Home Reports Automotive Engineering Content

Researchers develop intelligent, driverless car

next article

21.03.2007

If you thought intelligent cars capable of negotiating a city centre with no driver behind the wheel were just the dream of Hollywood film writers you could be wrong. Researchers at the University of Essex think their work developing an autonomous model car could pave the way for intelligent driverless cars.

The project, led by Dr Simon Lucas of the Department of Computer Science, will see researchers build an autonomous model car which will be tested on a race track at the Colchester campus during the summer. It will provide a prototype for researchers around the world to develop their own smart model cars.

Dr Lucas explained: ‘This project will push computational intelligence methods to their limits, and beyond. As far as we are aware, this is the first time a completely autonomous model car has been developed. Similar principles have been applied to full-size cars in the past - for instance in the DARPA challenge to navigate across the Mohave Desert - but the cost implications of developing the technology using real cars mean it just isn’t viable for most researchers. By using model cars, we will be able investigate the possibilities of the technology far easier and more cheaply.’

The intelligent model car will be built using a standard remote control model vehicle. A PC will be mounted on the chassis and a video camera, streaming real-time computer vision, along with other sensors will be added. The software written for the PC will allow the car to be fully autonomous; it will be able to recognise obstacles and make tactical decisions as it drives itself around the racetrack.

The Essex prototype will allow researchers across the globe to build their own autonomous cars which will race against one another at the IEEE (Institute of Electrical and Electronics Engineers) World Congress on Computational Intelligence to be held in Hong Kong in 2008.

Dr Lucas said: ‘The race in 2008 will be about whose car is the fastest but also the smartest. The challenge is to use computer vision methods together with a range of other sensor data to race the car as fast as possible around the track while outwitting the opponent cars but to do so it needs to be smart, it needs adapt to the behaviour of the other cars as it drives.’

He added: ‘We envisage that the technology needed to develop our prototype could pave the way for a future where driverless cars are a reality. It is entirely possible that in the next 15 years we could see driverless cars being used in cities around the world, probably for specific transportation needs such as taxis or delivery vehicles. The potential real-world applications of the computer vision technology that we will develop are endless.’

The development of the Essex prototype model car is being funded by the IEEE Computational Intelligence Society.

Kate Clayton | Source: alphagalileo
Further information: www.essex.ac.uk/news

next article