Distinguished Scholar Forum
Title: Preconditions of AI technologies: From closedness to non-closedness
Panelist: Xiaoping Chen（陈小平）
Abstract: As research on Artificial Intelligence is progressing rapidly in its extension and depth, it permeates to adjacent disciplines extensively and deeply. In the first part of this lecture, I will clarify the existing AI technology systematically, summarizing two sorts (thinking machines/intelligent machinery) and two modes of thinking (brute-force/training) of AI. In the second part, I will indicate the precondition of existing AI technology, i.e., the principle of closedness, which specifies the limitation and applicability of the brute-force and the training approaches. A prospect of the fourth wave of AI and a brief description of some efforts to transcend closedness (the Open Knowledge and Rong-Cha approaches) are presented in the last part.
Panelist: Panfeng Huang（黄攀峰）
Abstract: 进入21 世纪以来，航天器在轨服务与维护技术已成为航天高技术领域发展的新热点和国家安全
报告人：黄攀峰，香港中文大学博士，西北工业大学自动化学院院长，教授，博士生导师，国家杰出青年基金获得者，国家“万人计划”科技创新领军人才，国防科技卓越青年基金获得者，国家重点研发计划项目首席科学家。现任中央军委科技委专家组专家，国家2030新一代人工智能重大项目专家组专家，载人航天应用与服务专家组特邀专家。曾任国家863 计划重大项目专家组专家，国家重大任务副总师。主要研究方向：空间机器人技术、遥操作技术、航天器智能控制、人机混合智能控制等。先后主持国家重点研发计划项目，国家自然基金委重点项目，军委科技委项目、载人航天工程、国家863 计划重大项目，重点项目等30 余项。负责研发了我国首套空间机械臂地面遥操作系统，在我国首次成功实施了人在地面对空间机械手的遥操作；首次系统性的提出并发展了空间绳系机器人系统的设计理论和方法。在机器人与控制领域重要期刊上发表SCI 论文100 余篇，出版中英文专著4 部，获授权国家发明专利70 余件；先后获得军队科技进步一等奖，国防技术发明二等奖等多项科技奖励；获得国家863 计划“十二五”优秀创新团队首席等荣誉称号。
Title: Integrated Coastal Zone Aerial Perception with UAV
Panelist: Hailong Pei（裴海龙）
Abstract: The coastal zone is a corridor in which the sea interfaces the land, containing the coast parts,
the nearshore water bodies and the underwater bottoms. Because of the extreme terrestrial-aquatic transition environment, it is difficult for personnel to implement the multi-element direct surveying (coast land, waterline, nearshore hydrology, etc.). The existing remote sensing techniques are also not efficient for accurate spatio-temporal measuring under this dynamic circumstance, especially for large region survey. This talk introduces the application of UAV remote sensing technology in coastal zone exploration, focusing on the low-altitude small UAV wave observation and moving inverse mechanism of bathymetry perception, along with the airborne survey system configuration and promising field test practices. Further discussions will show the existing challenges as well as the potential applications.
报告人：Hai-Long Pei received his Ph.D degree from the South China University of Technology , China in 1992, and Master and Bachelor degrees from the Northwestern Polytechnical University, China in 1989 and 1986, respectively. Currently, he is a professor of School of Automation Science and Engineering in the South China University of Technology, Director of the Key Lab of Autonomous Systems and Networked Control, Ministry of Education, and Director of the Unmanned Engineering Center of Guangdong Province. He works on unmanned systems and robotic control, and now serves as editor-in-chief of the Journal of Control Theory and Technology, as associate editor of International Journal of Intelligent & Robotic Systems, and as
associate editor of Acta Automatica Sinica.
