Robotic process automation system trained to undertake actions with a vehicle based on user interactions with a user interface of the vehicle
A method of operating a vehicle in a transportation system includes: receiving data collected for each of a set of users based on interactions of the set of users with a user interface of the vehicle including at least one of a vehicle data system, a vision system, and a connected system; performing robotic process automation on the interactions; learning changes in driving style using an artificial intelligence system based on the robotic process automation; and undertaking an action within the vehicle on behalf of the user based on the learned changes in driving style.
1. A method of operating a vehicle in a transportation system, the method comprising:
receiving data collected for each of a set of users based on interactions of the set of users with a user interface of the vehicle including at least one of a vehicle data system, a vision system, and a connected system;
performing robotic process automation on the interactions to learn a driving style for at least one user of the set of users;
learning changes in the driving style using an artificial intelligence system based on the robotic process automation and based on feedback of the robotic process automation; and
optimizing a margin of safety and controlling the vehicle with the optimized margin of safety on behalf of the at least one user of the set of users based on the learned changes in the driving style, wherein the optimizing and the controlling affect at least one of: a route of the vehicle, a speed of the vehicle, an acceleration of the vehicle, a deceleration of the vehicle, a proximity to other vehicles along the route of the vehicle, a proximity to objects along the route of the vehicle, braking intensity, steering sensitivity, or route selection.
2. The method of claim 1 , wherein the data collected for each of the set of users includes at least one of: driving speed, braking patterns, steering patterns, or route preferences.
3. The method of claim 1 , wherein the artificial intelligence system is further trained using data from external sources including at least one of: traffic data, weather data, or road condition data.
4. The method of claim 1 , wherein the artificial intelligence system uses machine learning algorithms to learn the changes in the driving style.
5. The method of claim 1 , wherein the user interface of the vehicle includes at least one of: a touch screen display, voice recognition system, or a gesture recognition system.
6. The method of claim 1 , wherein the learned changes in the driving style are stored in at least one user profile associated with the at least one user of the set of users.
7. The method of claim 1 , wherein a robotic process automation system provides audio or visual feedback to the at least one user regarding the learned changes in the driving style.
8. The method of claim 1 , wherein an action undertaken within the vehicle during the optimizing and the controlling is based on real-time data collected during a current driving session.
9. The method of claim 1 , wherein the artificial intelligence system is further trained to predict future changes in the driving style based on historical data.
10. A method of robotic process automation to facilitate mimicking human operation of a vehicle, the method comprising:
tracking human interactions with a vehicle control-facilitating interface;
recording the tracked human interactions in a robotic process automation training data structure;
tracking vehicle operational state information of the vehicle, wherein the vehicle is controlled through the vehicle control-facilitating interface;
recording the vehicle operational state information in the robotic process automation training data structure;
training, through use of at least one neural network, an artificial intelligence system to operate the vehicle in a manner consistent with the human interactions based on the human interactions and the vehicle operational state information in the robotic process automation training data structure and based on feedback obtained from the robotic process automation training data structure,
wherein the training of the artificial intelligence system further involves training the artificial intelligence system to optimize a margin of safety and to control the vehicle on behalf of a user of the vehicle, wherein the optimizing and the controlling affect at least one of: a route of the vehicle, a speed of the vehicle, an acceleration of the vehicle, a deceleration of the vehicle, a proximity to other vehicles along the route of the vehicle, a proximity to objects along the route of the vehicle, braking intensity, steering sensitivity, or route selection; and
controlling, via the trained artificial intelligence system, the vehicle with the optimized margin of safety.
11. The method of claim 10 , wherein the human interactions with the vehicle control-facilitating interface include at least one of: steering inputs, braking inputs, acceleration inputs, or route selection inputs.
12. The method of claim 10 , wherein the vehicle operational state information includes at least one of: the speed of the vehicle, a location of the vehicle, a direction of the vehicle, a fuel level of the vehicle, or a battery level of the vehicle.
13. The method of claim 10 , wherein the at least one neural network is a deep learning neural network.
14. The method of claim 10 , wherein the vehicle control-facilitating interface includes at least one of: a touch screen display, a steering wheel, a brake pedal, an accelerator pedal, or a navigation system.
15. The method of claim 10 , wherein the robotic process automation training data structure is stored in a non-transitory computer-readable medium.
16. The method of claim 10 , wherein the training of the artificial intelligence system further includes reinforcement learning based on the feedback.
17. The method of claim 10 , further comprising providing a user interface that allows a human operator to override operation of the vehicle by the artificial intelligence system.
18. The method of claim 10 , wherein the vehicle is a self-driving vehicle and the human interactions are simulated based on data from a database of human driving behavior.