AUTONOMOUS VEHICLE WITH IMPROVED VISUAL DETECTION ABILITY

• US 20170285649A1
• Filed: 11/16/2016
• Published: 10/05/2017
• Est. Priority Date: 03/29/2016
• Status: Active Grant

• Current Assignee: AImotive Kft
• Original Assignee: Adasworks Kft.
• Inventors: DEBRECZENI, Gergely
• Granted Patent: US 10,073,462 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2552/35 Road bumpiness, e.g. potholes
• CPC Class Codes: B60W 2552/53 Road markings, e.g. lane marker or crosswalk
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/4029 Pedestrians
• CPC Class Codes: B60W 2720/24 Direction of travel
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 60/001 Planning or execution of driving tasks
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• 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: G08G 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: H04N 5/77 between a recording apparatus and a television camera

Abstract

The invention provides an autonomous vehicle capable of driving independently through a path of intense traffic and transporting objects or people, even on rough surfaces, whilst ensuring safety of the vehicle and general road safety. The autonomous vehicle includes at least one variable pitch camera for producing images to be used for a computer vision to control the autonomous vehicle. The invention facilitates changing the pitch of the variable pitch camera to maximise camera image clarity and/or resolution as the autonomous vehicle moves. The images can be used for lane detection, pedestrian detection, three-dimensional (3D) reconstruction of an environment and/or pothole detection. With the invention, at least one image from the variable pitch camera is used in controlling the movement and/or the trajectory of the autonomous vehicle.

Claims

1. An autonomous vehicle (100), comprising at least one camera (110, 111, or 112) configured to produce images (141, 142, 143, or 144) for the computer vision used to control the autonomous vehicle (100), wherein,

at least one said camera (110, 111, 112, or 113) has a variable and movable pitch, yaw and/or roll to the direction of travel that is configured to be controlled,

the pitch, yaw and/or roll of at least one camera (110, 111, 112, or 113) is configured to be changed to maximise camera image clarity and/or resolution as said autonomous vehicle moves,

at least one image (141, 142, 143, or 144) from the variable pitch, yaw and/or roll camera (110, 111, 112, or 113) is configured to be used in controlling the movement of the autonomous vehicle (100).

2. An autonomous vehicle (100) as claimed in claim 1, characterised in that, at least one said camera (110, 111, 112, or 113) is configured to be used in any of the following:

lane detection, pedestrian detection, general 3D reconstruction of the environment and/or pothole detection.

3. An autonomous vehicle (100) as claimed in claim 1, characterised in that, the variable pitch, yaw and/or roll of the camera (110, 111, 112, or 113) is controlled based on any of the following:

camera position, camera orientation and/or speed of said vehicle, and/or output of image processing algorithm of the camera (100).

4. An autonomous vehicle (100) as claimed in claim 1, characterised in that, the the variable pitch, yaw and/or roll of the camera (110, 111, 112, or 113) is controlled based on any of the following:

weather and/or traffic situation.

5. An autonomous vehicle (100) as claimed in claim 1, characterised in that, the said plurality of cameras (110, 111, 112, or 113) are located in different parts of the autonomous vehicle (100) and are configured to perform different tasks.

6. An autonomous vehicle (100) as claimed in claim 5, characterised in that, each of the said tasks is configured to be completed at a different camera position and/or orientation.

7. An autonomous vehicle (100) as claimed in claim 1, characterised in that, at least one camera output is configured to be processed by an Artificial Intelligence and detection module (410).

8. An autonomous vehicle (100) as claimed in claim 7, characterised in that, the Artificial Intelligence and detection module (410) is configured to send steering control commands to a Steering unit (430).

9. An autonomous vehicle (100) as claimed in claim 8, characterised in that, the Steering unit (430) is configured to use vehicle speed and/or gyroscope data to control and alter the pitch, yaw and/or roll angle of at least one said camera (110, 111, 112, or 113).

10. An autonomous vehicle (100) as claimed in claim 9, characterised in that, the Steering unit (430) is configured to use any of the following:

vehicle speed, output of the imaging algorithm, mapping info, GPS and/or gyroscope data to control and alter the pitch, yaw and/or roll angle of at least one said camera (110, 111, 112, or 113) repeatedly in a closed loop, and optionally the improved detection performance is configured to be used to feed the control logic of the autonomous vehicle (100).

11. A method for controlling an autonomous vehicle (100), comprising at least one camera (110, 111, 112, or 113) configured to produce images (141, 142, 143, or 144) for the computer vision used to control the autonomous vehicle (100), comprising the following steps,

at least one said camera (110, 111, 112, or 113) has a variable and movable pitch, yaw and/or roll to the direction of travel that is controlled,

the pitch, yaw and/or roll of at least one camera (110, 111, 112, or 113) is changed to maximise camera image clarity and/or resolution as said autonomous vehicle (100) moves,

at least one image (141, 142, 143, or 144) from the variable pitch, yaw and/or roll camera (110, 111, 112, or 113) is used in controlling the movement of the autonomous vehicle (100).