Title: Development of vehicular regnerative systems from suspension to powertrains
Panelist: Xubin Song（宋旭滨）
Abstract: Today the vehicles are going to be electrified and equipped with more features of autonomous drives. One perspective is that a vehicle becomes more intelligent from drive to diagnostics, and at the same time more energy-efficient. This presentation reviews what the author has worked over the career on two fundamental vehicle systems from dynamics and controls, suspension system and powertrains. Usually a controllable suspension can be developed to improve both comfort and handling. A low-bandwidth active suspension is introduced here to explain how this four corner suspension system uses a digital displacement pump motor (DDPM) to deliver regenerative functions beyond vibration isolation. Secondly, this presentation talks about hybrid powertrains, hydraulic and electric. Kind of model predictive controls are exemplified to boost the powertrain performance regarding fuel efficiency and safety. The highlight is that both suspension and powertrain utilize hydraulics and electric devices as system compositions to make the vehicle more energy-efficient with the aid of regenerative functions. This presentation also discusses the challenges of control developments because of high nonlinearity and wide frequency domain. The proof of adaptive control system with hysteresis is briefly reviewed. Regardless of vehicle advancement with futuristic technologies, the fundamental dynamics and control of vehicles shall still be there for further exploration.
报告人：Dr. Xubin Song is the founding Editor-in-Chief of International Journal of Powertrains since 2010. In the past two decades, his engineering focus is on advancing vehicle technologies of chassis systems and powertrains for product development. That includes semi-active and active suspension systems and traction controls for passenger cars (Visteon, 2000-2004), transmissions and hybrid powertrain systems for commercial vehicles (Eaton Corp, 2004-2015), and vehicle/powertrain electrification for buses and trucks (Weichai Power, 2015-). His latest industry duty includes the principal engineer of Eaton Corp, and an executive position of VP & CTO of Weichai New Energy Technology Company. Dr. Song served as associate editor (2009-2012) of ASME Journal of Dynamic Systems, Measurement and Control. He has more than 50 peer-reviewed publications with more than 10 USA, European and China patents (granted and pending). Dr. Song is the recipient of Best Paper Award at the ASME IDTEC 2010, and in October of 2013 elected as Fellow of American Society of Mechanical Engineers (ASME).
Panelist: Ning Bian（边宁）
Title: Development of electronic control system for gasolin Engine
Panelist: Pengyuan Sun（孙鹏远）
Abstract: The engine is a key element to reflect the performance of the vehicle, and it is closely related to the emission and fuel consumption laws and regulations, So it is the core competitiveness of the vehicle factory. For the engine, the electronic control system plays a crucial role. In order to meet the increasingly stringent legislations and regulations, and meet the ever-increasing driving experience of users, gasoline engines are facing the technical challenges of deep energy saving and emission reduction, which also brings many new problems to the development of electronic control system. Based on the technical status and background of gasoline engine control, the future research direction, difficulties and key technologies to be solved are discussed, and the future development of this field is prospected.
Title: Technology and Application of Battery Management System on Cloud
Panelist: Munan Hong（洪木南）
Abstract: Safety and cycle life of the battery are two of the major factors which restrict the development of new energy vehicles. As the big data, cloud computing and artificial intelligence technologies are widely implemented in the internet area, they also provide a new approach to handle the battery application issues. A battery management system on cloud which consists of edge computing terminal, digital twin battery model and data-driven strategy is presented and its applications are introduced. The results show that the proposed battery management system on cloud can detect some potential safety problems and evaluate the battery state of health.
Title: Application of predictive cruise control technology in energy saving of heavy trucks
Panelist: Yuhai Wang（王玉海）
Abstract: In China, CO, HC, NOx, and PM emissions from heavy-duty trucks account for 16.9%, 20.5%, 61.5%, and 63.3% of total vehicle emissions, respectively. The road freight industry is facing severe pressure on energy conservation and emission reduction. Predictive cruise is a vehicle automatic control technology that uses the road gradient information provided by the high-precision map to plan the vehicle speed in advance to realize economical driving. It has a fuel saving contribution rate of 3-8%. This technology can not only be applied to heavy-duty fuel vehicles, but also can be combined with hybrid technology to deeply improve vehicle fuel-saving rates and increase battery cycle charge and discharge life. This report introduces the application status of predictive cruise technology in fuel and hybrid heavy trucks from the aspects of realization principle and energy saving effect, and briefly introduces the combination of predictive control technology and vehicle safety system.
