System for grid-based merge cut-in prediction and method thereof

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.

2. The prediction system of claim 1 , wherein the processor further analyzes a condition for a change in the merge cut-in threat of the target vehicles based on the generated global maneuver model and environmental factors obtained from the information of the surroundings.

3. The prediction system of claim 1 , wherein the processor further assesses a centralized risk management for merge cut-in based on the generated global maneuver model.

4. The prediction system of claim 1 , wherein the processor further performs adaptive grid mapping and dynamic grid sizing to dynamically alter shape and size of the grid based on the one or more attributes of the host vehicle and assess threat by utilizing the captured neighboring information.

5. The prediction system of claim 1 , wherein the driver behavior model for each target vehicle is developed by analyzing one or more of a driving parameter, lateral dynamics, longitudinal dynamics, or consistency in driving profile of the target vehicles.

6. The prediction system of claim 1 , wherein estimation of trajectory of each target vehicle is further based on assessing threat based on one or more of a neighboring situation, environmental factors, or estimated trajectories of other target vehicles, wherein the neighboring situation, the environmental factors, or the estimated trajectories of other target vehicles are determined by analyzing the neighboring information.

7. The prediction system of claim 1 , wherein a length of the grid is computed based on a longitudinal velocity and a longitudinal acceleration of the host vehicle, a width of the grid is computed based on a lateral velocity and a lateral acceleration of the host vehicle, and a shape of the grid is computed based on a lane of the host vehicle and an estimated path of the host vehicle.

8. The prediction system of claim 1 , wherein the processor estimates a trajectory of each target vehicle using a Hidden Markov Model (HMM) by:

defining HMM states for the target vehicle based on driver behavior model of the target vehicle;

iteratively optimizing path of the target vehicle based on feedback of the HMM model from the global maneuver model and influence of other target vehicles; and

selecting a priority trajectory of the target vehicle as optimized trajectory to be maintained across the grid map for searching optimized path for other target vehicles of the one or more target vehicles in the grid map.

9. The prediction system of claim 8 , wherein selection of the model classifier is performed based on one or more of a translation motion, a maneuvering motion, an overtaking motion, a lane change motion, or an unpredictable motion of the target vehicle.

10. The prediction system of claim 1 , wherein the threat assessment comprises assessment of a threat of collision due to a merge cut-in of any of the one or more target vehicles or the host vehicle.

11. A method, carried out according to instructions stored in a computer implemented in a host vehicle, comprising:

receiving neighboring information of the host vehicle from one or more sensors, 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;

generating 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;

estimating 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

generating 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.

12. The method of claim 11 , further comprising analyzing a condition for a change in the merge cut-in threat of the target vehicles based on the generated global maneuver model and environmental factors obtained from the information of the surroundings.

13. The method of claim 11 , further comprising assessing a centralized risk management for merge cut-in based on the generated global maneuver model.

14. The method of claim 11 , further comprising performing adaptive grid mapping and dynamic grid sizing to dynamically alter shape and size of the grid based on the one or more attributes of the host vehicle and assess threat by utilizing the captured neighboring information.

15. The method of claim 11 , wherein the driver behavior model for each target vehicle is developed by analyzing one or more of a driving parameter, lateral dynamics, longitudinal dynamics, or consistency in driving profile of the target vehicles.

16. The method of claim 11 , wherein estimation of trajectory of each target vehicle is further based on assessing threat based on one or more of a neighboring situation, environmental factors, or estimated trajectories of other target vehicles, wherein the neighboring situation, the environmental factors, or the estimated trajectories of other target vehicles are determined by analyzing the neighboring information.

17. The method of claim 11 , wherein a length of the grid is computed based on a longitudinal velocity and a longitudinal acceleration of the host vehicle, a width of the grid is computed based on a lateral velocity and a lateral acceleration of the host vehicle, and a shape of the grid is computed based on a lane of the host vehicle and an estimated path of the host vehicle.

18. The method of claim 11 , further comprising estimating a trajectory of each target vehicle using a Hidden Markov Model (HMM) by:

defining HMM states for the target vehicle based on driver behavior model of the target vehicle;

iteratively optimizing path of the target vehicle based on feedback of the HMI model from the global maneuver model and influence of other target vehicles; and

selecting a priority trajectory of the target vehicle as optimized trajectory to be maintained across the grid map for searching optimized path for other target vehicles of the one or more target vehicles in the grid map,

wherein selection of the model classifier is performed based on one or more of a translation motion, a manuvering motion, an overtaking motion, a lane change motion, or an unpredictable motion of the target vehicle.

19. The method of claim 11 , wherein the threat assessment comprises assessment of a threat of collision due to a merge cut-in of any of the one or more target vehicles or the host vehicle.

20. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to:

receive neighboring information of the host vehicle from one or more sensors, 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;

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.