Object Detection for Automated Vehicle:
Automobiles rely on their drivers less than ever before and fully driverless cars represent a potentially impactful change in urban transportation. Changes in automobile technology have enabled vehicles to perform safety-critical functions in more circumstances, ranging from cruise control and lane-keeping.
These changes may lead to fully-autonomous vehicles (AVs) which require no human control over safety critical functions. An automated vehicle requires an accurate perception of its surrounding environment to operate reliably. The perception system of such vehicles transforms sensory data into semantic information that enables autonomous driving.
Object detection is a fundamental function of this perception system. This project aims to build and optimize algorithms based on a large-scale dataset and focus on hard problems in this perception system i.e. 3D object detection over semantic maps. 3D object detection is a crucial task for autonomous driving. Many important fields in autonomous driving such as prediction, planning, and motion control generally require a faithful representation of the 3D space around the vehicle.