Assisted perception for autonomous vehicles
Disclosed herein are systems and methods for providing supplemental identification abilities to an autonomous vehicle system. The sensor unit of the vehicle may be configured to receive data indicating an environment of the vehicle, while the control system may be configured to operate the vehicle. The vehicle may also include a processing unit configured to analyze the data indicating the environment to determine at least one object having a detection confidence below a threshold. Based on the at least one object having a detection confidence below a threshold, the processor may communicate at least a subset of the data indicating the environment for further processing. The vehicle is also configured to receive an indication of an object confirmation of the subset of the data. Based on the object confirmation of the subset of the data, the processor may alter the control of the vehicle by the control system.
1. A method comprising:
receiving, at a first computing device coupled to a vehicle, sensor data representing an environment of the vehicle, wherein the sensor data is received from a sensor coupled to the vehicle;
detecting, based on the sensor data, the presence of an object in the environment;
determining a confidence level corresponding to the detection of the object is below a confidence threshold;
based on determining the confidence level corresponding to the object is below the confidence threshold, providing, by the first computing device, a request for assistance and the sensor data used to detect the object to a second computing device, the second computing device being remote from the first computing device;
receiving, at the first computing device, a response from the second computing device, the response comprising an identification of the object; and
causing, by the first computing device, the vehicle to perform a control strategy generated based on the response from the second computing device.
2. The method of claim 1 , wherein the confidence level is related to classifying a type of the object.
3. The method of claim 1 , wherein the confidence level is related to confirming the presence of the object in the environment.
4. The method of claim 1 , wherein the second computing device is computationally more powerful than the first computing device.
5. The method of claim 1 , wherein receiving sensor data representing the environment of the vehicle comprises:
receiving images representing the environment of the vehicle; and
wherein providing the request for assistance and the sensor data used to detect the object to the second computing device comprises:
providing the request for assistance with one or more images used to detect the object.
6. The method of claim 5 , wherein the second computing device is computationally more powerful than the first computing device, and
wherein the second computing device is configured to review the one or more images to identify the object.
7. The method of claim 6 , wherein receiving the response from the second computing device comprises:
receiving an identification of the object generated by the second computing device based on the one or more images.
8. The method of claim 6 , wherein receiving the response from the second computing device comprises:
receiving an identification of the object from a human operator using the second computing device, wherein the second computing device is configured to prompt the human operator to review the one or more images when the second computing device is unable to determine the identification of the object.
9. The method of claim 1 , wherein receiving sensor data representing the environment of the vehicle comprises:
receiving first sensor data representing the environment from a camera coupled to the vehicle; and
receiving second sensor data representing the environment from a radar system coupled to the vehicle.
10. The method of claim 9 , wherein determining the confidence level corresponding to the detection of the object is below the confidence threshold comprises:
detecting a difference between the first sensor data and the second sensor data with respect to the object; and
determining the confidence level corresponding to the detection of the object is below the confidence threshold based on detecting the difference.
11. The method of claim 1 , wherein receiving sensor data representing the environment of the vehicle comprises:
receiving audio data from the environment of the vehicle, wherein the audio data is received from a microphone coupled to the vehicle; and
wherein detecting, based on the sensor data, the presence of an object in the environment comprises:
detecting the presence of a siren in the environment.
12. The method of claim 11 , wherein determining the confidence level corresponding to the detection of the object is below the confidence threshold comprises:
determining the confidence level corresponding to the detection of the siren is below the confidence threshold.
13. The method of claim 12 , wherein providing the request for assistance and the sensor data used to detect the object to the second computing device comprises:
providing the request for assistance with a portion of the audio data used to detect the presence of the siren; and
wherein receiving the response from the second computing device comprises:
receiving confirmation that the siren is present in the environment of the vehicle.
14. A system comprising:
a vehicle comprising a sensor; and
a first computing device coupled to the vehicle, wherein the first computing device is configured to:
receive sensor data representing an environment of the vehicle, wherein the sensor data is received from a sensor coupled to the vehicle;
detect, based on the sensor data, the presence of an object in the environment;
determine a confidence level corresponding to the detection of the object is below a confidence threshold;
based on determining the confidence level corresponding to the object is below the confidence threshold, provide a request for assistance and the sensor data used to detect the object to a second computing device, the second computing device being remote from the first computing device;
receive a response from the second computing device, the response comprising an identification of the object; and
cause the vehicle to perform a control strategy generated based on the response from the second computing device.
15. The system of claim 14 , wherein the confidence level is related to classifying a type of the object.
16. The system of claim 14 , wherein the confidence level is related to confirming the presence of the object in the environment.
17. The system of claim 14 , wherein the second computing device is computationally more powerful than the first computing device.
18. The system of claim 14 , wherein the first computing device is configured to:
receive first sensor data representing the environment from a camera coupled to the vehicle and second sensor data representing the environment from a lidar coupled to the vehicle.
19. The system of claim 18 , wherein the first computing device is further configured to:
detect a difference between the first sensor data and the second sensor data with respect to the object; and
determine the confidence level corresponding to the detection of the object is below the confidence threshold based on detecting the difference.
20. A non-transitory computer-readable medium having stored thereon program instructions that, if executed by a first computing device, causes the first computing device to perform operations comprising:
receiving sensor data representing an environment of a vehicle, wherein the sensor data is received from a sensor coupled to the vehicle;
detecting, based on the sensor data, the presence of an object in the environment;
determining a confidence level corresponding to the detection of the object is below a confidence threshold;
based on determining the confidence level corresponding to the object is below the confidence threshold, providing a request for assistance and the sensor data used to detect the object to a second computing device, the second computing device being remote from the first computing device;
receiving a response from the second computing device, the response comprising an identification of the object; and
causing the vehicle to perform a control strategy generated based on the response from the second computing device.