Object bounding box estimation

• US 8,736,463 B1
• Filed: 01/30/2012
• Issued: 05/27/2014
• Est. Priority Date: 01/30/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhu, Jiajun, Haehnel, Dirk
• Primary Examiner(s): Tweel, Jr., John A
• Application Number:
  US13/361,023
• Time in Patent Office: 848 Days
• Field of Search: 340/933, 340/937, 180/169, 382/103, 382/104, 348/148, 701/1
• US Class Current: 340/933
• CPC Class Codes: B60K 31/0008 including means for detecting potential obstacles in vehicle path
• CPC Class Codes: B60W 2552/35 Road bumpiness, e.g. potholes
• CPC Class Codes: G01S 17/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S17/46
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• 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

Abstract

Aspects of the disclosure relate generally to maneuvering autonomous vehicles. Specifically, the vehicle may use a laser to collect scan data for a section of roadway. The vehicle may access a detailed map including the section of the roadway. A disturbance indicative of an object and including a set of data points data may be identified from the scan data based on the detailed map. The detailed map may also be used to estimate a heading of the disturbance. A bounding box for the disturbance may be estimated using the set of data points as well as the estimated heading. The parameters of the bounding box may then be adjusted in order to increase or maximize the average density of data points of the disturbance along the edges of the bounding box visible to the laser. This adjusted bounding box may then used to maneuver the vehicle.

Claims

1. A method for maneuvering a vehicle, the method comprising:

receiving sensor data from at least one sensor, the sensor data including a plurality of data points, each data point representing a location and elevation of a particular surface associated a section of roadway;

accessing a detailed map of the section of roadway;

identifying a disturbance in the sensor data indicative of an object in the section of roadway based on the detailed map, the disturbance being associated with a set of data points;

estimating, by a processor, a bounding box for the disturbance based on the detailed map;

projecting the set of data points of the disturbance onto a 2-dimensional intensity map within the estimated bounding box;

identifying edges of the bounding box visible to the at least one sensor;

adjusting a parameter of the estimated bounding box in order to increase a number of data points of the set of data points along the identified edges; and

using the adjusted bounding box to maneuver the vehicle.

2. The method of claim 1, wherein the at least one sensor includes a laser and the sensor data includes data points generated from the laser scanning the section of the roadway.

3. The method of claim 1, wherein the detailed map includes information indicating locations of the surface of the roadway, and the disturbance is identified by selecting data points that are associated with a location at or above a threshold distance above the locations of the surface of the roadway.

4. The method of claim 1, further comprising estimating a heading of the disturbance based on the detailed map.

5. The method of claim 1, wherein the detailed map includes information indicating a direction of a lane and estimating the heading of the disturbance is based on the information indicating the direction of the lane.

6. The method of claim 1, wherein the parameter is adjusted in order to maximize the number of data points of the set of data points along the identified edges.

7. The method of claim 1, wherein the parameter of the bounding box includes at least one of a heading, a position, an orientation, and a dimension.

8. A device for maneuvering a vehicle, the device comprising:

memory storing a detailed map of the section of roadway;

a processor coupled to the memory, the processor being operable to;

receive sensor data from at least one sensor, the sensor data including a plurality of data points, each data point representing a location and elevation of a particular surface associated a section of roadway;

identify a disturbance in the sensor data indicative of an object in the section of roadway based on the detailed map, the disturbance being associated with a set of data points;

estimate a bounding box for the disturbance based on the detailed map;

project the set of data points of the disturbance onto a 2-dimensional intensity map within the estimated bounding box;

identify edges of the bounding box visible to the at least one sensor;

adjust a parameter of the estimated bounding box in order to increase a number of data points of the set of data points along the identified edges; and

use the adjusted bounding box to maneuver the vehicle.

9. The device of claim 8, further comprising the at least one sensor.

10. The device of claim 9, wherein the at least one sensor includes a laser and the sensor data includes data points generated from the laser scanning the section of the roadway.

11. The device of claim 8, the memory further stores information indicating locations of the surface of the roadway, and the processor is further operable to identify the disturbance by selecting data points that are associated with a location at or above a threshold distance above the locations of the surface of the roadway.

12. The device of claim 8, wherein the processor is further operable to estimate a heading of the disturbance based on the detailed map.

13. The device of claim 8, wherein the memory also stores information indicating a direction of a lane and the processor is further operable to estimate the heading of the disturbance based on the information indicating the direction of the lane.

14. The device of claim 8, wherein the processor is further operable to adjust the parameter in order to maximize the number of data points of the set of data points along the identified edges.

15. The device of claim 8, wherein the processor is further operable to adjust the parameter of the bounding box by adjusting at least one of a heading, a position, an orientation, and a dimension of the bounding box.

16. A tangible computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by a processor, cause the processor to perform a method of maneuvering a vehicle, the method comprising:

receiving sensor data from at least one sensor, the sensor data including a plurality of data points, each data point representing a location and elevation of a particular surface associated a section of roadway;

accessing a detailed map of the section of roadway;

identifying a disturbance in the sensor data indicative of an object in the section of roadway based on the detailed map, the disturbance being associated with a set of data points;

estimating a bounding box for the disturbance based on the detailed map;

projecting the set of data points of the disturbance onto a 2-dimensional intensity map within the estimated bounding box;

identifying edges of the bounding box visible to the at least one sensor;

adjusting a parameter of the estimated bounding box in order to increase a number of data points of the set of data points along the identified edges; and

using the adjusted bounding box to maneuver the vehicle.

17. The tangible computer-readable storage medium of claim 16, the detailed map includes information indicating locations of the surface of the roadway, and the method further includes identifying the disturbance by selecting data points that are associated with a location at or above a threshold distance above the locations of the surface of the roadway.

18. The tangible computer-readable storage medium of claim 16, wherein the method further comprises estimating a heading of the disturbance based on the detailed map.

19. The tangible computer-readable storage medium of claim 16, wherein the detailed map includes information indicating a direction of a lane and the method further includes estimating the heading of the disturbance based on the information indicating the direction of the lane.

20. The tangible computer-readable storage medium of claim 16, wherein the method further includes adjusting the parameter in order to maximize the number of data points of the set of data points along the identified edges.