System and method for computing a probability that an object comprises a target

Patent metadata

Field	Value
Publication number	US-10515319-B2
Application number	US-201615382074-A
Country	US
Kind code	B2
Filing date	Dec 16, 2016
Priority date	Dec 16, 2016
Publication date	Dec 24, 2019
Grant date	Dec 24, 2019

Abstract

A method for computing a probability that an object comprises a target includes: performing a scan of an area comprising the object, generating points; creating a segment corresponding to the object using the points as segment points, the segment extending from a first segment point to a last segment point, the segment comprising a plurality of the segment points; and applying a metric, computing the probability that the object comprises the target.

First claim

What is claimed is:

1. A method for computing a probability that an object comprises a target, comprising:
using a computer, using segment points obtained in a scan of an area comprising a segment, the segment comprising a plurality of segment points, creating a line corresponding to the object, the line extending from a first segment point to a last segment point;
using the computer, adding the line to a candidate set of lines;
using the computer, for at least one segment point, computing a point-line distance from the point to the line; and
using the computer, determining that the point-line distance is less than a threshold distance;
using the computer, finding a farthest point that comprises the point that is farthest from the line;
using the computer, separating the segment points in the segment into a first group of adjacent segment points and a second group of adjacent segment points, with the farthest point being the only segment point in common between the first group and the second group, the farthest point being defined as the last segment point for the first group, the farthest point also being defined as the first segment point for the second group; and
using the computer, removing the line from a candidate set of lines;
using the computer, identifying the segment as one or more of target and non-target; and filtering the segment to integrate the classification with knowledge about one or more of locations of humans and locations of non-humans.

2. The method of claim 1 , wherein the filtering step comprises a sub-step of performing data association between a classified human appendage and a known location of a human.

3. The method of claim 1 , wherein the filtering step comprises using one or more of a particle filter, an Extended Kalman Filter (EKF), and another filter.

4. A method for computing a probability that an object comprises a target, comprising:
using a computer, using segment points obtained in a scan of an area comprising a segment, the segment comprising a plurality of segment points, creating a line corresponding to the object, the line extending from a first segment point to a last segment point;
using the computer, adding the line to a candidate set of lines;
using the computer, for at least one segment point, computing a point-line distance from the point to the line; and
using the computer, determining that the point-line distance is less than a threshold distance;
using the computer, finding a farthest point that comprises the point that is farthest from the line;
using the computer, separating the segment points in the segment into a first group of adjacent segment points and a second group of adjacent segment points, with the farthest point being the only segment point in common between the first group and the second group, the farthest point being defined as the last segment point for the first group, the farthest point also being defined as the first segment point for the second group; and
using the computer, removing the line from a candidate set of lines;
using the computer, identifying the segment as one or more of target and non-target, wherein the identifying step comprises a sub-step of removing a segment that corresponds to a non-moving object.

5. The method of claim 4 , wherein the removing sub-step comprises a sub-sub-step of:
performing one or more of reducing a weight accorded to the non-moving object and completely removing the non-moving object.

6. The method of claim 5 , wherein the performing sub-sub-step comprises:
consulting a map that indicates where the non-moving objects is located.

7. The method of claim 5 , wherein the performing sub-sub-step comprises:
consulting a costmap, factoring into the performing a calculation of likely cost as a function of distance.

8. The method of claim 1 , wherein the filtering step comprises a sub-step of remove a segment that corresponds to a non-moving object.

9. The method of claim 8 , wherein the removing sub-step comprises a sub-sub-step of:
performing one or more of reducing a weight accorded to the non-moving object and completely removing the non-moving object.

10. The method of claim 9 , wherein the performing sub-sub-step comprises:
consulting a map that indicates where the non-moving objects is located.

11. The method of claim 9 , wherein the performing sub-sub-step comprises:
consulting a costmap, factoring into the performing a calculation of likely cost as a function of distance.

Assignees

• Fetch Robotics Inc

Inventors

• Henning Alex
• Ferguson Michael
• Wise Melonee

Classifications

• G06N3/008

  based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• Y10S901/01

  Mobile robot · CPC title

• Y10S901/46

  Sensing device · CPC title