Intelligent engine activation planner
A method for planning an activation action for an engine of a vehicle is disclosed. The method includes planning, according to a model, an activation action of an engine of a vehicle, and activating the engine according to the activation action. The model includes a state space comprising a current charge level of the battery and whether the engine is currently on or off. The activation action is selected from a set comprising a first action to turn on the engine to charge the battery and a second action to turn off the engine.
1. A method, comprising:
planning, according to a model, an activation action of an engine of a vehicle,
wherein the model includes a state space comprising a current charge level of a battery, a navigation map, and whether the engine is currently on or off, and
wherein the activation action is selected from a set comprising a first action to turn on the engine to charge the battery and a second action to turn off the engine;
utilizing learned historic driving patterns included in the navigation map in determining whether to select the first action or the second action; and
activating the engine according to the activation action.
2. The method of claim 1 , wherein planning, according to the model, the activation action of the engine comprises:
selecting the second action when the vehicle enters an area where noise is undesirable.
3. The method of claim 1 , wherein the model follows hard-coded rules.
4. The method of claim 1 , wherein the navigation map includes a current road segment of the vehicle.
5. The method of claim 4 , wherein planning, according to the model, the activation action of the engine comprises:
planning the activation action based on an objective, wherein the objective is to minimize energy consumption of the vehicle.
6. The method of claim 4 , wherein planning, according to the model, the activation action of the engine comprises:
planning the activation action based on an objective, wherein the objective is to minimize a number of times that the engine is toggled.
7. The method of claim 4 , wherein the state space further comprises whether a power-consuming component of the vehicle is on or off.
8. The method of claim 4 , wherein the model employs a cost function including one or more costs, wherein the one or more costs are associated with the activation action of the engine, wherein the costs comprise at least one of:
an expected energy expenditure cost;
an expected wasted energy cost;
an expected cost of the engine switching; or
an extra noise generated if the engine is activated.
9. The method of claim 4 , wherein the model includes a transition function that uses a traffic information from the navigation map.
10. The method of claim 4 , wherein the model includes a transition function comprising at least one of a movement in edges of the navigation map, a battery change function, and a change in engine status based on the navigation map and a performed activation action.
11. A device for charging a battery of a vehicle by an engine comprising:
a memory; and
a processor, the processor configured to:
obtain an activation action from an action space, wherein the action space comprises a first activation action of turning the engine on and a second activation action of turning the engine off, and wherein obtaining the activation action from the action space comprises using a navigation map storing learned driving patterns specific to the vehicle; and
activate the engine according to the activation action, wherein activating the engine using the first activation action causes the engine to turn on to charge the battery of the vehicle.
12. The device of claim 11 , wherein the second activation action is obtained as the activation action when the vehicle enters an area where noise is undesirable.
13. The device of claim 11 , wherein obtaining the activation action from the action space comprises using a cost function including one or more costs, wherein the one or more costs are associated with the activation action, wherein the costs comprise at least one of:
an expected energy expenditure cost;
an expected wasted energy cost;
an expected cost of the engine switching; or
an extra noise generated if the engine is activated;
second component indicating a predefined engine activation based on a range of a state of charge of the battery.
14. The device of claim 11 , wherein obtaining the activation action from the action space comprises using a state transition function including a first component indicating how a location of the vehicle changes stochastically following a topological graph of edges formed by various road segments connecting start nodes to end nodes of the navigation map.
15. A vehicle comprising:
a battery;
an engine; and
a processor configured to:
determine, based on one or more objectives, an activation action of the engine of the vehicle,
wherein the activation action is selected from a set comprising a first activation action of turning the engine on and a second activation action of turning the engine off,
wherein the battery of the vehicle is charged by the engine when the engine is turned on,
wherein the activation action comprises taking a scalarization function of at least the one or more objectives and a battery level; and
activate the engine according to the determination of the activation action.
16. The vehicle of claim 15 , wherein the one or more objectives are based on at least one of an energy expenditure of the engine, a wasted energy, and an extra noise generated by the engine.
17. The vehicle of claim 15 , wherein the one or more objectives comprise minimizing, over time, a total energy consumption of the engine.