Search Results

In order to travel in a chaotic and dynamic environment, an autonomous vehicle requires a motion plan. This motion plan ensures collision free, optimum travel without violating any traffic rules. The optimum solution for path planning problem exists in higher dimensions, however, with the help of useful heuristics the problem can be solved in real time, which is required for real time operation of an autonomous vehicle. There are different well established techniques available to plan a collision free kinematically traversable path. One of such techniques is called conformal Lattice planner. However, the legacy version of conformal lattice planner is not optimized and also is prone to fail under specific dynamic environment conditions. Moreover, the legacy version of conformal lattice planner is also not road aware. Due to this reason it is a semi optimized way to solve the motion planning problem.

Now-a-days, Advanced driver-assistance systems (ADAS) is equipping cars and drivers with advance information and technology to make them become aware of the environment and handle potential situations in better way semi-autonomously. High-quality training and test data is essential in the development and validation of ADAS systems which lay the foundation for autonomous driving technology. ADAS uses the technology like radar, vision and combinations of various sensors including LIDAR to automatize dynamic driving tasks like steering, braking, and acceleration of vehicle for controlled and safe driving. And to integrate these advance technologies, the ADAS needs labeled data to train the algorithm to detect the various objects and moments of driver. Image annotation is one the well-known service to create such training data for computer vision. There are number of open source annotated datasets available viz. COCO, KITTI etc.