Brake preload system for autonomous vehicles
Vehicles according to at least some embodiments of the disclosure include a sensor, and a computing device comprising at least one hardware processing unit. The computing device is programmed to perform operations comprising capturing an image with the sensor, identifying an object in the image, and in response to an accuracy of the identification meeting a first criterion, pre-loading a braking system of the autonomous vehicle. In some aspects, the computing device may predict that an object not currently within a path of the vehicle has a probability of entering the path of the vehicle that meets a second criterion. When the probability of entering the path meets the second criterion, some of the disclosed embodiments may pre-load the braking system.
1. An apparatus, comprising:
hardware processing circuitry;
a hardware memory storing instructions that when executed configure the hardware processing circuitry to perform operations comprising:
capturing a first image via an imaging sensor;
identifying an object in the first image; and
in response to an accuracy of the identification meeting a first criterion, pre-loading a braking system of an autonomous vehicle.
2. The apparatus of claim 1 , the operations further comprising:
capturing a second image with the sensor;
further identifying the object in the second image; and
in response to an accuracy of the further identification meeting a second criterion, applying brakes via the pre-loaded braking system.
3. The apparatus of claim 1 , further comprising:
the braking system, the braking system comprising:
a pressurized air reservoir;
a service brake chamber in fluid communication with the pressurized air reservoir via a service brake line; and
a service brake valve on the service brake line to control a flow of pressurized air from the pressurized air reservoir to the service brake chamber to selectively engage or disengage a service brake, wherein the pre-loading of the braking system places the service brake valve in an open position so as to route pressurized air from the pressurized air reservoir to the service brake chamber.
4. The apparatus of claim 3 , further comprising a pressure sensor in fluid communication with the service brake chamber, wherein the pre-loading of the braking system reads a pressure measurement from the pressure sensor and maintains the service brake valve in the open position until the pressure measurement indicates a pressure above a first threshold.
5. The apparatus of claim 1 , the operations further comprising releasing the pre-load of the braking system in response to the accuracy of the further identification meeting a second criterion.
6. The apparatus of claim 1 , wherein the accuracy of the identification does not meet the first criterion if the identification of the object is based on less than a predefined number of images.
7. The apparatus of claim 1 , further comprising providing the first image to a trained model to generate a set of probabilities that the object is each of a corresponding set of object types, wherein the accuracy of the identification does not meet the first criterion if none of the probabilities in the set of probabilities is above a threshold.
8. The apparatus of claim 1 , further comprising an imaging sensor, wherein the sensor is the imaging sensor.
9. The apparatus of claim 1 , further comprising a ranging sensor, wherein the sensor is the ranging sensor.
10. The apparatus of claim 1 , the operations further comprising capturing a third image and fusing the third image with the first image, wherein the identification of the object is based on the fused third and first images.
11. The apparatus of claim 1 , wherein pre-loading the braking system of the autonomous vehicle comprises monitoring an air pressure within a braking chamber of the braking system, monitoring a resistance between at least two braking surfaces of the braking system, monitoring a velocity of the autonomous vehicle, or activating the braking system for a defined time limit, the defined time limit insufficient to cause a braking force against motion of the autonomous vehicle.
12. The apparatus of claim 1 , further comprising an autonomous vehicle.
13. A method, comprising:
capturing a first image via an imaging sensor;
identifying an object in the first image; and
in response to an accuracy of the identification meeting a first criterion, pre-loading a braking system of an autonomous vehicle.
14. The method of claim 13 , the operations further comprising:
capturing a second image with the sensor;
further identifying the object in the second image; and
in response to an accuracy of the further identification meeting a second criterion, applying brakes via the pre-loaded braking system.
15. The method of claim 14 , the operations further comprising releasing the pre-load of the braking system in response to the accuracy of the further identification meeting a second criterion.
16. The method of claim 13 , wherein the accuracy of the identification does not meet the first criterion if the identification of the object is based on less than a predefined number of images.
17. The method of claim 13 , further comprising providing the first image to a trained model to generate a set of probabilities that the object is each of a corresponding set of object types, wherein the accuracy of the identification does not meet the first criterion if none of the probabilities in the set of probabilities is above a threshold.
18. A non-transitory computer readable storage medium comprising instructions that when executed configure hardware processing circuitry to perform operations comprising:
capturing a first image via an imaging sensor;
identifying an object in the first image; and
in response to an accuracy of the identification meeting a first criterion, pre-loading a braking system of an autonomous vehicle.
19. The non-transitory computer readable storage medium of claim 18 , the operations further comprising:
capturing a second image with the sensor;
further identifying the object in the second image; and
in response to an accuracy of the further identification meeting a second criterion, applying brakes via the pre-loaded braking system.
20. The non-transitory computer readable storage medium of claim 18 , the operations further comprising providing the first image to a trained model to generate a set of probabilities that the object is each of a corresponding set of object types, wherein the accuracy of the identification does not meet the first criterion if none of the probabilities in the set of probabilities is above a threshold.