Methods and systems for pedestrian avoidance using LIDAR

• US 9,315,192 B1
• Filed: 09/30/2013
• Issued: 04/19/2016
• Est. Priority Date: 09/30/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhu, Jiajun, Morton, Peter
• Primary Examiner(s): To, Tuan C.
• Application Number:
  US14/041,121
• Time in Patent Office: 932 Days
• Field of Search: 701/28
• US Class Current: 1/1
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/42 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• 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: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

An autonomous vehicle configured to detect and avoid pedestrians may use information from LIDAR or other range-based sensors. An example method involves: (a) receiving, at a computing device, range data corresponding to a plurality of objects in an environment of a vehicle, wherein the range data comprises a plurality of first data points; (b) generating a spherical data set comprising a plurality of second data points, wherein spherical coordinates for each second data point are generated based on a corresponding one of the first plurality of data points; and (c) determining a two-dimensional map based on the spherical data set comprising the plurality of second data points, wherein the two-dimensional map comprises a plurality of pixels, wherein each pixel of the plurality of pixels is indicative of a plurality of parameters corresponding to the plurality of objects in the environment.

Claims

1. A computer-implemented method comprising:

receiving, at a computing device from at least one sensor coupled to a vehicle, range data corresponding to a plurality of objects in an environment of the vehicle, wherein the range data comprises a plurality of first data points configured in a three-dimensional point cloud;

responsive to receiving the range data, generating a spherical data set comprising a plurality of second data points, wherein spherical coordinates for each second data point are generated based on a corresponding one of the first plurality of data points; and

determining, by the computing device associated with the vehicle, a two-dimensional map based on the spherical data set comprising the plurality of second data points, wherein the two-dimensional map comprises a plurality of pixels, wherein each pixel of the plurality of pixels is indicative of a plurality of parameters including elevation information, intensity information, and distances from the vehicle corresponding to the plurality of objects in the environment.

2. The method of claim 1, wherein the plurality of parameters corresponding to the plurality of objects in the environment comprises range information corresponding to the plurality of objects in the environment.

3. The method of claim 1, further comprising:

based on the two-dimensional map, determining whether or not one or more pixels of the plurality of pixels is indicative of a plurality of parameters corresponding to a pedestrian.

4. The method of claim 1, further comprising:

determining whether or not a predefined pattern exists within the two-dimensional map, wherein the predefined pattern is indicative of an object.

5. The method of claim 4, wherein determining whether or not a predefined pattern exists within the two-dimensional map comprises:

using a predefined pattern indicative of a pedestrian; and

based on whether or not the predefined pattern indicative of a pedestrian exists within the two-dimensional map, identifying a pedestrian.

6. The method of claim 3, wherein determining whether or not one or more pixels of the plurality of pixels is indicative of a plurality of parameters corresponding to a pedestrian comprises analyzing the two-dimensional map based on a set of predefined values for the plurality of parameters and the distance between each pixel in the plurality of pixels.

7. The method of claim 1, further comprising:

based on the two-dimensional map, determining whether or not one or more pixels of the of pixels is indicative of a plurality of parameters corresponding to a pedestrian via a sliding window scan.

8. The method of claim 1, wherein generating a spherical data set comprising a plurality of second data points comprises removing any data points that do not comprise an elevation above a predefined threshold based on an elevation map.

9. An autonomous-vehicle system comprising:

one or more sensors;

a computer system associated with a vehicle configured to;

receive, from at least one sensor, range data corresponding to a plurality of objects in an environment of the vehicle, wherein the range data comprises a plurality of first data points configured in a three-dimensional point cloud;

responsive to receiving the range data, generate a spherical data set comprising a plurality of second data points, wherein spherical coordinates for each second data point are generated based on a corresponding one of the first plurality of data points; and

determine a two-dimensional map based on generating the spherical data set comprising the plurality of second data points, wherein the two-dimensional map comprises a plurality of pixels, wherein each pixel of the plurality of pixels is indicative of a plurality of parameters including elevation information, intensity information, and distances from the vehicle corresponding to the plurality of objects in the environment.

10. The system of claim 9, wherein the plurality of parameters corresponding to the plurality of objects in the environment comprises range information corresponding to the plurality of objects in the environment.

11. The system of claim 9, further comprising:

based on the two-dimensional map, determine whether or not one or more pixels of the plurality of pixels is indicative of a plurality of parameters corresponding to a pedestrian.

12. The system of claim 9, further comprising:

based on the two-dimensional map, determine whether or not one or more pixels of the of pixels is indicative of a plurality of parameters corresponding to a pedestrian via a sliding window scan.

13. The non-transitory computer-readable medium of claim 12, wherein the instructions further comprise:

instructions for, based on the two-dimensional map, determining whether or not one or more pixels of the plurality of pixels is indicative of a plurality of parameters corresponding to a pedestrian via a sliding window scan.

14. A non-transitory computer-readable medium having program instructions stored thereon that are executable by at least one processor, the program instructions comprising:

instructions for receiving, at a computing device from at least one sensor coupled to a vehicle, range data corresponding to a plurality of objects in an environment of the vehicle, wherein the range data comprises a plurality of first data points configured in a three-dimensional point cloud;

instructions for generating, responsive to receiving the range data, a spherical data set comprising a plurality of second data points, wherein spherical coordinates for each second data point are generated based on a corresponding one of the first plurality of data points; and

instructions for determining a two-dimensional map based on generating the spherical data set comprising the plurality of second data points, wherein the two-dimensional map comprises a plurality of pixels, wherein each pixel of the plurality of pixels is indicative of a plurality of parameters including elevation information, intensity information, and distances from the vehicle corresponding to the plurality of objects in the environment.