Augmented learning model for autonomous earth-moving vehicles
Systems and methods for using augmented learning models for autonomous earth-moving vehicles are disclosed. The method can comprise receiving a second set of sensor data; generating a first condensed vector from the second set of sensor data at least in part by processing the second set of sensor data with a first machine learning model; selecting an action to be performed by the vehicle at least in part by processing the first condensed vector with a second machine learning model. The method can further comprise retrieving one or more samples of sensor data from the first set of sensor data; fine-tuning the first machine learning model at least in part by processing the one or more samples of sensor data to produce a second condensed vector; and fine-tuning the second machine learning model at least in part by processing the second condensed vector.
1. A method for autonomous operation of a vehicle, comprising:
(a) maintaining, at a computer data store, a first set of sensor data;
(b) until a convergence condition is reached:
(i) executing, by one or more processors, a first set of instructions and a second set of instructions in parallel, the first set of instructions comprising:
(1) receiving a second set of sensor data, wherein the second set of sensor data is not included within the first set of sensor data;
(2) generating a first condensed vector from the second set of sensor data at least in part by processing the second set of sensor data with a first machine learning model; and
(3) selecting an action to be performed by the vehicle at least in part by processing the first condensed vector with a second machine learning model;
(ii) the second set of instructions comprising:
(1) retrieving one or more samples of sensor data from the first set of sensor data and/or the second set of sensor data;
(2) fine-tuning the first machine learning model at least in part by processing the one or more samples of sensor data to produce a second condensed vector; and
(3) fine-tuning the second machine learning model at least in part by processing the second condensed vector; and
(c) prior to (b), (i) training, by the one or more processors, the first machine learning model on the first set of sensor data and (ii) training, by the one or more processors, the second machine learning model at least in part on the first condensed vector produced by the first machine learning model.
2. The method of claim 1 , wherein the first machine learning model includes a first set of model weights, and the second machine learning model includes a second set of model weights.
3. The method of claim 2 , wherein the fine-tuning further comprises changing the first set of model weights and/or the second set of model weights based on an outcome of the action.
4. The method of claim 1 , wherein the vehicle comprises an earth-moving vehicle or piece of heavy machinery.
5. The method of claim 4 , wherein the earth-moving vehicle or piece of heavy machinery comprises an earthmover, bulldozer, backhoe, shovel, tractor, snowcat, excavator, crane, forklift, boring machine, harvester, compactor, drilling machine, pile driver, street sweeper, snow plow machine, cherry picker, or dump truck.
6. The method of claim 1 , wherein the first set of instructions is executed on a first thread and the second set of instructions is executing on a second thread.
7. The method of claim 1 , further comprising training, by the one or more processors, the second machine learning model on the first set of sensor data.
8. The method of claim 1 , further comprising, prior to (b), condensing, by sampling, the first set of sensor data.
9. The method of claim 8 , further comprising, prior to (b)(i)(2), condensing, by sampling, the second set of sensor data.
10. The method of claim 8 , wherein the fine-tuning further comprising, computing the differences between the first set of sensor data and the second set of sensor data.
11. The method of claim 1 , wherein the first set of sensor data comprises light detection and ranging (LIDAR) data, GPS data, vehicle state data, or a combination thereof, and wherein the second set of sensor data comprises LIDAR data, GPS data, vehicle state data, or a combination thereof.
12. The method of claim 11 , wherein the vehicle state data comprises position data or motion data.
13. The method of claim 12 , wherein the position data is associated with a component of the vehicle.
14. The method of claim 13 , wherein the position data is associated with an angle or orientation of the component of the vehicle.
15. The method of claim 14 , wherein the component of the vehicle comprises an arm, a blade, or a tool.
16. The method of claim 15 , wherein the tool comprises a digging bucket, a hammer, a hydraulic thumb, a coupler, a breaker, a compactor, a grading bucket, a demolition grapple, or a tiltrotator.
17. The method of claim 12 , wherein the motion data relates to speed or acceleration.
18. The method of claim 17 , wherein the motion data is the speed of the vehicle or the acceleration of the vehicle.
19. The method of claim 12 , wherein the motion data is associated with a component of the vehicle, and wherein the motion data relates to speed or acceleration.