Method, system and apparatus for self-driving vehicle obstacle avoidance

Patent metadata

Field	Value
Publication number	US-11225275-B2
Application number	US-202017016478-A
Country	US
Kind code	B2
Filing date	Sep 10, 2020
Priority date	May 29, 2015
Publication date	Jan 18, 2022
Grant date	Jan 18, 2022

Abstract

A system for path control for a mobile unmanned vehicle in an environment is provided. The system includes: a sensor connected to the mobile unmanned vehicle; the mobile unmanned vehicle configured to initiate a first fail-safe routine responsive to detection of an object in a first sensor region adjacent to the sensor; and a processor connected to the mobile unmanned vehicle. The processor is configured to: generate a current path based on a map of the environment; based on the current path, issue velocity commands to cause the mobile unmanned vehicle to execute the current path; responsive to detection of an obstacle in a second sensor region, initiate a second fail-safe routine in the mobile unmanned vehicle to avoid entry of the obstacle into the first sensor region and initiation of the first fail-safe routine.

First claim

We claim:

1. A method for obstacle avoidance for a self-driving vehicle in an environment, the method comprising:
operating, by a processor of the self-driving vehicle, the vehicle to autonomously navigate the environment, the processor being in communicationwith one or more sensors mounted to the self-driving vehicle, at least one sensor of the one or more sensors is configured to measure rotational velocity data for the vehicle;
defining, by the processor, a first sensor region and a second sensor region for at least one sensor of the one or more sensors, the at least one sensor being configured to detect an object in the first or second sensor regions, wherein the second sensor region has a greater range than the first sensor region;
receiving, by the processor from the second sensor, rotational velocity data for the vehicle;
based on the rotational velocity data, determining, by the processor, that the vehicle is turning along a turn direction;
in response to determining that the vehicle is turning along the turn direction, adjusting, by the processor, an orientation of at least the first sensor to follow the turn direction while the vehicle is turning;
based on sensor data generated by the at least one sensor, detecting, by the processor, an object in at least one of the first or second sensor regions; and

in response to detecting the object in at least one of the first or second sensor regions, adjusting, by the processor, an operation of the self-driving vehicle to reduce a risk of colliding with the object.

2. The method of claim 1 , wherein adjusting, by the processor, an orientation of at least the first sensor further comprises at least one of: maintaining constant the orientation of the second sensor, or adjusting the orientation of the second sensor to follow the turn direction.

3. The method of claim 1 , wherein the first and second sensor regions correspond to a detection range of the at least one sensor.

4. The method of claim 1 , wherein the processor operates the vehicle to follow a vehicle trajectory, the vehicle trajectory comprising a plurality of segments each defining a portion of the vehicle trajectory and having a corresponding segment-specific vehicle travel direction, the method further comprising:
determining, by the processor, a current location of the vehicle along the vehicle trajectory;
identifying, by the processor, a current segment corresponding to the current location of the vehicle;
determining, by the processor, a next segment along the vehicle trajectory that is subsequent to the current segment; and
determining, by the processor, that the vehicle is turning based on the segment-specific travel directions for the current segment and the next segment.

5. The method of claim 4 , further comprising:
accessing, by the processor, a map of the environment, wherein the map includes information for the plurality of segments and the segment-specific travel directions; and
determining, by the processor, the current segment and the next segment based on the map and the current location of the vehicle.

6. The method of claim 5 , wherein the map is stored on a memory coupled to the processor.

7. The method of claim 4 , wherein each of the plurality of segments include corresponding segment-specific vehicle speed, and the method further comprises:
determining, by the processor, a current location of the vehicle along the vehicle trajectory;
identifying, by the processor, a segment corresponding to the current location of the vehicle;
determining a segment-specific vehicle speed which corresponds to the identified segment; and
adjusting a range of at least one of the first and second sensor regions based on the segment-specific vehicle speed.

8. The method of claim 1 , wherein at least one sensor of the one or more sensors is configured to measure vehicle speed, and the method further comprises:
receiving, by the processor from the second sensor, a vehicle speed; and
adjusting, by the processor, a range of at least one of the first and second sensor regions based on the vehicle speed.

9. The method of claim 1 , further comprising:
detecting, by the processor, an object in at least one of the first and second sensor regions; and
in response to detecting the object in the first sensor region, triggering, by the processor, an emergency stop to avoid collision with the object;
otherwise, in response to detecting the object in the second sensor region, generating, by the processor, a vehicle trajectory to avoid the object and operating, by the processor, the vehicle to follow the vehicle trajectory.

10. A system for self-driving vehicle obstacle avoidance in an environment, the system comprising:
a processor connected to the self-driving vehicle;
one or more sensors mounted to the self-driving vehicle and in communication with the processor, at least one sensor of the one or more sensors being configured to detect an object, at least one sensor of the one or more sensors is configured to measure rotational velocity data for the vehicle;
the processor being configured to:
operate the self-driving vehicle to autonomously navigate the environment; define a first sensor region and a second sensor region for the at least one sensor, wherein the second sensor region has a greater range than the first sensor region;
based on the rotational velocity data, determine that the vehicle is turning along a turn direction;
in response to determining that the vehicle is turning along the turn direction, adjust an orientation of at least the first sensor to follow the turn direction while the vehicle is turning;
detect, based on sensor data generated by the at least one sensor, an object in at least one of the first or second sensor regions; and in response to detecting the object in at least one of the first or second sensor regions, adjust an operation of the self-driving vehicle to reduce a risk of colliding with the object.

11. The system of claim 10 , wherein adjusting an orientation of at least the first sensor further comprises at least one of: maintain constant the orientation of the second sensor, or adjust the orientation of the second sensor to follow the turn direction.

12. The system of claim 10 , wherein the first and second sensor regions correspond to a detection range of the at least one sensor.

13. The system of claim 10 , wherein the processor is further configured to:
operate the vehicle to follow a vehicle trajectory, the vehicle trajectory comprising a plurality of segments each defining a portion of the vehicle trajectory and having a corresponding segment-specific vehicle travel direction;
determine a current location of the vehicle along the vehicle trajectory;
identify a current segment corresponding to the current location of the vehicle;
determine a next segment along the vehicle trajectory that is subsequent to the current segment; and
determine that the vehicle is turning based on the segment-specific travel directions for the current segment and the next segment.

14. The system of claim 13 , wherein the processor is further configured to:
access a map of the environment, wherein the map includes information for the plurality of segments and the segment-specific travel directions; and
determine the current segment and the next segment based on the map and the current location of the vehicle.

15. The system of claim 14 , wherein the system further comprises a memory coupled to the processor, and the map is stored on the memory.

16. The system of claim 13 , wherein each of the plurality of segments include corre

Assignees

• Clearpath Robotics Inc

Inventors

• Gariepy Ryan Christopher
• Bencz Alex
• Ma Yan
• Irvine Michael
• Kaynama Shahab
• Servos James
• Chen Peiyi

Classifications

• B61L15/0072

  On-board train data handling · CPC title

• G05D1/0238 Primary

  using obstacle or wall sensors (G05D1/0246 and G05D1/0289 take precedence; lidar systems designed for anti-collision purposes G01S17/93) · CPC title

• G05D2201/0212

  Physics · mapped topic

• G05D1/0066

  for limitation of acceleration or stress · CPC title

• B61L3/008

  Operations & Transport · mapped topic