| CPC G01M 17/0072 (2013.01) [G07C 5/0808 (2013.01)] | 13 Claims |
|
1. An autonomous vehicle comprising:
a vehicle propulsion system;
at least one memory comprising instructions; and
at least one processor coupled to the vehicle propulsion system and the at least one memory, wherein the at least one processor is configured to execute the instructions and cause the at least one processor to:
receive one or more simulation inputs corresponding to a simulated scene while the autonomous vehicle is within a controlled testing environment;
generate, via the vehicle propulsion system, a torque in response to the one or more simulation inputs, wherein the torque corresponds to a path of the autonomous vehicle within the simulated scene; and
receive calibration information that is based on the path of the autonomous vehicle within the simulated scene,
a navigational system that includes at least one machine learning model, wherein the navigational system is coupled to the at least one processor and wherein the at least one processor is further configured to:
train the at least one machine learning model using the calibration information,
wherein, in response to determining that the path of the autonomous vehicle is an optimal path, the at least one machine learning model is trained using the calibration information as an optimal response to the simulated scene such that the autonomous vehicle will be more likely to take a similar path when presented with similar inputs, and
wherein, in response to determining that the path of the autonomous vehicle is a sub-optimal path, the at least one machine learning model is trained using the calibration information as a sub-optimal response to the simulated scene such that the autonomous vehicle will be less likely to take a similar path when presented with similar inputs.
|