公司人工智能与机器人国际学术讲坛

Nankai University International E-Forum on Artificial Intelligence and Robotics

第七期

l 2021年6月15日（周二） 腾讯会议：637 206 384

报告16：

报告时间：2021年6月15日（周二）15:00p.m.~16:00p.m. (Beijing Time)

腾讯会议：637 206 384

Speaker : Prof. Lounis Adouane

Heudiasyc, UMR CNRS/UTC 7253

Université de Technologie de Compiègne (France) 法国贡比涅技术大学

报告题目：Toward fully autonomous vehicle while ensuing enhanced safety and flexibility

Abstract: This talk, in addition to give an overview of the research activities made in Heudiasyc laboratory, it will make the focus on the way to increase gradually the autonomy of mobile mono-robot as well as Multi-Robot Systems (MRS) to achieve complex tasks. Its main objective is to given an overview of the developed generic control architectures, and their different components, in order to enhance the safety, flexibility and the reliability of autonomous navigations in complex environments (e.g., cluttered, uncertain and/or dynamic). The proposed control architectures (decision/action) have been addressed through three closely related elements: task modeling (e.g., according for instance to appropriate local or global reference frames); planning/re-planning and finally the control aspects. More precisely the main discussed complementary components deal with: reliable and flexible obstacle avoidance; stable control laws for target reaching/tracking; optimal short-term and long-term trajectories/waypoints planning (set-points definition); safe and flexible navigation through sequential waypoints; cooperative control and interaction of a group of mobile robots. Furthermore, among the main ideas developed in this talk are those related to the potentiality of using multi-controller architectures (well-known initially in the literature as behavioral control architectures). Indeed, using this kind of control permits us to break the complexity of the overall tasks to be carried out and therefore allows a bottom-up development. This will imply the development of appropriate reliable elementary controllers (obstacle avoidance, target reaching/tracking, formation maintaining, etc.), but also the proposition of appropriate mechanisms to manage the controllers’ interactions characterizing these kinds of architectures, which ensures the respect of different constraints and enhancing metrics/criteria linked to the overall control reliability. Although the developed concepts/methods/architectures could be applied for different domains (such as service robotics or agriculture), the transportation-related purposes remains the privileged target. Applications include the transportation of persons (private car or public transport) as well as merchandise transportation (in warehouses or ports for instance).

Biography: Lounis Adouane is Full Professor since September 2019 at Heudiasyc – UTC (Université de Technologie de Compiègne, France), and he was Associate Professor between 2006 and 2019 at the Institut Pascal (IP) - Polytech Clermont-Ferrand. In IP, he leaded between 2018 and 2019 the ISPR group (80 persons, Images, Perception Systems and Robotics). Dr. Adouane is an active member of the international community of mobile robotics/autonomous vehicles, he is member of Technical Committee of Intelligent Autonomous Vehicles – IFAC and Multi-Robot Systems – IEEE RAS, and he serves as an Editorial Board Member of the Journal of Intelligent and Robotic Systems. He has been participated to more than 20 program committees of international conferences and workshops. Dr. Adouane had the opportunity to visit several institutions/laboratories, such as 6 months in 2014 at Cranfield and Kingston universities (United Kingdom) and 2 months in 2018 at KIT (Karlsruhe Institute of Technology, Germany). In terms of academic training, Dr. Adouane received an M.Sc in 2001 from LS2N - ECN Nantes, where he worked on the control of legged mobile robotics. In 2005, he obtained a PhD in automatic control from FEMTO-ST laboratory-UFC Besançon. During his PhD studies, he deeply investigated the field of multi-robot systems, especially those related to bottom-up and hybrid control architectures. After that, he joined in 2005 Ampère laboratory–INSA Lyon and studied hybrid (continuous/discrete) control architectures applied to cooperative mobile robot arms. In 2015, he obtained from Blaise Pascal University a HDR (habilitation to steer research in Robotics). Dr. Adouane’s main teaching and research activities are linked to robotics / automatic control and artificial intelligence. His current research focuses on Intelligent Vehicles (autonomous and clean vehicles), more specifically, he is working on three main topics (cf. below). Their objectives are to increase decision-making autonomy (topic 1 and 2) but also energetic autonomy (topic 3, more recently investigated (started in 2015)) of the studied complex systems:

1. Autonomous navigation of mobile robots / vehicles in complex environments

2. Cooperative control architectures for multi-robot / vehicle systems

3. Optimized energy management of dynamic hybrid electric vehicles

More details could be seen via this webpage: http://LounisAdouane.online.fr/

Dr. Adouane is the author/coauthor of more than 120 refereed international papers and two books. His main research interest include planning and control of mobile robots / intelligent vehicles (autonomous and clean), decision-making under uncertainty, hybrid (continuous/discrete) and hybrid (reactive/cognitive) multi-controller architectures, Lyapunov based synthesis and stability, cooperative multi-robot systems, artificial intelligence (e.g., MDP or MAS approaches), energy management (e.g., with optimal control or neuro-fuzzy approaches).