Development of Monocular Vision based Autonomous Car

Abstract

Abstract: The evolution of the artificial intelligence has served as the catalyst in the field of technology. We can now develop things which was once just an imagination. One of such creation is the birthof Autonomous cars. Days have come one can do their work even touching steering wheel, accelerator you will still be able to reach your target destination safely. Self-driving car (Autonomous cars) is a robotic vehicle that is designed to travel between destinations without human intervention. It is capable of sensing environment and navigate without human input. Autonomous cars must have control systems that are capable of analysing sensor data to distinguish between different cars on the road. The potential benefits of autonomous cars include reduced mobility and infrastructure costs, increased safety, increased mobility, increased customer satisfaction and reduced crime. Self-driving cars rely on software which needs to be thoroughly tested. Testing self-drivingcar software in real traffic is not only expensive but also dangerous and has already caused fatalities. Virtual tests, in which self-driving car software is tested in computer simulations, offer a more efficient and safer alternative compared to naturalistic field operational tests. However, creating suitable test scenarios is laborious and difficult. In this paper we combine procedural content generation, a technique commonly employed in modern video games, and search-based testing, a testing technique proven to be effective in many domains, in order to automatically create challenging virtual scenarios for testing self-driving car soft- ware. Our as Fault prototype implements this approach to generate virtual roads for testing lane keeping, one of the defining features of autonomous driving. Evaluation on two different self-driving car software systems demonstrates that as Fault can generate effective virtual road networks that succeed in revealing software failures, which manifest as cars departing their lane. Compared to random testing as Faultwas not only more efficient, but also caused up to twice as many lane departures