US 11,814,085 B2
System for grid-based merge cut-in prediction and method thereof
Soumyo Das, Pune (IN); Ashutosh Sharma, Pune (IN); Rastri Dey, Pune (IN); and Srinath Shankarappa Budhavaram, Pune (IN)
Assigned to KPIT TECHNOLOGIES LIMITED, Pune (IN)
Filed by KPIT TECHNOLOGIES LIMITED, Pune (IN)
Filed on Mar. 26, 2021, as Appl. No. 17/214,130.
Application 17/214,130 is a continuation of application No. PCT/IB2019/055877, filed on Jul. 10, 2019.
Claims priority of application No. 201821036581 (IN), filed on Sep. 27, 2018.
Prior Publication US 2021/0237779 A1, Aug. 5, 2021
Int. Cl. B60W 60/00 (2020.01); B60W 40/09 (2012.01)
CPC B60W 60/00274 (2020.02) [B60W 40/09 (2013.01); B60W 60/00272 (2020.02); B60W 2554/4045 (2020.02); B60W 2554/4049 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A prediction system implemented in a host vehicle, said system comprising:
an input unit comprising one or more sensors to capture neighboring information of the host vehicle, the neighboring information comprising information of one or more target vehicles and information of surroundings, in proximity of the host vehicle, wherein the host vehicle is positioned in a lane of a road; and
a processing unit comprising a processor coupled with a memory, the memory storing instructions executable by the processor to:
receive the captured neighboring information from the input unit;
generate a grid map by determining dimensions of a grid based on analysis of any or a combination of the captured neighboring information and one or more attributes of the host vehicle;
estimate a trajectory of each target vehicle of the one or more target vehicles, based on a driver behavior model of each target vehicle, to determine an optimized path of each target vehicle, wherein the dimensions of the grid are updated based on said estimation; and
generate a global maneuver model by analyzing motion of each target vehicle based on selection of a model classifier for each target vehicle, wherein the model classifier is selected by analyzing the trajectory estimated for each target vehicle, and wherein on generation of the global maneuver model, a merge cut-in threat for the host vehicle is computed by performing threat assessment and utilizing the trajectory of the one or more target vehicles.