Driving support apparatus, driving support system, driving support method, and computer readable recording medium

• US 10,410,072 B2
• Filed: 11/20/2015
• Issued: 09/10/2019
• Est. Priority Date: 11/20/2015
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Corporation
• Original Assignee: Mitsubishi Electric Corporation
• Inventors: Yoshida, Michinori, Tsushima, Naoyuki, Hasegawa, Takefumi, Abukawa, Masahiro
• Primary Examiner(s): Hoang, Phi
• Application Number:
  US15/772,475
• Publication Number:
  US 20180315240A1
• Time in Patent Office: 1,390 Days
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G05D 1/0212 with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 1/096716 where the received information does not generate an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096741 where the source of the transmitted information selects which information to transmit to each vehicle
• CPC Class Codes: G08G 1/09675 where a selection from the received information takes place in the vehicle
• CPC Class Codes: G08G 1/096783 where the origin of the information is a roadside individual element
• CPC Class Codes: G08G 1/096791 where the origin of the information is another vehicle
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A driving support apparatus (10) converts at least one of a first map (43) and a second map (53) so that the first map (43) and the second map (53) become three-dimensional maps in a same coordinate system. The first map (43) is a three-dimensional map indicating three-dimensional positions of objects around a vehicle (100). The second map (53) is a three-dimensional map indicating three-dimensional positions of objects around an external apparatus (200) that is one of a roadside apparatus (201) and a different vehicle (202) from the vehicle (100). Then, the driving support apparatus (10) synthesizes the first map (43) and the second map (53) after the conversion, thereby generating a composite map (44).

Claims

1. A driving support apparatus comprising:

processing circuitry

to acquire sensor data from a sensor mounted on a vehicle,

to generate a first map from the acquired sensor data, the first map being a three-dimensional map indicating three-dimensional positions of objects around the vehicle,

to receive a second map from transmission equipment mounted on an external apparatus, the second map being generated from sensor data acquired from a sensor mounted on the external apparatus, the second map being a three-dimensional map indicating three-dimensional positions of objects around the external apparatus, the external apparatus being one of a roadside apparatus and a different vehicle from the vehicle,

to convert the second map so that a second coordinate system being a coordinate system of the second map matches a first coordinate system being a coordinate system of the first map generated, and

to generate a composite map by synthesizing the first map and the second map after the conversion,

wherein the processing circuitry

repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the first map, three target points, as a point a1, a point a2, and a point a3 and repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the second map, three target points respectively made to correspond to the point a1, the point a2, and the point a3, as a point b1, a point b2, and a point b3,

computes a likelihood when the point a1 and the point b1 indicate a same position, the point a2 and the point b2 indicate a same position, and the point a3 and the point b3 indicate a same position,

computes a conversion amount for matching the second coordinate system to the first coordinate system, assuming that, with respect to the target points repeatedly extracted and having a high likelihood computed, the point a1 and the point b1 indicate the same position, the point a2 and the point b2 indicate the same position, and the point a3 and the point b3 indicate the same position,

converts the second map, using the conversion amount computed,

computes, using a distance between the point b1 and the point b2, the position of the point b2 when the point b1 is placed at the same position as the point a1 in the first coordinate system and the point b2 is placed on a straight line X passing through the point a1 and the point a2,

computes, using a distance between the point b2 and the point b3, the position of the point b3 when the point b3 is placed on a straight line Z in the first coordinate system, the straight line Z being obtained by moving a straight line Y passing through the point a2 and the point a3 in parallel so that the straight line Y passes through the position of the point b2 computed, and

computes a distance between the point a3 and the position of the point b3 computed, as the likelihood.

2. The driving support apparatus according to claim 1,

wherein the processing circuitry extracts, as the point b1, a point indicating the position of the object having an attribute being the same as an attribute of the object whose position is indicated by the point a1, extracts, as the point b2, a point indicating the position of the object having an attribute being the same as an attribute of the object whose position is indicated by the point a2, and extracts, as the point b3, a point indicating the position of the object having an attribute being the same as an attribute of the object whose position is indicated by the point a3.

