Machine Learning and Model-based Control for Autonomous Driving
An autonomous car senses its environment, plans the motion for safe and efficient driving and move to follow the plan with minimal or no human intervention. Currently, cars on the road have not yet reached to the stage of complete autonomous driving, but intensive research and development efforts are taking place in automotive industry, information technology industry, national research laboratories and university laboratories.Society of Automotive Engineers (SAE) defines the level of driving automation from Level 0 to Level 5.At Level 5, no human intervention is required, and at Level 4, no driver attention is required for safety.Forefront research efforts focus on the level 4 and level 5 automation.Functions of autonomous cars at Level 4 include: 1) Detection, Tracking, Localization & Mapping, 2) Motion Prediction & Behavioral Planning and 3) Motion Planning & Control. The leading enabling technology for autonomous driving is machine learning and AI.Traditional model-based control also plays a significant role, and merging machine learning and model based-control is an exciting research topic. We will examine fundamental issues in autonomous driving and the use of the enabling technologies to address the issues.
自动驾驶汽车能感知周围环境，为安全高效的驾驶制定行动计划，并在最少或不需要人为干预的情况下按照计划行动。目前，汽车还没有达到完全自动驾驶的阶段，但大量的研究和努力已经投入汽车工业、信息技术产业、国家研究实验室和大学实验室。美国汽车工程师学会（SAE）定义了从0级到5级的驾驶水平。到了第五级不再需要人为干预，在第四级驾驶员无需注意安全。前沿的研究工作集中在第四级和第五级。第四级的自动驾驶功能包括：1） 探测、跟踪、定位和测绘，2） 运动预测与行为规划，3） 运动规划与控制。自动驾驶的领先技术是机器学习和人工智能，传统基于模型的控制也发挥了重要作用，将机器学习和基于模型的控制相结合是一个令人兴奋的研究课题。我们将研究自动驾驶的基本问题，以及如何使用使能技术来解决这些问题。
Masayoshi Tomizuka received his Ph. D. degree in Mechanical Engineering from the Massachusetts Institute of Technology in February 1974. In 1974, he joined the faculty of the Department of Mechanical Engineering at the University of California at Berkeley, where he currently holds the Cheryl and John Neerhout, Jr., Distinguished Professorship Chair. His current research interests are intelligent control, optimal and adaptive control, digital control, signal processing, motion control, and control problems related to robotics, precision motion control and vehicles. He served as Program Director of the Dynamic Systems and Control Program of the Civil and Mechanical Systems Division of NSF (2002- 2004). He served as Technical Editor of the ASME Journal of Dynamic Systems, Measurement and Control, J-DSMC (1988-93), and Editor-in-Chief of the IEEE/ASME Transactions on Mechatronics (1997-99). Prof. Tomizuka is a Life Fellow of the ASME and IEEE and a Fellow of IFAC (International Federation of Automatic Control). He is the recipient of the Charles Russ Richards Memorial Award (ASME, 1997), the Rufus Oldenburger Medal (ASME, 2002), the John R. Ragazzini Award (American Automatic Control Council (AACC), 2006) and the Richard E. Bellman Control Heritage Award (AACC, 2018).