Panelist: Kuifeng Su（苏奎峰）
报告人：苏奎峰，腾讯自动驾驶业务总经理，清华大学计算机科学与技术专业博士。多年从事高精度稳定系统、无人作战平台和自主驾驶技术和应用研究工作，主要研究领域人工智能、多传感器融合、自动驾驶系统测试验证、城市级交通场景仿真、基于数字孪生的智慧城市/智慧交通等。主持研发的自动驾驶开发云、自动驾驶模拟仿真系统被国内外头部企业选用，助力加速了自动驾驶的产业化落地。现任中国自动化学会智能自动化专业委员会委员，中国全国专业标准化技术委员会智能网联汽车标准委员会委员。曾出版学术专著8 部，自动驾驶及国防领域专利5 个，发表专业论文40 余篇。
Semi-Plenary Lecture for Young Scholar
Title: Perception and control of hydrogen-electric intelligent mobile platforms
Panelist: Jian Chen
Abstract: With the intensification of environmental and energy crisis and the arrival of artificial intelligence era, sustainable energy and intelligence are inevitable trends in the future development of mobile platforms such as vehicles, which is also the major demand of national strategy and economic development. We have carried out in-depth research on hydrogen-electric intelligent mobile platforms, based on multi-view geometry technology and nonlinear theory, and achieved some academic achievements in environmental perception, target observation, motion control, hydrogen-electric hybrid system modeling and control, and multi-objective energy management. Our target is to provide some theoretical support and technical foundation to develop sustainable energy and intelligent mobile platforms.
报告人：陈剑，浙江大学教授，博导，浙江省特聘专家, IEEE Senior Member,中国自动化学会控制理论专委会委员、新能源控制学组主任，浙江省氢电混合动力系统创新团队负责人。主持国家自然科学基金重点项目和浙江省重点研发计划各一项。主要研究方向包括燃料电池系统控制、机器视觉、智能驾驶、氢电混合动力系统。出版机器人感知与控制英文学术专著一部，发表了130篇SCI/EI学术论文。
Title: Application of sparse optimization in trajectory planning for intelligent vehicles
Panelist: Li Li（李力）
Abstract: Sparse optimization refers to the mathematical or logical "sparse" representation of some characteristics of the problem to be solved and then the use of specific algorithms to find the solutions. We introduce sparse optimization into the research of trajectory planning for intelligent vehicles, considering reducing the frequency of driverless vehicle control actions, reducing the frequency of wireless communication required by multi vehicle cooperation, and quickly solving the collision avoidance trajectory in complex environment. We will present a series of new theoretical analysis methods and practical results are obtained.
报告人：He is currently an Associate Professor with the Department of Automation, Tsinghua University, Beijing, China, where he was involved in artificial intelligence, intelligent control and sensing, intelligent transportation systems, and intelligent vehicles research. He has authored over 100 SCI-indexed international journal papers. Dr. Li serves as an Associate Editor for the IEEE Transactions on Intelligent Transportations Systems. He is a member of the Editorial Advisory Board for Transportation Research Part C: Emerging Technologies, a member of the Editorial Board of Transport Reviews and ACTA Automatica Sinica. He is the Chair of Technical Committee on Cooperative and Connected Vehicles for IEEE Intelligent Transportation Systems Society.
