Target recognition and localization methods using a laser sensor for wheeled mobile robots

• US 10,175,049 B2
• Filed: 03/14/2018
• Issued: 01/08/2019
• Est. Priority Date: 06/02/2011
• Status: Active Grant

• Current Assignee: Honda Motor Company
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Wang, Junmin, Govindarajan, Madhu Soodhanan, Post, II, James W., Fox, Andrew John
• Primary Examiner(s): Khatib, Rami
• Assistant Examiner(s): Foster, Gerrad A
• Application Number:
  US15/920,520
• Publication Number:
  US 20180202812A1
• Time in Patent Office: 300 Days
• Field of Search: None
• CPC Class Codes: G01B 11/028 by measuring lateral position of a boundary of the object G01B11/022, G01B11/024, G01B11/04 take precedence
• CPC Class Codes: G01B 7/004 for measuring coordinates of points
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G06T 11/005 Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating

Abstract

A target system that includes a target that is selected, wherein the target includes a surface with depth variations. The target system additionally includes a laser sensor adapted to scan the target for localization.

Claims

1. A target system, comprising:

a wheeled robot/vehicle that includes a laser sensor that unilaterally scans a wide angular section of a surrounding environment; and

a target that is identified based on the scanning by the laser sensor, wherein the target includes a surface with uniquely combined depth variations,

wherein the laser sensor is adapted to scan the target for localization, wherein the localization occurs based on a detection of the target by the laser sensor, wherein the target is detected by distance measurements upon the laser sensor scanning the surface of the target based on the uniquely combined depth variations.

2. The target system of claim 1, wherein the laser sensor is used to recognize a pattern of the target, wherein the pattern of the target is used as a reference for the localization.

3. The target system of claim 1, further including generating templates for the target, wherein the templates for the target include three different templates that are each utilized based on the location of the wheeled robot/vehicle.

4. The target system of claim 1, wherein the depth variations of the surface of the target include at least two edge depth variations.

5. The target system of claim 4, wherein each depth variation includes an edge depth to width ratio, wherein the target is selected taking into account the edge depth to width ratio that is based on a worst angle of the laser sensor.

6. The target system of claim 5, wherein the worst angle of the laser sensor includes at least one of:

an angle at which the laser sensor loses a required accuracy to detect the target based on refraction of a laser signal and an angle at which the entire length of the target cannot be detected by the laser sensor.

7. The target system of claim 5, wherein the target is selected based on a likelihood of detecting the target by the laser sensor, wherein the likelihood of detecting the target by the laser sensor is increased when the edge depth to width ratio is greater than or equal to a tangent of the worst angle.

8. The target system of claim 1, wherein the laser sensor is adapted to a laser scanner that is mounted on a rotary actuator, wherein the rotary actuator provides the laser scanner with a capability of rotary motion.

9. The target system of claim 8, wherein the laser scanner and the rotary actuator are mounted to a linear actuator that is used as a guide way to move the laser scanner and the rotary actuator together along a lateral direction, wherein the linear actuator provides the laser scanner with a capability of linear motion.