The VILMA intelligent vehicle

The VILMA intelligent vehicle:an architectural design

for cooperative control between driver and automated system Olmer Garcia1?Giovani Bernardes Vitor2?Janito Vaqueiro Ferreira3?

Pablo Siqueira Meirelles3?Arthur de Miranda Neto4

Received:26September2017/Revised:5April2018/Accepted:9April2018/Published online:26April2018

óThe Author(s)2018

Abstract Intelligent autonomous vehicles have received a great degree of attention in recent years.Although the technology required for these vehicles is relatively advanced,the challenge is?rstly to ensure that drivers can understand the capabilities and limitations of such systems and secondly to design a system that can handle the interaction between the driver and the automated intelligent system.In this study,we describe an approach using dif-ferent strategies for an autonomous system and a driver to drive a vehicle cooperatively.The proposed strategies are referred to as cooperative planning and control and deter-mine when and how the path projected by the autonomous system can be changed safely by the driver to a path that he wishes to follow.The?rst phase of the project is described, covering the design and implementation of an autonomous test vehicle.Experiments are carried out with a driver to test the cooperative planning and control concepts pro-posed here.

Keywords Autonomous vehiclesáEmbedded systemsáCooperative systemsáVisual servoing 1Introduction

According to the data published by the United Nations, more than1.2million people die on roads around the world every year,and as many as50million are injured.Over 90%of these deaths occur in low-and middle-income countries.Brazil is among the states in which the number of such deaths is relatively high.Figure1shows historical data for traf?c accident deaths in Brazil,the USA,Iran, France,and Germany.There is a signi?cant difference in the?gures between developing countries and high-income countries.However,per capita statistics are controversial as the number of people who drive varies between coun-tries,as does the number of kilometers traveled by drivers.

The trend toward the use of automated,semiau-tonomous,and autonomous systems to assist drivers has received an impetus from signi?cant technological advan-ces and recent studies of accident rates[2].In parallel,the challenges posed by autonomous and semiautonomous navigation have motivated researchers from different groups to research this area.One of the most important issues when designing an autonomous vehicle[3]or a driver assistance system is vehicle safety and security.

Here,we investigate cooperative control in automated cars,where the driver is sometimes in the control loop,and the vehicle is operating at level3automation[4].The most common strategy for transferring control to the driver, particularly in risk situations,is to use an emergency but-ton.However,in practice,this may have serious draw-backs.For example,Google patent[5],which describes a system in which all the security variables are checked before control,is transferred.

Cooperative control also addresses the problem of driver inattention,as Ref.[6]present.Jain et al.[7]use an autoregressive input–output hidden Markov model to

&Olmer Garcia

olmer.garciab@https://www.wendangku.net/doc/7b2706663.html,.co

1Universidad de Bogota Jorge Tadeo Lozano,Bogota, Colombia

2Robotics,Intelligent and Complex Systems(RobSIC)Lab, Universidade Federal de Itajuba′(UNIFEI),Itabira,MG,

Brazil

3Autonomous Mobility Lab.at the Universidade Estadual de Campinas,(UNICAMP),Campinas,SP13083-860,Brazil 4Terrestrial Mobility Lab at the Universidade Federal de Lavras,(UFLA),Lavras,MG37200-000,Brazil

123