Title: Distributional reinforcement learning and its application on self-learning automated vehicles
Panelist: Shengbo Li（李升波）
Abstract: Reinforcement learning (RL) has been successfully applied to a range of challenging sequential decision making and control tasks such as games and robotics. However, current RL algorithms typically suffer from the Q-value overestimation problem, which will greatly reduce policy performance and limit the applicability of RL to real-world domains. This talk will introduce the distributional soft actor-critic (DSAC) algorithm, which is recently developed for mitigating Q-value overestimations. The main theoretical basis of DSAC is that learning a distribution function of state-action returns can effectively mitigate Q-value overestimations because it is capable of adaptively adjusting the update step of the Q-value function, thereby improving policy performance. The application of DSAC in decision making and motion control of autonomous vehicles will be introduced.
报告人：Prof. Shengbo Li is now leading Intelligent Driving Lab (iDLab) at Tsinghua University. Before joining Tsinghua University, he has worked at Stanford University, University of Michigan, and UC Berkeley. His active research interests include intelligent vehicles and driver assistance, reinforcement learning and optimal control, distributed control and estimation, etc. He is the author of over 100 peer-reviewed journal/conference papers. Dr. Li was the recipient of best paper awards in IEEE ITSC, Asian ITS, CCCC, IEEE ICUS, ICCAS, etc. He also serves as Board of Governors of IEEE ITS Society, AEs of IEEE ITSM, IEEE Trans ITS, etc.
Title: Multi-objective Predictive Platooning Control for Conflict Resolution of Connected Vehicles
Panelist: Defeng He（何德峰）
Abstract: With the development of wireless communication and advanced control technologies, platooning systems of connected vehicles have developed from single objective control problem of (string) stability to multi-objective coordinated platooning control problem consisting of safety, car-following, economy and comfort. Taking model predictive control as the basic method, this talk first briefly illustrates the conflict of multiple control objectives of connected vehicles. Then we focuse on the latest achievements in the multi-objective platooning control of connected vehicles, namely, conflict-resolving multi-objective predictive platooning pontrol of ponnected vehicles. Finally, some representative scenarios are used to demonstrate the effectivenes of the proposed method.
Title: Measurement, Assessment and Modelling of Heavy Goods Vehicle Energy Consumption
Panelist: Xiaoxiang Na（那晓翔）
Abstract: Fuel consumption and carbon emissions of heavy goods vehicles (HGVs) can be reduced by engineering and logistics measures. Engineering measures include vehicle efficiency improvements and changes to energy sources and drivetrains. Both are needed to get anywhere near a zero GHG emissions target by 2050. Essential approaches in the decarbonisation task are assessment of vehicle performance and computer modelling of vehicle energy consumption. Extensive in-service measurements are needed to provide data for performance assessment and identify parameters for model validation. This presentation will describe recent work on measurement, assessment and modelling of HGV energy consumption, carried out by the Centre for Sustainable Road Freight in the UK.
报告人：那晓翔，现任英国剑桥大学工程系副研究员。2014年获剑桥大学工学博士学位，师从David Cole教授，课题方向为驾驶员与车辆先进转向系统的动态博弈。2014年3月加入剑桥大学道路运输可持续发展研究中心，与英国皇家工程院院士David Cebon教授合作，从事重型商用车智能车载信息系统的研发，以及车辆节能减排特性的评价等工作。现已发表国际期刊及会议论文40余篇，获发明专利授权3项。现担任自动化学报英文版（IEEE/CAA Journal of Automatic Sinica）编委、中国自动化学会平行智能专业委会副秘书长、国际平行驾驶联盟副秘书长等职务。
Title: The holistic motion planning and control for autonomous driving
Panelist: Yanjun Huang（黄岩军）
Abstract: Trajectory planning and control is extremely important to the development of the autonomous vehicle. This presentation first discusses the framework of the autonomous driving algorithm, its future direction, and the related research of the presenter; then, it proposes a holistic algorithm for motion planning and control, including an MPC, prediction of traffic participants, resistance network, artificial potential function, etc. Finally, the experimental platform is shown and some preliminary results are provided as well.
