Connected and Automated Vehicles

FMCW MMW Radar for Automotive Longitudinal Control

David, William
1997

This report presents information on millimeter wave (MMW) radar for automotive longitudinal control. It addresses the fundamental capabilities and limitations of millimeter waves for ranging and contrasts their operation with that of conventional microwave radar. The report analyzes pulsed and FMCW radar configurations, and provides detailed treatment of FMCW radar operating at MMW frequency, its advantages and disadvantages as they relate to range and velocity measurements.

Feasibility Study of Fully Autonomous Vehicles Using Decision-Theoretic Control

Forbes, Jeffrey
Et. al.
1997

This project studied the feasibility of constructing an autonomous vehicle controller based on probabilistic inference and utility maximization. Several theoretical and algorithmic advances were required in order to create an inference system capable of handling vehicle monitoring in a real-time fashion. New methods were also developed for learning probabilistic models from data, and for learning control policies given reward/penalty feedback.

Fault Tree Analysis of an Automated Freeway with Vehicle-borne Intelligence

Hitchcock, Anthony
2004

This report summarizes research work conducted under TO4143 at the California PATH ATMS Center at the University of California, Irvine. This project has two tasks: Functionality enhancements of the PARAMICS simulation model through API programming for the on-line simulation application; On-line data fusion algorithm for a better section travel time estimation based on point detector data and probe vehicle data. In order to conduct these two tasks, we complete the following two related studies, which are the basis of the two tasks of this project: Development of the capability-enhanced...

Fault Detection and Identification with Application to Advanced Vehicle Control Systems: Final Report

Douglas, R. K.
Speyer, J. L.
Mingori, D. L.
Chen, R. H.
Malladi, D. P.
Chung, W. H.
1996

This study reports on a preliminary design of a health monitoring system for automated vehicles. A new detailed nonlinear vehicle simulation which extends the current simulation is documented and will be used as a future testbed for evaluating the performance of the health monitoring system. A health monitoring system has been constructed for the lateral and longitudinal modes that monitors twelve sensors and three actuators. The approach is to fuse data from dissimilar instruments using modeled dynamic relationships and fault detection and identification filters.

Fault Detection and Tolerant Control for Lateral Guidance of Vehicles in Automated Highways

Patwardhan, Satyajit Neelkanth
1994

In this dissertation, the problem of fault tolerant control of automobiles is addressed. The three main problems handled in the dissertation are tire burst, sensor fault detection and slip angle control. The tire burst and sensor faults are important failure modes for automated highways, whereas the slip angle control problem is important during severe maneuvers for enhancing the vehicle safety.

Experimental Results of Fuzzy Logic Control for Lateral Vehicle Guidance

Hessburg, Thomas
Peng, Hei
Zhang, Wei-bin
Arai, Alan
Tomizuka, Masayoshi
1994

A Fuzzy logic controller (FLC) is designed and implemented in real time on a Toyota Celica test vehicle to achieve control of the lateral motion of the vehicle. The structure of the FLC is modularized as a feedback, preview, and gain scheduling rule base. The parameters of the FLC are tuned manually using information from characteristics of human driving operation and an existing controller. The fuzzy logic control strategies are implemented on the test vehicle, automatically following a multiple curved track using discrete magnetic markers as a lateral error reference system. The test...

Experimental Automatic Lateral Control System for an Automobile

Peng, Huei
Zhang, Wei-bin
Arai, Alan
Lin, Ye
Hessburg, Thomas
Devlin, Peter
Tomizuka, Masayoshi
Shladover, Steven
1992

This report summarizes an experimental effort in integrating and testing an automated vehicle lateral control system. The project, a cooperative effort between the California Partners for Advanced Transit and Highway ( PATH) Program and IMRA America, Inc., included a discrete roadway reference system, on-vehicle magnetic sensing system, a computer control system and a hydraulic actuator.

Evaluation of Mixed Automated/Manual Traffic

Ioannou, Petros
1998

The advance in research and development will make the deployment of automated vehicles a reality in the near future. The principal question is whether these technologies will lead to any benefits in terms of safety, capacity and traffic flow characteristics as they penetrate the current transportation system. Another aspect is how to exploit these technologies in order to achieve benefits without adversely affecting the efficiency of the current transportation system and the drivers who cannot afford them. The penetration of automated vehicles into the existing transportation system will...

Evaluation and Analysis of Automated Highway System Concepts and Architectures

Ioannou, Petros
1998

This is the final report for the project entitled \Evaluation and Analysis of Automated Highway System Concepts and Architectures" in response to the contractual requirements of the Memorandum of Understanding MOU# 235, between the Partners of Advanced Transit and Highways (PATH) and the University of Southern California, administered at the University of Califor- nia at Berkeley. The purpose of this project was to select, evaluate and analyze a num- ber of promising Automated Highway System (AHS) operational concepts based on previous work. The evaluation and analysis includes headway dis...

Ecological Velocity Planning Through Signalized Intersections: A Deep Reinforcement Learning Approach

Pozzi, Andrea
Bae, Sangjae
Choi, Yongkeun
Borrelli, Francesco
Raimondo, Davide M.
Moura, Scott
2020

The use of infrastructure-to-vehicle communication technologies can enable improved energy efficient autonomous driving. Traditional ecological velocity planning methods have high computational burden, particularly when plug-in hybrid electric vehicles are considered. Consequently, in order to retrieve an optimal velocity profile in real time, it is necessary to rely on significant approximations.In this paper, the aforementioned issue is addressed by exploiting deep reinforcement learning in order to "learn" an eco-driving velocity planner for a plug-in hybrid electric vehicle within a...