An autonomous car is a self-driving vehicle, that operates without human intervention
and has the capability of sensing the environment around it. To achieve this, the autonomous
vehicle mostly depends on multiple Sensors, Actuators, Machine learning, complex algorithms and processors for software execution. Developed Software, at that point, processes
all the information obtained from sensors, plans the path, and the instructions are passed
to the vehicle’s actuators, which are capable of controlling acceleration, steering, and brake
systems. The rules that are hard-coded, algorithms for detection of object and obstacle
avoidance, and predictive modelling control algorithms assist the software with observing
traffic guidelines and navigate the vehicle accordingly. Free driving is anything but a simple
assignment, and to make independent driving game plans is an extraordinarily critical capacity in the current programming planning field. Engineers and Researchers have been keeping
huge endeavors to develop safe and precise algorithms to be incorporated in autonomous
vehicles.
ROS is a flexible and perfect middle ware tool for robotic applications. ROS offers the
necessary tools to effortlessly get the sensors information, process that information, and
produce a suitable response to actuators of the vehicle. This thesis work plans to exhibit
how ROS could be utilized as a middle- ware tool to make the vehicle move autonomously
by examining the surroundings and taking decision.
The main focus of this thesis is to develop a one-tenth scale of an autonomous Race
car equipped with Jetson Nano as the on-board computer, ROS based software architecture,
sensors, and a PWM driver and implement ADAS features such as Emergency Brake system,
Lane Detection and Lane change on the autonomous Race car vehicle. At last, by following
the strategies introduced in this thesis work, it is possible to build and develop an autonomous
vehicle that uses ROS framework.