Granted Patent B2

US 12,523,481 · App. 18/182,742 · Granted Jan 13, 2026

Inventors: Kyle Hollins Wray (Fremont, CA); Liam Pedersen (San Francisco, CA); Richard Lui (Sunnyvale, CA); Christopher Ostafew (Mountain View, CA)

Assignee: Nissan North America, Inc.

G01C21/3469B60W10/06B60W20/12B60W20/17B60W20/40B60W30/18127B60W50/14G01C21/3407G01C21/3492G01C21/3685B60W2050/146B60W2510/244B60W2556/10

Abstract

Claims (53)

1 . A method of route planning for a hybrid electric vehicle (HEV), comprising:

obtaining respective engine activation actions for at least some road segments of a route between an origin and a destination by optimizing 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;

controlling the HEV to follow the at least some of the road segments of the route and to activate the engine according to the respective engine activation actions;

updating vehicle parameters of the HEV so that patterns of drivers of the HEV are tracked, wherein controlling the HEV to follow the at least some of the road segments comprises:

anticipating upcoming road segments, based on the vehicle parameters, that will result in regenerative energy being produced that charge the battery, and maintaining the engine in an off position or turning off the engine so that the regenerative energy is captured and the regenerative energy is not wasted;

tracking historical driver behavior patterns, for a single driver, over multiple trips and changing the engine activation actions based on the historical driver patterns of the single driver to further control the energy consumption so that the regenerative energy is not wasted for the single driver;

planning the engine activation actions, with an engine activation planner, for each possible route that could arise, even if the route is not known, in the upcoming road segments as the vehicle travels along a current road segment; and

refining the engine activation actions based on a current position of the vehicle so that the engine activation actions are a customized optimization based upon anticipation of the upcoming road segments to control the engine activation to not waste the regenerative energy.

2 . The method of claim 1 , wherein the route is obtained using engine activation rules that include maintaining homeostasis within a range.

3 . The method of claim 1 , wherein the respective engine activation actions are obtained based on a model that uses a navigation map, the current road segment of the HEV, a current charge level of the battery, and whether the engine is currently on or off.

4 . The method of claim 3 , wherein the navigation map was learned from Global Positioning System (GPS) traces and includes topological road structures and at least one of battery consumptions, battery regenerations, or ambient noises.

5 . The method of claim 3 , wherein the navigation map includes the patterns of the drivers, wherein the patterns of the drivers are determined from a least one of the patterns of a driver of the HEV or an aggregated pattern of several vehicles.

6 . The method of claim 1 , further comprising:

receiving, from a driver of the HEV, an optimization criteria for the route, wherein the optimization criteria relates to at least one of the noise level or the energy consumption.

7 . The method of claim 1 , wherein the route is optimized using a single value, the single value representing a combination of expected costs with respect to time, the noise level, and a battery charge 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 time, the noise level, or battery charge level.

9 . The method of claim 1 , wherein obtaining the route between the origin and the destination comprises:

in anticipation of upcoming road segments resulting in the regenerative energy that charges the battery, not turning on the engine.

10 . The method of claim 9 , wherein the upcoming road segments resulting in the regenerative energy include at least one of a traffic light, a stop sign, a downhill, an intersection, a merge on a freeway, a curve on a freeway, or a freeway exit.

11 . The method of claim 9 , further comprising:

displaying, on a display of the HEV, an indication of at least one of the upcoming road segments that results in the regenerative energy;

receiving, from a driver of the HEV, an input relating to the at least one of the upcoming road segments resulting in the regenerative energy; and

controlling the HEV based on the input of the driver of the HEV.

12 . The method of claim 1 , wherein obtaining the route between the origin and the destination comprises:

in anticipation of a hill, calculating a policy to turn the engine on while going up the hill such that the battery is relatively discharged by a time the HEV is going down the hill so that energy is captured for regeneration.

13 . An apparatus for driver assistance in a hybrid electric vehicle (HEV), comprising:

a battery;

an engine; and

a processor, the processor configured to configured to:

update vehicle parameters based on patterns of drivers of the vehicle, the patterns of the drivers obtained from a vehicle model learner;

determine, when a driver assistance feature of the HEV is enabled and a destination of the HEV is not known, a next road segment and an engine activation action, wherein the next road segment is a successor road to a current road segment as the vehicle travels from an origin to the destination;

plan the engine activation action using a cost function that represents an expected immediate cost of performing the engine activation action;

in response to the HEV following the next road segment, 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;

anticipate upcoming road segments, based on the vehicle parameters, that will result in regenerative energy being produced that charge the battery and maintain the engine off or turn off the engine so that the regenerative energy is captured and the regenerative energy is not wasted;

track historical driver behavior patterns, for a single driver, over multiple trips and changing the engine activation actions based on the historical driver patterns of the single driver to further control energy consumption so that the regenerative energy is not wasted for the single driver;

plan the engine activation actions, with an engine activation planner, for each possible route that could arise, even if a route is not known, as the vehicle travels along the current road segment; and

refining the engine activation actions based on a current position of the vehicle so that the engine activation actions are a customized optimization based upon anticipation of the upcoming road segments to control the engine activation to not waste the regenerative energy.

14 . The apparatus of claim 13 , wherein the engine activation action is determined based on the current road segment of the HEV, a current charge level of the battery, and whether the engine is currently on or off.

15 . 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 respective engine activation actions for at least some road segments of a route between an origin and a destination by optimizing 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;

controlling the HEV to follow the at least some of the road segments of the route and to activate the engine according to the respective engine activation actions;

updating vehicle parameters so that patterns of drivers of the HEV are tracked, wherein controlling the HEV to follow the at least some of the road segments comprises:

anticipating upcoming road segments, based on the vehicle parameters, that will result in regenerative energy being produced that charge the battery, maintaining the engine off or turning off the engine so that the regenerative energy is captured and the regenerative energy is not wasted;

track historical driver behavior patterns, for a single driver, over multiple trips and changing the engine activation actions based on the historical driver patterns of the single driver to further control the energy consumption so that the regenerative energy is not wasted for the single driver;

plan the engine activation actions, with an engine activation planner, for each possible route that could arise, even if the route is not known, as the vehicle travels along a current road segment; and

refine the engine activation actions based on a current position of the vehicle so that the engine activation actions are a customized optimization based upon anticipation of the upcoming road segments to control the engine activation to not waste the regenerative energy.

16 . The non-transitory computer-readable storage medium of claim 15 , wherein the respective engine activation actions are obtained based on a model that uses the patterns of the drivers that correspond to at least some of the vehicle parameters collected from the HEV.

17 . The non-transitory computer-readable storage medium of claim 16 , wherein the destination is determined according to a learned topological graph of a navigation map.

18 . The non-transitory computer-readable storage medium of claim 15 , wherein the respective engine activation actions are based on at least one of road conditions, the HEV, or a driving style of a driver of the HEV.

19 . The non-transitory computer-readable storage medium of claim 15 , wherein the route is optimized by minimizing an objective related to a battery charge level constrained by at least one of time, the noise level, or the battery charge level.

20 . The method of claim 1 , further comprising:

determining, with a navigation map learner, an average battery consumption/regeneration of a road segment that is traversed multiple times and

determining edges within the road segment where the HEV stopped.

Assignments (2)

Continuity (2)

References Cited (54)

Cited By (1)

US 12,703,267