Route planner optimization for hybrid-electric vehicles
Route planning for a hybrid electric vehicle (HEV) includes obtaining a route between an origin and a destination, where the route is optimized for at least one of a noise level or energy consumption of an engine of the HEV that is used to charge a battery of the HEV, and where the route comprises respective engine activation actions for at least some segments of the route; and controlling the HEV to follow the segments of the route and to activate the engine according to the respective engine activation actions.
1. A method of route planning for a hybrid electric vehicle (HEV), comprising:
obtaining a route between an origin and a destination,
wherein the route is optimized for at least one of a noise level or energy consumption of an engine of the HEV that is used to charge a battery of the HEV,
wherein the route is obtained using a model that maps current states of a state space to actions of an action space according to a policy,
wherein obtaining the route includes obtaining respective engine activation actions for at least some segments of the route,
wherein the policy provides an engine activation action for a next road segment subsequent to a current road segment given a current state, and
wherein the current state includes whether an entertainment system of the HEV is turned on and the action includes to increase a volume of the entertainment system to mask an action of activating the engine; and
controlling the HEV to follow the segments of the route and to activate the engine according to the respective engine activation actions.
2. The method of claim 1 , wherein the route is obtained using engine activation rules comprising maintaining homeostasis within a range.
3. The method of claim 1 , wherein the model is a multi-objective stochastic shortest path (MOSSP).
4. The method of claim 3 , wherein the state space further includes a navigation map that includes the current road segment of the HEV, a current charge level of the battery, and whether the engine is currently on or off.
5. The method of claim 1 , wherein the destination is determined stochastically.
6. The method of claim 1 , further comprising:
receiving, from a driver of the HEV, an optimization criterion for the route, wherein the optimization criterion relates to one the noise level or the energy consumption.
7. The method of claim 1 , wherein the route is optimized using a scalarization function of time, the noise level, and a battery level.
8. The method of claim 1 , wherein the route is optimized by minimizing an objective related to time constrained by at least one of noise level or battery level.
9. The method of claim 1 , wherein the route is optimized by minimizing an objective related to battery level constrained by at least one of time or the noise level.
10. The method of claim 1 , wherein the route is optimized by minimizing an objective related to noise level constrained by at least one of time or battery level.
11. The method of claim 1 , wherein obtaining the route between the origin and the destination comprises:
in anticipation of upcoming road segments resulting in regenerative energy that charges the battery, not turning on the engine.
12. An apparatus for driver assistance in a hybrid electric vehicle (HEV), comprising:
a battery;
an engine; and
a processor configured to:
when a driver assistance feature of the HEV is enabled and a destination of the HEV is not known, determine, using a policy of a Markov decision process a next road segment subsequent to a current road segment for the HEV and an engine activation action,
wherein the policy maps states to actions,
wherein a current state of the states includes the current road segment,
wherein an action of the actions includes the next road segment and the engine activation action,
wherein the Markov decision process uses a cost function that represents an expected immediate cost of performing the engine activation action in the current state, and
wherein the cost function includes a determination of at least one of a wasted energy indicating an amount of energy regenerated beyond a capacity of the battery on, or
a toggling of the engine between an off state and an on state; and
in response to the next road segment being followed by the HEV, activate the engine according to the engine activation action, wherein the engine 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, and the first activation action causes the engine to turn on to charge the battery of the HEV.
13. The apparatus of claim 12 , wherein the state further includes a navigation map including the current road segment of the HEV, a current charge level of the battery, and whether the engine is currently on or off.
14. A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations for route planning in a hybrid electric vehicle (HEV), comprising:
obtaining a route between an origin and a destination,
wherein the route is optimized for at least one of a noise level or energy consumption of an engine of the HEV that is used to charge a battery of the HEV,
wherein the route is obtained using a model that maps current states of a state space to actions of an action space according to a policy,
wherein obtaining the route includes obtaining respective engine activation actions for at least some segments of the route,
wherein the policy provides an engine activation action for a next road segment subsequent to a current road segment given a current state, and
wherein the current state includes whether an entertainment system of the HEV is turned on and the action includes to increase a volume of the entertainment system to mask an action of activating the engine; and
controlling the HEV to follow the segments of the route and to activate the engine according to the respective engine activation actions.
15. The non-transitory computer-readable storage medium of claim 14 , wherein the route is obtained using engine activation rules comprising maintaining homeostasis within a range.
16. The non-transitory computer-readable storage medium of claim 14 , wherein the state space further includes a navigation map that includes the current road segment of the HEV, a current charge level of the battery, and whether the engine is currently on or off.
17. The non-transitory computer-readable storage medium of claim 14 , wherein the operations further comprise:
receiving, from a driver of the HEV, an optimization criterion for the route, wherein the optimization criterion relates to one the noise level or the energy consumption.
18. The non-transitory computer-readable storage medium of claim 14 , wherein the route is optimized by minimizing an objective related to battery level constrained by at least one of time or the noise level.
19. The non-transitory computer-readable storage medium of claim 14 , wherein the route is optimized by minimizing an objective related to noise level constrained by at least one of time or battery level.
20. The non-transitory computer-readable storage medium of claim 14 , wherein obtaining the route between the origin and the destination comprises:
in anticipation of upcoming road segments resulting in regenerative energy that charges the battery, not turning on the engine.