal with cooperative robotic systems, including multi-robot systems and the cooperation between robots and persons. In these lines I have made contributions on new localization and navigation techniques, cooperative perception methods, decision making under uncertainties, and human-robot collaboration in social settings. I am leading or have led UPO’s team as PI in more than 15 international and national projects in these lines. Our group participated in the Mohammed Bin Zayed International Robotics Challenge (MBZIRC) in 2020, where we finished third in the Grand Finale of the competition.

  I serve as Associated Editor of the Image and Vision Computing and IEEE Robotics and Automation Letters journals, and of ICRA and IROS, the two flagship conferences on robotics.

  个人简介

  The talk will deal with the exploration problem using multiple robots. This problem consists of reconstructing, in the most efficient way possible, a spatial model of some phenomenon of interest, such as a 2D/3D map of an area, the spatial distribution of the concentration of a gas or a map of a magnetic field, using measurements from the robot's sensors. Efficiency in this context means obtaining the model with the least possible "effort" by the robots, typically in the shortest possible time, or by performing the minimum number of measurements necessary. If probabilistic models are used, metrics derived from Information Theory can be employed to determine those actions that will be most effective when carrying out the perception task. Specifically, in the talk Gaussian Processes will be considered as those models, and active perception algorithms will be presented for efficient exploration in these cases using a robot. Likewise, the talk will discuss how to extend these techniques to the case of multiple robots efficiently and taking into account the kinematic and communications restrictions present.

视频回顾