Abstract: A prediction system implemented in a host vehicle to predict a merge cut-in for an autonomous vehicle. The system comprises an input unit for capturing neighboring information of the host vehicle, and a processing unit to receive the captured neighboring information and generate a grid map by determining shape and dimensions of a grid, estimate trajectory of each target vehicle of the one or more target vehicles, based on a driver behavior model of each target vehicle, to determine optimized path of each target vehicle, and generate a global maneuver model by analyzing motion of each neighboring target vehicle, wherein on generation of the global maneuver model a merge cut-in threat for the host vehicle is computed by performing centralized risk management and utilizing the predicted trajectory of the one or more target vehicles.

Abstract: The pedestrian tracking system implemented in a host vehicle is disclosed. The system estimates trajectories of the host vehicle and the pedestrian based on factors of position and velocity of the host vehicle and parameters of position and velocity of the pedestrian. The trajectories of the host vehicle and the pedestrian are estimated to estimate a point of intersection of the host vehicle and the pedestrian. Further, the system estimates time to collision based on the estimated point of intersection and determines trajectory of the pedestrian in path of the host vehicle. Furthermore, the system assesses collision risk to select the pedestrian as a target and generates a deceleration actuation command to decelerate the host vehicle based on the selected target, which is provided to an automatic emergency braking (AEB) actuation unit.

Abstract: A system implemented in a vehicle for tracking and mapping of one or more objects to identify free space is disclosed. The system has an input unit having lidar sensors and radar sensors that sense objects in a region surrounding the vehicle, and a processing unit that: receives data from lidar sensors and radar sensors and maps the data in corresponding grid maps of corresponding sensors; tracks objects in regions corresponding to the sensors and performs estimation for objects not sensed by any of the sensors; fuses the grid maps by converting them from sensor frame to vehicle frame to generate a fused grid map; and integrates the fused grid map with any or a combination of track management and scan matching to perform classification of the one or more objects into static objects or dynamic objects and identification of free space in the fused grid map.

Abstract: A prediction system implemented in a host vehicle to predict a merge cut-in for an autonomous vehicle. The system comprises an input unit for capturing neighboring information of the host vehicle, and a processing unit to receive the captured neighboring information and generate a grid map by determining shape and dimensions of a grid, estimate trajectory of each target vehicle of the one or more target vehicles, based on a driver behavior model of each target vehicle, to determine optimized path of each target vehicle, and generate a global maneuver model by analyzing motion of each neighboring target vehicle, wherein on generation of the global maneuver model a merge cut-in threat for the host vehicle is computed by performing centralized risk management and utilizing the predicted trajectory of the one or more target vehicles.