System for predicting vehicle behavior

Patent metadata

Field	Value
Publication number	US-2020357282-A1
Application number	US-201916408257-A
Country	US
Kind code	A1
Filing date	May 9, 2019
Priority date	May 9, 2019
Publication date	Nov 12, 2020
Grant date	—

Abstract

Example implementations described herein involve a system for predicting vehicle behavior with a higher efficiency which can reduce the number of sensors and the amount of data needed for vehicle control systems. Example implementations described herein can be used for any type of vehicle control system, such as a powertrain control system, an adaptive cruise control system, an autonomous driving system, because the target vehicle to be predicted can be replaced to a preceding vehicle, a surrounding vehicle, and an ego vehicle.

First claim

What is claimed is:

1 . A method, comprising:
obtaining state sensor information and location sensor information of a target vehicle, the state sensor information indicative of a vehicle state of the target vehicle, the location sensor information indicative of a location of the target vehicle; determining a behavior prediction of the target vehicle through determining potential state changes of the target vehicle based on comparing the vehicle state of the target vehicle and the location of the target vehicle to one or more historical data points of vehicle state and vehicle location pairs; and controlling a vehicle system based on the behavior prediction of the target vehicle.

2 . The method of claim 1 , further comprising:
obtaining traffic sensor information indicative of a traffic density in proximity to the target vehicle; wherein the one or more historical data points of vehicle state and vehicle location pairs are selected from historical data points within a distance of the target vehicle, the distance determined based on the traffic density and the vehicle state of the target vehicle.

3 . The method of claim 1 , further comprising obtaining the one or more historical data points of the vehicle state and vehicle location pairs from a database, the database selected based on one or more of: a designation of a road type associated with the target vehicle being a major road type or minor road type, a vehicle type of the target vehicle, and a time of day in a week.

4 . The method of claim 1 , wherein the target vehicle is a vehicle in front of the vehicle system, wherein the controlling the vehicle system based on the behavior prediction comprises reducing a speed of the vehicle system for the behavior prediction being indicative of deceleration of the target vehicle.

5 . The method of claim 1 , wherein the target vehicle is the vehicle system, wherein the controlling the vehicle system based on the behavior prediction of the target vehicle comprises, for the behavior prediction indicative of the vehicle system heading towards a portion of a travel route in which speed is reduced, reducing the speed of the vehicle system based on the location of the target vehicle.

6 . The method of claim 1 , wherein the controlling a vehicle system based on the behavior prediction of the target vehicle comprises providing a notification in the vehicle system indicative of control being initiated before controlling the vehicle system.

7 . A non-transitory computer readable medium, storing instructions for executing a process, the instructions comprising:
obtaining state sensor information and location sensor information of a target vehicle, the state sensor information indicative of a vehicle state of the target vehicle, the location sensor information indicative of a location of the target vehicle; determining a behavior prediction of the target vehicle through determining potential state changes of the target vehicle based on comparing the vehicle state of the target vehicle and the location of the target vehicle to one or more historical data points of vehicle state and vehicle location pairs; and controlling a vehicle system based on the behavior prediction of the target vehicle.

8 . The non-transitory computer readable medium of claim 7 , the instructions further comprising:
obtaining traffic sensor information indicative of a traffic density in proximity to the target vehicle; wherein the one or more historical data points of vehicle state and vehicle location pairs are selected from historical data points within a distance of the target vehicle, the distance determined based on the traffic density and the vehicle state of the target vehicle.

9 . The non-transitory computer readable medium of claim 7 , the instructions further comprising obtaining the one or more historical data points of the vehicle state and vehicle location pairs from a database, the database selected based on one or more of: a designation of a road type associated with the target vehicle being a major road type or minor road type, a vehicle type of the target vehicle, and a time of day in a week.

10 . The non-transitory computer readable medium of claim 7 , wherein the target vehicle is a vehicle in front of the vehicle system, wherein the controlling the vehicle system based on the behavior prediction comprises reducing a speed of the vehicle system for the behavior prediction being indicative of deceleration of the target vehicle.

11 . The non-transitory computer readable medium of claim 7 , wherein the target vehicle is the vehicle system, wherein the controlling the vehicle system based on the behavior prediction of the target vehicle comprises, for the behavior prediction indicative of the vehicle system heading towards a portion of a travel route in which speed is reduced, reducing the speed of the vehicle system based on the location of the target vehicle.

12 . The non-transitory computer readable medium of claim 7 , wherein the controlling a vehicle system based on the behavior prediction of the target vehicle comprises providing a notification in the vehicle system indicative of control being initiated before controlling the vehicle system.

13 . A vehicle system, comprising:
a location sensor configured to measure a location of a target vehicle; a state sensor configured to measure a vehicle state of the target vehicle; a storage device configured to store one or more historical data points of vehicle state and vehicle location pairs; and a processor, configured to: determine a behavior prediction of the target vehicle through determining potential state changes of the target vehicle based on comparing the vehicle state of the target vehicle and the location of the target vehicle to the one or more historical data points of vehicle state and vehicle location pairs; and control the vehicle system based on the behavior prediction of the target vehicle.

14 . The vehicle system of claim 13 , wherein the processor is configured to:
obtain traffic sensor information indicative of a traffic density in proximity to the target vehicle from a traffic system; and store the one or more historical data points of vehicle state and vehicle location pairs into the storage device based on a selection from historical data points within a distance of the target vehicle, the distance determined based on the traffic density and the vehicle state of the target vehicle.

15 . The vehicle system of claim 13 , wherein the processor is configured to obtain the one or more historical data points of the vehicle state and vehicle location pairs from a database, the database selected based on one or more of: a designation of a road type associated with the target vehicle being a major road type or minor road type, a vehicle type of the target vehicle, and a time of day in a week.

16 . The vehicle system of claim 13 , wherein the target vehicle is a vehicle in front of the vehicle system, wherein the processor is configured to control the vehicle system based on the behavior prediction by instructing an electronics control unit (ECU) to reduce a speed of the vehicle system for the behavior prediction being indicative of deceleration of the target vehicle.

17 . The vehicle system of claim 13 , wherein the target vehicle is the vehicle system, wherein the processor is configured to control the vehicle system based on the behavior prediction of the target vehicle by, for the behavior prediction indicative of the vehicle system heading towards a portion of a travel route in which speed is reduc

Assignees

• Hitachi Automotive Systems Ltd

Inventors

• Imanishi Yuto
• Kundu Subrata Kumar
• Iihoshi Yoichi
• Okada Takashi
• Okuda Yuuki

Classifications

• B60W2556/10

  Historical data · CPC title

• B60W2050/0075

  Automatic parameter input, automatic initialising or calibrating means · CPC title

• G08G1/0129

  for creating historical data or processing based on historical data · CPC title

• G08G1/166 Primary

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title