12. A method as claimed in claim 11, characterised in that, at least one said camera (110, 111, 112, or 113) is used in any of the following:

lane detection, pedestrian detection, general 3D reconstruction of the environment and/or pothole detection.

13. A method as claimed in claim 11, characterised in that, the pitch, yaw and/or roll of the camera (110, 111, 112, or 113) is controlled based on any of the following:

camera position, camera orientation and/or speed of said vehicle, and/or output of image processing algorithm of the camera (100).

14. A method as claimed in claim 11, characterised in that, the pitch of the variable pitch, yaw and/or roll camera (110, 111, 112, or 113) is controlled based on any of the following:

weather and/or traffic situation.

15. A method as claimed in claim 11, characterised in that, the said plurality of cameras (110, 111, 112, or 113) are located in different parts of the autonomous vehicle (100) and performing different tasks,

16. A method as claimed in claim 15, characterised in that, each of the said tasks is completed at a different camera position and/or orientation.

17. A method as claimed in claim 11, characterised in that, at least one camera output is processed by an Artificial Intelligence and detection module (410).

18. A method as claimed in claim 11, characterised in that, the output of the Artificial Intelligence and detection module (410) sends steering control commands to a Steering unit (430).

19. A method as claimed in claim 18, characterised in that, the Steering unit (430) uses vehicle speed and/or gyroscope data to control and alter the pitch, yaw and/or roll angle of at least one said camera (110, 111, 112, or 113).

20. A method as claimed in claim 19, characterised in that, the Steering unit (430) uses vehicle speed, output of the imaging algorithm, mapping info, GPS and/or gyroscope data to control and alter the pitch, yaw and/or roll angle of at least one said camera (110, 111, 112, or 113) repeatedly in a closed loop, and optionally the improved detection performance is used to feed the control logic of the autonomous vehicle (100).

21. A software program product stored on a non-transient memory medium for controlling an autonomous vehicle (100), comprising at least one camera software configured to produce images (141, 142, 143, or 144) for the computer vision software used to control the autonomous vehicle (100), wherein,

at least one said camera (110, 111, 112, or 113) has a variable and movable pitch, yaw and/or roll to the direction of travel that is configured to be controlled,

the pitch, yaw and/or roll of at least one camera (110, 111, 112, or 113) is configured to be changed to maximise camera image clarity and/or resolution as said autonomous vehicle (100) moves,

at least one image (141, 142, 143, or 144) from the variable pitch, yaw and/or roll camera (110, 111, 112, or 113) is configured to be used in controlling the movement of the autonomous vehicle (100).

22. A software program product as claimed in claim 21, characterised in that, at least one said camera (110, 111, 112, or 113) is configured to be used in any of the following:

lane detection, pedestrian detection, general 3D reconstruction of the environment and/or pothole detection.

23. A software program product as claimed in claim 21, characterised in that, the pitch, yaw and/or roll of the camera (110, 111, 112, or 113) is controlled based on any of the following:

camera position, camera orientation and/or speed of said vehicle (100), and/or output of image processing algorithm of the camera.

24. A software program product as claimed in claim 21, characterised in that, the pitch of the variable pitch camera (110, 111, 112, or 113) is controlled based on any of the following:

weather and/or traffic situation.

25. A software program product as claimed in claim 21, characterised in that, the said plurality of cameras (110, 111, 112, or 113) are located in different parts of the autonomous vehicle (100) and are configured to perform different tasks.

26. A software program product as claimed in claim 25, characterised in that, each of the said tasks is configured to be completed at a different camera position and/or orientation.

27. A software program product as claimed in claim 21, characterised in that, at least one camera output is configured to be processed by an Artificial Intelligence and detection module (410).

28. A software program product as claimed in claim 27, characterised in that, the Artificial Intelligence and detection module (410) is configured to send steering control commands to a Steering unit (430).

29. A software program product as claimed in claim 28, characterised in that, the Steering unit (430) is configured to use vehicle speed and/or gyroscope data to control and alter the pitch angle of at least one said camera (110, 111, 112, or 113).

30. A software program product as claimed in claim 29, characterised in that, the Steering unit (430) is configured to use vehicle speed, output of the imaging algorithm, mapping info, GPS and/or gyroscope data to control and alter the pitch, yaw and/or roll angle of at least one said camera (110, 111, 112, or 113) repeatedly in a closed loop, and optionally the improved detection performance is configured to be used to feed the control logic of the autonomous vehicle (100).