SPONSOR

Featured

Ford files 20 patents on Motorcycle Filtering Detection Technology


According to the filed patent, system uses the set of cameras and sensors for detection of the motorcycles between lane.
What is claimed is:
1. A controller for an autonomous vehicle comprising:
one or more processing devices programmed to
receive one or more image streams;
receive one or more audio streams;
identify a plurality of vehicle images in the one or more image streams;
identify a plurality of audible features in the one or more audio streams; and
identify a potential lane-splitting motorcycle by correlating the plurality of vehicle images and the plurality of audible features.
2. The controller of claim 1, wherein the one or more processing devices are further programmed to receive environmental information from one or more of one or more cameras, RADAR sensors, LIDAR sensors, and SONAR sensors.
3. The controller of claim 2, wherein the one or more processing devices are further programmed to:
in response to identifying the potential lane-splitting motorcycle, avoid causing the autonomous vehicle to make lane changes.
4. The controller of claim 1, wherein the one or more processing devices are further programmed to:
identify one or more audible features in the one or more audio streams, the one or more audible features having a motorcycle-specific sound pattern;
identify among the plurality of vehicle images, motorcycle-specific image patterns;
attempt to correlate the one or more audible features and the one or more image patterns;
if the one or more audible features and the one or more image patterns are correlated, augment a confidence score that the potential lane-splitting motorcycle is a potential obstacle.
5. The controller of claim 4, wherein the one or more processing devices are programmed to attempt to correlate the one or more audible features and the one or more image patterns by inputting the one or more audible features and one or more image patterns to a machine learning algorithm.
6. The controller of claim 5, wherein the one or more processing devices are further programmed to identify among the plurality of vehicle images, motorcycle-specific image patterns comprises identifying objects exhibiting motorcycle-specific movement among the plurality of vehicle images.
7. The controller of claim 5, wherein the one or more processing devices are further programmed to identify the one or more audible features by filtering the one or more audio streams to obtain a filtered signal including the one or more audible features.
8. The controller of claim 1, further comprising a microphone array coupled thereto, the microphone array configure to generate the one or more audio streams.
9. The controller of claim 1, further comprising at least one microphone coupled configured to generate the one or more audio streams, the at least one microphone located within a cabin of the autonomous vehicle.
10. The controller of claim 1, further comprising one or more cameras configured to generate the one or more images streams, the one or more cameras coupled to the autonomous vehicle and oriented rearwardly relative to the autonomous vehicle.
11. A method for collision avoidance comprising:
receiving, by a controller of an autonomous vehicle, one or more image streams;
receiving, by the controller, one or more audio streams;
identifying, by the controller, a plurality of vehicle images in the one or more image streams;
identifying, by the controller, a plurality of audible features in the one or more audio streams; and
identifying, by the controller, a potential lane-splitting motorcycle by correlating the plurality of vehicle images and the plurality of audible features.
12. The method of claim 11, further comprising:
identifying, by the controller, a set of potential obstacles among the plurality of vehicle images, the set of potential obstacles including the potential lane splitting motorcycle;
evaluating, by the controller, possible collisions between the autonomous vehicle and the set of potential obstacles; and
activating, by the controller, at least one of a steering actuator, accelerator actuator, and brake actuator of the autonomous vehicle effective to avoid collisions with the set of potential obstacles.
13. The method of claim 12, further comprising:
in response to identifying the potential lane-splitting motorcycle, avoiding, by the controller, causing the autonomous vehicle to make lane changes.
14. The method of claim 11, further comprising:
(a) identifying, by the controller, one or more audible features in the one or more audio streams, the one or more audible features having motorcycle-specific sound patterns;
(b) identifying, by the controller, among the plurality of vehicle images, image patterns characteristic of a motorcycle;
(c) attempting, by the controller, to correlate the one or more audible features and the one or more image patterns;
in response to the attempt of (c) being successful, augmenting, by the controller, a confidence score that the potential lane-splitting motorcycle is a potential obstacle.
15. The method of claim 14, wherein attempting to correlate the one or more audible features and the one or more image patterns comprises inputting the one or more audible features and one or more image patterns to a machine learning algorithm.
16. The method of claim 15, wherein identifying among the plurality of vehicle images, motorcycle-specific image patterns comprises identifying objects exhibiting motorcycle-specific movement among the plurality of vehicle images.
17. The method of claim 15, wherein identifying the one or more audible features comprises filtering the one or more audio streams to obtain a filtered signal including the one or more audible features.
18. The method of claim 11, wherein receiving the one or more audio streams comprises receiving the one or more audio streams from a microphone array.
19. The method of claim 11, wherein receiving the one or more audio streams comprises receiving the one or more audio streams from least one microphone coupled located within a cabin of the autonomous vehicle.
20. The method of claim 11, wherein receiving the one or more images streams comprises receiving the one or more image streams from one or more cameras coupled to the autonomous vehicle and oriented rearwardly relative to the autonomous vehicle.

1 comment: