Obstacle evaluation technique

• US 8,781,721 B2
• Filed: 06/06/2012
• Issued: 07/15/2014
• Est. Priority Date: 06/06/2012
• Status: Active Grant

• Current Assignee: Waymo LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Dowdall, Jonathan Baldwin, Zhu, Jiajun
• Primary Examiner(s): To, Tuan C.
• Application Number:
  US13/489,794
• Publication Number:
  US 20130332061A1
• Time in Patent Office: 769 Days
• Field of Search: 701/301, 340/436, 348/139
• US Class Current: 701/301
• CPC Class Codes: B60R 21/00 Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks safety belts or body harnesses in vehicles B60R22/00; devices, apparatus or methods for life-saving in general A62B; safety devices for propulsion unit control specially adapted for, or arranged in, vehicles B60K28/00; seats constructed to protect the occupant from the effect of abnormal g-forces, e.g. crash or safety seats, B60N2/42; energy-absorbing arrangements for hand wheels for steering vehicles B62D1/11; energy-absorbing arrangements for vehicle steering columns B62D1/19; harnessing in aircraft B64D25/00
• CPC Class Codes: B60R 21/013 including means for detecting collisions, impending collisions or roll-over
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• 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 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A vehicle configured to operate in an autonomous mode may engage in an obstacle evaluation technique that includes employing a sensor system to collect data relating to a plurality of obstacles, identifying from the plurality of obstacles an obstacle pair including a first obstacle and a second obstacle, engaging in an evaluation process by comparing the data collected for the first obstacle to the data collected for the second obstacle, and in response to engaging in the evaluation process, making a determination of whether the first obstacle and the second obstacle are two separate obstacles.

Claims

1. A method comprising:

a vehicle system employing at least one sensor to collect data relating to a plurality of obstacles;

the vehicle system identifying from the plurality of obstacles an obstacle pair, the obstacle pair including a first obstacle and a second obstacle;

the vehicle system engaging in an evaluation process by comparing the data collected for the first obstacle to the data collected for the second obstacle,wherein the evaluation process includes at least one of the follow;

(i) a determination of whether a change in distance between the first and second obstacles exceeds a distance threshold,

(ii) a determination of whether a speed differential between the first and second obstacles exceeds a speed threshold, and

(iii) a determination of whether an orientation differential between the first and second obstacles exceeds an orientation threshold; and

based on the evaluation process, the vehicle system making a determination of whether the first obstacle and the second obstacle are two separate obstacles.

2. The method of claim 1, further comprising the vehicle system determining that, based on the collected data, at least one of the first obstacle and the second obstacle has taken some action that is inconsistent with the first obstacle and second obstacle being a single obstacle;

and

the vehicle system classifying the obstacle pair as two separate obstacles.

3. The method of claim 1, further comprising the vehicle system determining that, based on the collected data, the first obstacle and the second obstacle have not taken any action that is inconsistent with the first obstacle and second obstacle being a single obstacle;

and

the vehicle system classifying the obstacle pair a single obstacle.

4. The method of claim 1, wherein the collected data comprises distance data, and wherein the evaluation process comprises:

calculating the change in distance between the first obstacle and the second obstacle; and

determining whether the change in distance exceeds a distance threshold.

5. The method of claim 1, wherein the collected data comprises speed data, and wherein the evaluation process comprises:

calculating the speed differential between the first obstacle and the second obstacle; and

determining whether the speed differential exceeds the speed threshold.

6. The method of claim 1, wherein the collected data comprises orientation data, and wherein the evaluation process comprises:

calculating the orientation differential between the first obstacle and the second obstacle; and

determining whether the orientation differential exceeds the orientation threshold.

7. A method comprising:

a vehicle system using a sensor system to collect data for a first obstacle and a second obstacle, the collected data including at least one of speed data, distance data, and orientation data;

the vehicle system engaging in a first evaluation process by comparing the collected data and determining whether a first threshold is met;

based on the first evaluation process, the vehicle system making a first determination of whether the first obstacle and the second obstacle are two separate obstacles;

the vehicle system detecting that one or more environmental conditions have changed and responsively changing the first threshold to a second threshold;

the vehicle system engaging in a second evaluation process by comparing the collected data and determining whether the second threshold is met; and

based on the second evaluation process, making a second determination of whether the first obstacle and the second obstacle are two separate obstacles.

8. The method of claim 7, wherein the first evaluation process comprises calculating a change in distance between the first obstacle and the second obstacle, and determining whether the change in distance exceeds a first distance threshold, and

wherein the second evaluation process comprises calculating a new change in distance between the first obstacle and the second obstacle, and determining whether the new change in distance exceeds a second distance threshold.

9. The method of claim 7, wherein the first evaluation process comprises calculating a speed differential between the first obstacle and the second obstacle and determining whether the speed differential exceeds a first speed threshold, and

wherein the second evaluation process comprises calculating a new speed differential between the first obstacle and the second obstacle and determining whether the new speed differential exceeds a second speed threshold.

10. The method of claim 7, wherein the first evaluation process comprises calculating an orientation differential between the first obstacle and the second obstacle and determining whether the orientation differential exceeds a first orientation threshold, and

wherein the second evaluation process comprises calculating a new orientation differential between the first obstacle and the second obstacle and determining whether the new orientation differential exceeds a second orientation threshold.

11. A non-transitory computer readable medium (CRM) having stored thereon instructions executable by a computing device to cause the computing device to perform functions, the functions comprising:

employing at least one sensor to collect data relating to a plurality of obstacles;

identifying from the plurality of obstacles an obstacle pair, the obstacle pair including a first obstacle and a second obstacle;

engaging in an evaluation process by comparing the data collected for the first obstacle to the data collected for the second obstacle, wherein the evaluation process includes at least one of the following;

(i) a determination of whether a change in distance between the first and second obstacles exceeds a distance threshold,

(ii) a determination of whether a speed differential between the first and second obstacles exceeds a speed threshold, and

(iii) a determination of whether an orientation differential between the first and second obstacles exceeds an orientation threshold; and

based on the evaluation process, making a determination of whether the first obstacle and the second obstacle are two separate obstacles.

12. The CRM of claim 11, wherein the functions further comprise:

determining, based on the evaluation process, that no threshold condition is met; and

in response to determining that no threshold condition is met, classifying the obstacle pair as a single obstacle.

13. The CRM of claim 12, wherein the evaluation process includes:

(i) the determination of whether the change in distance between the first and second obstacles exceeds the distance threshold,

(ii) the determination of whether the speed differential between the first and second obstacles exceeds the speed threshold, and

(iii) the determination of whether the orientation differential between the first and second obstacles exceeds the orientation threshold.