3. The driving support apparatus according to claim 1, wherein the processing circuitry

receives a plurality of the second maps from the transmission equipment mounted on the external apparatus,

identifies, among the plurality of the second maps received, the second map generated from data acquired at a same time as an acquisition time of data used for generating the first map, and

synthesizes the first map and the second map identified.

4. The driving support apparatus according to claim 3,

wherein when there is not the second map generated from the data acquired at the same time as the acquisition time, the processing circuitry estimates the second map to be generated from the data acquired at the same time as the acquisition time, using the plurality of the second maps, and

synthesizes the first map and the second map estimated.

5. The driving support apparatus according to claim 1, wherein the processing circuitry

determines a travel route, based on the composite map generated, and

controls the vehicle so that the vehicle travels on the travel route determined.

6. The driving support apparatus according to claim 1, wherein the processing circuitry

displays the composite map generated.

7. A driving support apparatus comprising:

processing circuitry

to acquire sensor data from a sensor mounted on a vehicle,

to generate a first map from the acquired sensor data, the first map being a three-dimensional map indicating three-dimensional positions of objects around the vehicle,

to receive a second map from transmission equipment mounted on an external apparatus, the second map being generated from sensor data acquired from a sensor mounted on the external apparatus, the second map being a three-dimensional map indicating three-dimensional positions of objects around the external apparatus, the external apparatus being one of a roadside apparatus and a different vehicle from the vehicle,

to convert the second map so that a second coordinate system being a coordinate system of the second map matches a first coordinate system being a coordinate system of the first map generated, and

to generate a composite map by synthesizing the first map and the second map after the conversion,

wherein the processing circuitry

repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the first map, three target points, as a point a1, a point a2, and a point a3 and repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the second map, three target points respectively made to correspond to the point a1, the point a2, and the point a3, as a point b1, a point b2, and a point b3,

computes a likelihood when the point a1 and the point b1 indicate a same position, the point a2 and the point b2 indicate a same position, and the point a3 and the point b3 indicate a same position,

computes a conversion amount for matching the second coordinate system to the first coordinate system, assuming that, with respect to the target points repeatedly extracted and having a high likelihood computed, the point a1 and the point b1 indicate the same position, the point a2 and the point b2 indicate the same position, and the point a3 and the point b3 indicate the same position,

converts the second map, using the conversion amount computed,

computes a rotation amount when a straight line Y passing through the point b1 and the point b2 in the second coordinate system is converted to a straight line parallel to a straight line X passing through the point a1 and the point a2 in the first coordinate system,

computes a translation amount in the conversion amount when a rotation amount in the conversion amount for matching the second coordinate system to the first coordinate system is assumed to be the rotation amount computed,

computes the positions of the point b1, the point b2, and the point b3 in the first coordinate system, based on the rotation amount computed and the translation amount computed, and

computes a sum of a distance between the point a1 and the position of the point b1 computed, a distance between the point a2 and the position of the b2 computed, and a distance between the point a3 and the position of the point b3 computed, as the likelihood.

8. A driving support apparatus comprising:

processing circuitry

to acquire sensor data from a sensor mounted on a vehicle,

to generate a first map from the acquired sensor data, the first map being a three-dimensional map indicating three-dimensional positions of objects around the vehicle, and

to receive a second map from transmission equipment mounted on an external apparatus, the second map being generated from sensor data acquired from a sensor mounted on the external apparatus, the second map being a three-dimensional map indicating three-dimensional positions of objects around the external apparatus, the external apparatus being one of a roadside apparatus and a different vehicle from the vehicle,

to convert the second map so that a second coordinate system being a coordinate system of the second map matches a first coordinate system being a coordinate system of the first map, and

to generate a composite map by synthesizing the first map and the second map after the conversion,

