Sadayuki Tsugawa

Vision-based vehicles in Japan: machine vision systems and driving control systems

This paper surveys three intelligent vehicles developed in Japan, and in particular the configurations, the machine vision systems, and the driving control systems. The first one is the Intelligent Vehicle, developed since the mid 1970s, which has a machine vision system for obstacle detection and a dead reckoning system for autonomous navigation on a compact car. The machine vision system with stereo TV cameras is featured by real time processing using hard-wired logic. The dead reckoning function and a new lateral control algorithm enable the vehicle to drive from a starting point to a goal. It drove autonomously at about 10 km/h while avoiding an obstacle. The second one is the Personal Vehicle System (PVS), developed in the late 1980s, which is a comprehensive test system for a vision-based vehicle. The machine vision system captures lane markings at both road edges along which the vehicle is guided. The PVS has another machine vision system for obstacle detection with stereo cameras. The PVS drove at 10-30 km/h along lanes with turnings and crossings. The third one is the Automated Highway Vehicle System (AHVS) with a single TV camera for lane-keeping by PD control. The machine vision system uses an edge extraction algorithm to detect lane markings. The AHVS drove at 50 km/h along a lane with a large curvature. >

An architecture for cooperative driving of automated vehicles

This paper presents an architecture for cooperative driving of automated vehicles, which means flexible platooning including smooth merging and lane changing, in conjunction with experiments on a test track using some technologies for sensing, control, and inter-vehicle communications. The architecture consists of three layers: the vehicle control layer, the vehicle management layer, both of which are on each vehicle, and the traffic management layer on the infrastructure. The experiments illustrating the parts of the architecture include visual platooning by two automated vehicles, and fusion of the data through the inter-vehicle communications and the data of the inter-vehicle gap measurement.

A SURVEY OF PRESENT IVHS ACTIVITIES IN JAPAN

Abstract The Japanese Government has been conducting IVHS (Intelligent Vehicle-Highway Systems) projects on ATMS (Advanced Traffic Management Systems), ATIS (Advanced Traveller Information Systems) and AVCS (Advanced Vehicle Control Systems). In the spring of 1996, VICS (Vehicle Information and Communication System) started a driver information service including dynamic route guidance, and ASV (Advanced Safety Vehicle) aiming at active safety for passenger cars had demonstrations. Experiments related to Automated Highway Systems have been conducted since 1995 on a test track and an expressway. Cooperative driving, with inter-vehicle communication, was tested in the spring of 1997. Besides the Government projects, navigation systems have become widespread, and inter-vehicle distance warning systems for trucks and an intelligent cruise control system for passenger cars have become commercially available.

A Survey of Present IVHS Activities in Japan

Abstract The Japanese Government is conducting IVHS projects on ATMS, ATIS and AVCS. VICS will start information service including route guidance in spring of 1996. ASV aiming at active safety for passenger cars will have demonstrations in spring of 1996. Experiments on LCX-based information service and automated highway systems in ARTS have been conducted since 1995. Platoon driving with inter-vehicle communication in SSVS will be tested in 1996. Besides the Government projects, navigation systems are widely spread, and inter-vehicle distance warning systems for trucks and an intelligent cruise control system for passenger cars are commercially available nowadays in Japan.

An overview on control algorithms for automated highway systems

This paper surveys lateral and longitudinal vehicle control algorithms in automated highway systems. In the lateral control, an onboard sensing system detects or captures a reference on a roadway indicating the path of an automated vehicle, and PID control and state variable feedback control based on the modern control theory with deviation from a planned path are mainly used to drive the vehicle along the path. In the longitudinal control, an inter-vehicle gap and relative speed to a preceding vehicle are measured, and feedback control with state variables including deviations in the gap, relative speed, and relative acceleration, some of which are obtained by the transmission over inter-vehicle communication rather than measurement, is used to maintain a predetermined gap in a platoon. Lateral and longitudinal vehicle control algorithms are explained with references to some systems developed since 1960s.

Recent Japanese projects of AVCS-related systems

This paper introduces recent developments of Japanese AVCS-related systems following the general introduction of the Japanese Intelligent Vehicle Highway System/ATT. The Vehicle Information Communication System and Universal Traffic Management System, categorized as ATMS/ATIS, are now at the stage of practical implementation. The Advanced Road Transportation System, featured by infrastructure-oriented AVCS with use of leakage coaxial cables, and an advanced safety vehicle aiming at active safety, and their experiments have been conducted. Some experiments on intervehicle communication, which is one of the technologies in Super Smart Vehicle System for the future AVCS, are also described.

Lane-change manoeuvres for vision-based vehicle

This paper describes algorithms of path generation and lateral control of an automated vehicle with a vision system for autonomous navigation and lane-change manoeuvres. The vision system detects reference lines along which the vehicle is guided. The lateral control consists of steps of reference line detection, path generation, and lateral control calculation. A coefficient of a cubic curve that approximates a series of sampled points on the reference line provides the lateral control. The approximation can be done with a series of sampled points that are detected on the reference line in the field of view with image processing. A path for various manoeuvres including lane-changing is generated by shifting the series of sampled points. Simulation studies and outdoor experiments were conducted to show the feasibility of the algorithms.

Steering Control Algorithms for Intelligent Vehicles with Machine Vision

This paper presents two steering control algorithms for intelligent vehicles with a machine vision system to detect lane lines or a reference line along a path for lateral control. In one algorithm steering control is given as a weighted sum of deviations at multiple points along the path, the locations of which are defined based on a human driver behavior model. The other algorithm gives steering control by straightforward calculation based on the whole reference line captured in the field of view. Experiments with the vehicles are shown.

ROUTE GUIDANCE SYSTEM FOR AUTOMOBILE DRIVERS BY SPEECH SYNTHESIS

Abstract This paper describes a route guidance system for automobile drivers by speech synthesis and road-vehicle digital communication. The system, included in a computer-aided driving instruction system installed on a training ground, aims to guide a driving trainee along a route fixed by an instructor. The system consists of a personal computer in the control center, on-board computers in each automobile, and inductive loop antennas. At an inductive loop antenna buried in the road and connected to the control center, transmitting the ID number, each automobile receives data code, with which speech data stored in the ROM of the on-board computer are retrieved and edited to a route guidance message. It is outputted in a synthesized female voice by ADPCM. The carrier frequency for the road-vehicle communication from a road is 223.2 kHz and that from a vehicle is 304.8 kHz. Data, modulated by minimum frequency shift keying, are transmitted at 9600 bps. The data frame is based on the HDLC. Experiments by trainees show that the route guidance system by speech synthesis is effective on the training ground.