Sensor recognition integration device

Patent metadata

Field	Value
Publication number	US-11636691-B2
Application number	US-201917253884-A
Country	US
Kind code	B2
Filing date	Jun 11, 2019
Priority date	Jun 22, 2018
Publication date	Apr 25, 2023
Grant date	Apr 25, 2023

Abstract

The present invention provides a sensor recognition integration device capable of preventing a rapid change in coordinates of an integrated object and preventing, for example, an erroneous determination in an autonomous driving plan determination device, even when the combination of sensors that perform detection changes. In the present invention, since an object position is estimated in a state where information of a position detected by a sensor that recognizes an object in an external field is corrected or changed, the rapid change of coordinates of an integrated object is prevented even when the combination of sensors that perform detection changes.

First claim

The invention claimed is:

1. A sensor recognition integration device comprising:
a sensor object information unit that generates integration object information by integrating sensor object information regarding a sensor object obtained by a plurality of external field recognition sensors recognizing an object in an external field,
wherein the sensor object information integration unit includes
an integration object information storage unit that stores the integration object information,
a prediction update unit that extracts a prediction object to be predicted from the integration object information which is previously stored in the integration object information storage unit, and predicts a position of the prediction object after a predetermined time, without using the sensor object information,
an association unit that estimates the prediction object to be associated with the sensor object information,
an offset parameter update unit that updates an offset parameter required for calculating an offset to be applied to the sensor object information,
an integration target information generation unit that applies the offset to the sensor object based on the offset parameter and generates integration target information in which the prediction object and the offset-applied sensor object are linked to each other, based on an estimation result of the association unit, and
an integration update unit that generates the integration object information including the estimated position of the object based on the integration target information.

2. The sensor recognition integration device according to claim 1 , wherein the offset parameter update unit updates the offset parameter such that the offset to be applied to the sensor object information has a magnitude depending on an external situation.

3. The sensor recognition integration device according to claim 1 , wherein the offset parameter update unit updates the offset parameter by adding a difference of an estimation target time to an offset duration time obtained by the association unit.

4. The sensor recognition integration device according to claim 1 , wherein the integration target information generation unit adopts an offset function of reducing a magnitude of the offset to be applied to a position or a speed of the sensor object with time, and setting the magnitude to 0 for a predetermined offset application completion time.

5. The sensor recognition integration device according to claim 1 , wherein the integration target information generation unit adopts an offset function of setting the offset to be applied to a speed of the sensor object to be a derivative of the offset to be applied to a position of the sensor object.

6. The sensor recognition integration device according to claim 1 , wherein the integration target information generation unit adopts an offset function of determining an offset application completion time for each prediction object.

7. The sensor recognition integration device according to claim 1 , wherein the integration target information generation unit adopts an offset function of causing a maximum value of a magnitude of a difference vector to be equal for all prediction objects, the difference vector being between the offset to be applied to a position or a speed of the sensor object and the offset to be applied to the position or the speed of the sensor object before a predetermined time.

8. The sensor recognition integration device according to claim 1 , wherein the integration target information generation unit is configured not to apply the offset when it is determined that the offset is not required to be applied, by a situation of the sensor object.

9. The sensor recognition integration device according to claim 1 , wherein the integration target information generation unit adopts an offset function capable of calculating the offset to be applied to the sensor object only by a product-sum operation.

10. A sensor recognition integration device that receives own-vehicle behavior information, sensor object information, sensor road information, positioning information, and map information acquired by an information acquisition device including an own-vehicle behavior recognition sensor, a plurality of external field recognition sensors, a positioning system, and a map unit, integrates the received information, and transmits a result of the integration to an autonomous driving plan determination device, the sensor recognition integration device comprising:
a sensor object information integration unit that integrates the sensor object information regarding a sensor object obtained by the plurality of external field recognition sensors recognizing an object in an external field, as integration object information; and
an own-vehicle surrounding information integration unit that integrates the integration object information, the own-vehicle behavior information, the sensor road information, the positioning information, and the map information as own-vehicle surrounding information and outputs the own-vehicle surrounding information to the autonomous driving plan determination device,
wherein the sensor object information integration unit includes
an integration object information storage unit that stores the integration object information,
a prediction update unit that extracts a prediction object to be predicted from the integration object information which is previously stored in the integration object information storage unit, and predicts a position of the prediction object after a predetermined time, without using the sensor object information,
an association unit that estimates the prediction object to be associated with the sensor object information,
an offset parameter update unit that updates an offset parameter required for calculating an offset to be applied to the sensor object information,
an integration target information generation unit that calculates the offset to be applied to the sensor object information based on the offset parameter to apply the calculated offset to the sensor object and generates integration target information in which the prediction object and the offset-applied sensor object are linked to each other, based on an estimation result of the association unit, and
an integration update unit that estimates the position of the object to generate integration object information, based on the integration target information.

Assignees

• Hitachi Automotive Systems Ltd
• Hitachi Astemo Ltd

Inventors

• Aoki Naoto
• Hayase Shigenori

Classifications

• G01S13/862

  Combination of radar systems with sonar systems · CPC title

• B60W40/04

  Traffic conditions · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06F18/251

  of input or preprocessed data · CPC title

• G01S13/867 Primary

  Combination of radar systems with cameras · CPC title