wherein the processing circuitry

repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the first map, three target points, as a point a1, a point a2, and a point a3 and repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the second map, three target points respectively made to correspond to the point a1, the point a2, and the point a3, as a point b1, a point b2, and a point b3,

computes a likelihood when the point a1 and the point b1 indicate a same position, the point a2 and the point b2 indicate a same position, and the point a3 and the point b3 indicate a same position,

computes a conversion amount for matching the second coordinate system to the first coordinate system, assuming that, with respect to the target points repeatedly extracted and having a high likelihood computed, the point a1 and the point b1 indicate the same position, the point a2 and the point b2 indicate the same position, and the point a3 and the point b3 indicate the same position,

converts the second map, using the conversion amount computed,

computes a distance a12 between the point a1 and the point a2, a distance a23 between the point a2 and the point a3, a distance a13 between the point a1 and the point a3, a distance b12 between the point b1 and the point b2, a distance b23 between the point b2 and the point b3, and a distance b13 between the point b1 and the point b3, and

computes a sum of a difference between the distance a12 and the distance b12, a difference between the distance a23 and the distance b23, and a difference between the distance a13 and the distance b13, as the likelihood.

9. A driving support system comprising a driving support apparatus installed on a vehicle and an externally mounted apparatus mounted on an external apparatus being one of a roadside apparatus and a different vehicle from the vehicle,

wherein the externally mounted apparatus includes:

a first sensor to detect positions of objects around the external apparatus; and

a transmitting unit to transmit data regarding the detected positions of objects around the external apparatus to the driving support apparatus,

wherein the driving support apparatus includes;

processing circuitry

to acquire sensor data from a second sensor mounted on the vehicle,

to generate a first map from the acquired sensor data, the first map being a three-dimensional map indicating three-dimensional positions of objects around the vehicle,

to receive the data regarding the positions transmitted by the transmitting unit,

to convert a second map obtained from the received data regarding the positions so that a second coordinate system being a coordinate system of the second map matches a first coordinate system being a coordinate system of the first map, and

to generate a composite map by synthesizing the first map and the second map after the conversion,

wherein the processing circuitry

repeatedly extracts, from a plurality of points indicating the three-dimensional positions of the objects in the first map, three target points, as a point a1, a point a2, and a point a3 and to repeatedly extract, from a plurality of points indicating the three-dimensional positions of the objects in the second map, three target points respectively made to correspond to the point a1, the point a2, and the point a3, as a point b1, a point b2, and a point b3;

computes a likelihood when the point a1 and the point b1 indicate a same position, the point a2 and the point b2 indicate a same position, and the point a3 and the point b3 indicate a same position;

computes a conversion amount for matching the second coordinate system to the first coordinate system, assuming that, with respect to the target points repeatedly extracted by the target point extraction unit and having a high computed likelihood, the point a1 and the point b1 indicate the same position, the point a2 and the point b2 indicate the same position, and the point a3 and the point b3 indicate the same position;

converts the second map, using the conversion amount;

computes, using a distance between the point b1 and the point b2, the position of the point b2 when the point b1 is placed at the same position as the point a1 in the first coordinate system and the point b2 is placed on a straight line X passing through the point a1 and the point a2;

computes, using a distance between the point b2 and the point b3, the position of the point b3 when the point b3 is placed on a straight line Z in the first coordinate system, the straight line Z being obtained by moving a straight line Y passing through the point a2 and the point a3 in parallel so that the straight line Y passes through the position of the point b2; and

computes a distance between the point a3 and the position of the point b3, as the likelihood.