报告人：黄岩军，同济大学研究员/博导，上海市高层次人才特聘专家，博士毕业于滑铁卢大学机电工程系，曾任滑铁卢大学副研究员。研究领域为车辆安全、智能、节能等集成控制。出版新能源和智能车学术著作5部；发表学术论文80余篇，以第一作者/通讯作者身份在顶级/一区期刊上发表SCI 论文40余篇。获得IEEE/TVT和Automotive Innovation期刊年度最佳论文、汽车工程杂志最受欢迎论文等。担任SCI期刊IET Intelligent Transport System、Int. Journal of Vehicle Design、SAE Int. Journal of Commercial Vehicle、Int. Journal of Autonomous Vehicle Systems、中国汽车工程学会英文会刊Automotive Innovation等若干汽车领域期刊编委。长期担任70个高水平期刊审稿人且获得多个顶级期刊杰出审稿人奖。多次担任智能汽车领域国际高水平会议分会主席，并多次在知名国际学术会议、大学和研究机构做特邀报告。
Online Distinguished Scholar Forum
Title: Safe Motion Planning and Control of Aggressive Vehicle Maneuvers
Panelist: Jingang Yi
Abstract: Aggressive vehicle maneuvers are commonly used by professional racing car drivers to achieve fast and agile performance. Understanding these skilled maneuvers can help to design autonomous driving capability and active safety features under extremely events, such as emergency maneuvers. In this talk, I will present some recent developments in stability analysis, motion planning and control of aggressive vehicle maneuvers. I will first define the motion stability and agility metrics for vehicle maneuvers and then present a case study on how the racing car drivers achieve unstable yet agile driving skills. I will then present the motion planner that takes advantages of the sparse stable trees (SST), the RRT* algorithm and the model predictive control (MPC) and machine learning design. Rather than restricting the vehicle motion within the stability region of its open-loop dynamics, the motion controller design allows the vehicle to operate outside the stability bounds to accomplish a safe and agile maneuver. I will demonstrate the motion planning and control design for autonomous aggressive maneuvers on a 1/7-scale RC vehicle platform.
报告人：Professor Jingang Yi received the B.S. degree in electrical engineering from Zhejiang University in 1993, the M.Eng. degree in precision instruments from Tsinghua University in 1996, and the M.A. degree in mathematics and the Ph.D. degree in mechanical engineering from the University of California, Berkeley, in 2001 and 2002, respectively. He is currently a Full Professor in mechanical engineering and a Graduate Faculty member in electrical and computer engineering at Rutgers University. His research interests include autonomous robotic and vehicle systems, dynamic systems and control, mechatronics, automation science and engineering, with applications to iomedical, transportation and civil infrastructure systems.
Panelist: Mou Chen（陈谋）
报告人：陈谋，博士，南京航空航天大学自动化学院副院长，省特聘教授，博士生导师。国家自然科学基金杰出青年基金获得者、国家“百千万”人才工程和教育部“新世纪优秀人才支持计划”入选者。先后在南京航空航天大学获学士与博士学位，2007年11月-2008年2月在英国拉夫堡大学访问研究。2008年6月-2009年9月新加坡国立大学博士后研究员(Research fellow A)。2014年5月-2014年11月澳大利亚阿德莱德大学高级研究学者。目前担任SCI收录英文期刊《IEEE Transactions on Systems, Man, and Cybernetics: Systems》、《IEEE Access》、《Neurocomputing》等编委、SCI收录英文期刊《Chinese Journal of Aeronautics》和《SCIENCE CHINA Information Sciences》青年编委等。同时也担任教育部高等学校教学指导委员会兵器类委员、中国航空学会导航制导与控制分会委员、中国自动化学会系统仿真专业委员会委员、中国航空学会武器系统专业委员会委员、江苏省自动化学会理事等。先后获国家自然科学二等奖1项(排名第二)、教育部自然科学奖一等奖1项(排名第二)、获国防科技进步二等奖2项(排名第一)，申请授权发明专利10余项。出版中英文专著各1部，参编著作3部，发表学术论文100余篇。