This paper looks into recent developments and research trends in collision avoidance/warning systems and automation of vehicle longitudinal/lateral control tasks. It is an attempt to provide a bigger picture of the very diverse, detailed and highly multidisciplinary research in this area. Based on diversely selected research, this paper explains the initiatives for automation in different levels of transportation system with a specific emphasis on the vehicle-level automation. Human factor studies and legal issues are analyzed as well as control algorithms. Drivers' comfort and well being, increased safety, and increased highway capacity are among the most important initiatives counted for automation. However, sometimes these are contradictory requirements. Relying on an analytical survey of the published research, we will try to provide a more clear understanding of the impact of automation/warning systems on each of the above-mentioned factors. The discussion of sensory issues requires a dedicated paper due to its broad range and is not addressed in this paper.

Research advances in intelligent collision avoidance and adaptive cruise control

An objective of developing intelligent transport systems (ITS) is to enhance driving convenience. As an ITS technology that meets this objective, an adaptive cruise control (ACC) system has already been commercialized. Another objective is to enhance the vehicle safety performance. With the aim of attaining this objective, we have developed a Pre-crash Safety system by evolving the ITS technology used in ACC. The Pre-crash Safety system is designed to predict an unavoidable collision and activate Pre-crash Seatbelt and Pre-crash Brake Assist well in advance of the collision to mitigate occupant injury caused by the collision. A millimeter-wave radar sensor is indispensable to the Pre-crash Safety system. This present paper describes the electronically scanned millimeter-wave radar sensor developed for use in the system. This radar is physically compact while providing high object recognition performance. This is due to the phased array technology employed for the first time in the world for automotive radar. Other features of the radar include a "high-efficiency planar antenna, "high-power and low-loss monolithic microwave ICs (MMICs) and millimeter-wave circuit" and a "high-speed digital-beam-forming (DBF) algorithm".

Electronically scanned millimeter-wave radar for pre-crash safety and adaptive cruise control system

This paper presents a method of predicting future human driving behavior under the condition that its resultant behavior and past observations are given. The proposed method makes use of a dynamic Bayesian network and the junction tree algorithm for probabilistic inference. The method is applied to behavior prediction for a vehicle assumed to stop at an intersection. Such a predictive system would facilitate warning and assistance to prevent dangerous activities, such as red-light violations, by allowing detection of a deviation from normal behavior.

Prediction of Human Driving Behavior Using Dynamic Bayesian Networks

Social demands for promoting safety-driving are enhancing, particularly in Japan as the number of traffic accidents have increased in recent years. To correspond with these demands, many vehicle manufacturers or suppliers have been researching or developing technologies of safety-driving, in co-operation with the government or authorities. Specially, research and development for providing vehicles with more "intelligence" through application of electronic engineering technologies are attracting much attention. Obstacle detection technology plays an important part as elementary technology for the development of these "intelligent vehicles". This paper introduces an automotive millimeter-wave radar to which a high expectation is attached as one of the obstacle detection technologies, and the application systems thereof. The paper also discusses subjects to be encountered in the course of development toward actual application.

Automotive application systems of a millimeter-wave radar

The objective of developing "ITS" is to realize driver convenience systems represented by ACC (adaptive cruise control), and to create active safety systems that realize an excellent vehicle safety performance. From February of last year we have, for the first time in the world, succeeded in creating a commercially available mass production pre-crash safety system (PCS) for excellent vehicle safety through developing and further evolving ITS technology applied to ACC. As the first crucial step in realizing an obstacle detection sensor was our development of "millimeter-wave radar." The second step was the successful development of a sensor fusion system integrating the millimeter-wave radar and a newly developed image sensor into the PCS system. By combining the vision-based obstacle detection system with the radar-based obstacle detection system, we have realized excellent obstacle detection performance.

Sensor fusion system for pre-crash safety system

This paper provides an overview of the status quo of vehicle collision avoidance technologies, and discusses the technological and social issues for the practical applications of such technologies. Efforts are discussed to develop technologies to support the driver's recognition, judgment, and operation in a more positive manner.

Mitsuo Kawai

Papers

Collision avoidance technologies