10. A driving support method comprising:

acquiring sensor data from a sensor mounted on a vehicle;

generating a first map from the acquired sensor data, the first map being a three-dimensional map indicating three-dimensional positions of objects around a vehicle; and

receiving a second map from transmission equipment mounted on an external apparatus, the second map being generated from sequence data acquired from a sensor mounted on the external apparatus, the second map being a three-dimensional map indicating three-dimensional positions of objects around the external apparatus, the external apparatus being one of a roadside apparatus and a different vehicle from the vehicle;

converting the second map so that a second coordinate system being a coordinate system of the second map matches a first coordinate system being a coordinate system of the first map generated; and

generating a composite map by synthesizing the first map and the second map after the conversion,

wherein converting the second map includes;

repeatedly extracting, from a plurality of points indicating the three-dimensional positions of the objects in the first map, three target points, as a point a1, a point a2, and a point a3 and repeatedly extracting, from a plurality of points indicating the three-dimensional positions of the objects in the second map, three target points respectively made to correspond to the point a1, the point a2, and the point a3, as a point b1, a point b2, and a point b3;

computing a likelihood when the point a1 and the point b1 indicate a same position, the point a2 and the point b2 indicate a same position, and the point a3 and the point b3 indicate a same position;

computing a conversion amount for matching the second coordinate system to the first coordinate system, assuming that, with respect to the target points repeatedly extracted by the target point extraction step and having a high likelihood computed by the likelihood computation step, the point a1 and the point b1 indicate the same position, the point a2 and the point b2 indicate the same position, and the point a3 and the point b3 indicate the same position; and

converting the second map, using the conversion amount computed, and

wherein computing the likelihood includes;

computing, using a distance between the point b1 and the point b2, the position of the point b2 when the point b1 is placed at the same position as the point a1 in the first coordinate system and the point b2 is placed on a straight line X passing through the point a1 and the point a2;

computing, using a distance between the point b2 and the point b3, the position of the point b3 when the point b3 is placed on a straight line Z in the first coordinate system, the straight line Z being obtained by moving a straight line Y passing through the point a2 and the point a3 in parallel so that the straight line Y passes through the position of the point b2 computed; and

computing a distance between the point a3 and the position of the point b3 computed, as the likelihood.

11. A non-transitory computer readable medium storing a driving support program to cause a computer to execute a process including:

acquiring sensor data from a sensor mounted on a vehicle;

generating a first map from the acquired sensor data, the first map being a three-dimensional map indicating three-dimensional positions of objects around the vehicle;

receiving a second map from transmission equipment mounted on an external apparatus, the second map being generated from sensor data acquired from a sensor mounted on the external apparatus, the second map being a three-dimensional map indicating three-dimensional positions of objects around the external apparatus, the external apparatus being one of a roadside apparatus and a different vehicle from the vehicle;

converting the second map so that a second coordinate system being a coordinate system of the second map matches a first coordinate system being a coordinate system of the first map; and

generating a composite map by synthesizing the first map and the second map after the conversion,

wherein the converting step includes;

repeatedly extracting, from a plurality of points indicating the three-dimensional positions of the objects in the first map, three target points, as a point a1, a point a2, and a point a3 and repeatedly extracting, from a plurality of points indicating the three-dimensional positions of the objects in the second map, three target points respectively made to correspond to the point a1, the point a2, and the point a3, as a point b1, a point b2, and a point b3;

computing a likelihood when the point a1 and the point b1 indicate a same position, the point a2 and the point b2 indicate a same position, and the point a3 and the point b3 indicate a same position;

computing a conversion amount for matching the second coordinate system to the first coordinate system, assuming that, with respect to the target points repeatedly extracted and having a high computed likelihood, the point a1 and the point b1 indicate the same position, the point a2 and the point b2 indicate the same position, and the point a3 and the point b3 indicate the same position; and

converting the second map, using the conversion amount, and

wherein the likelihood computation process includes;

computing, using a distance between the point b1 and the point b2, the position of the point b2 when the point b1 is placed at the same position as the point a1 in the first coordinate system and the point b2 is placed on a straight line X passing through the point a1 and the point a2;

computing, using a distance between the point b2 and the point b3, the position of the point b3 when the point b3 is placed on a straight line Z in the first coordinate system, the straight line Z being obtained by moving a straight line Y passing through the point a2 and the point a3 in parallel so that the straight line Y passes through the position of the point b2; and

computing a distance between the point a3 and the position of the point b3, as the likelihood.