Granted Patent B2

US 12,656,137 · App. 18/759,922 · Granted Jun 16, 2026

Inventors: Cnaan Aviv (Herzliya Pituach, IL); Nisan Katz (Yaaf, IL)

Assignee: MAKE MY DAY LTD.

G01C21/3469G06Q10/047

Abstract

Claims (48)

1 . A method for planning an optimal route in an area for a trip that starts at a start time, by an electric car that comprises a rechargeable battery, from an origin point to a final point via geographical locations of target places, using time- or trip-sensitive data and non-time- or non-trip-sensitive data, the method comprising:

obtaining locations of origin and final points;

obtaining a State of Charge (SoC) of the rechargeable battery at the origin point;

obtaining a roads data that comprises a digital map of the area;

obtaining charging stations data that comprises a first list of geographical locations of charging stations in the area;

obtaining a weather data relating to the area and the start time that comprise a forecasted, estimated, or measured, temperature, a wind, a humidity, a precipitation, or any combination thereof;

obtaining a car data relating to the specific electric car that comprises an estimated or nominal battery discharging rate in reference or ideal conditions;

obtaining drag data that comprises a drag coefficient of the electric car;

obtaining number of passengers;

obtaining driver data;

obtaining the start time;

obtaining target places data that comprises a second list of geographical locations of the target places;

generating, using a Machine Learning (ML) scheme that comprises, or is based on, unsupervised clustering, the optimal route that minimizes a cost function for travelling from the origin point to the final point while visiting at least one charging station location and all target places locations, based on the roads data, the charging stations data, the weather data, the car data, the drag data, the driver data, the number of passengers; the State of Charge (SoC) of the rechargeable battery at the origin point, and the start time; and

notifying a user of the generated optimal route or guiding the electric car to navigate according to the generated optimal route,

wherein the unsupervised clustering uses, or is based on, K-Means clustering or algorithm.

2 . The method according to claim 1 , wherein the origin point and the final point are the same point.

3 . The method according to claim 1 , wherein the area comprises a country, a state, a region, a county, a city, a neighborhood, or a Zone Improvement Plan (ZIP)/postal code area.

4 . The method according to claim 1 , wherein at least one of the geographical locations in the first or second list is represented as Latitude and Longitude values, according to World Geodetic System (WGS) 84 standard, or according to Universal Transverse Mercator (UTM) zones.

5 . The method according to claim 1 , wherein at least one of the geographical locations in the first or second list is represented as a building or lot number, a street name, a city name, a country or region name, a state or country name, a Zone Improvement Plan (ZIP)/postal code, or any combination thereof.

6 . A non-transitory computer readable medium having computer executable instructions stored thereon, wherein the instructions include the steps according to claim 1 .

7 . The method according to claim 1 , wherein the cost function comprises a total optimal route travel distance, a total optimal route travel time, a total associated discharging of the battery in the electric car, a total cost associated with charging the battery in the one or more charging stations, or any combination thereof.

8 . The method according to claim 1 , wherein the generating further comprises, or is based on, using a Bayesian optimization or network methodology.

9 . The method according to claim 8 , wherein the Bayesian optimization or network methodology comprises a first, second, and third vertices graph, wherein a first vertex is associated with environmental factors, a second vertex is associated with decision nodes, and a third vertex is associated with the cost function.

10 . The method according to claim 1 , wherein the generating further comprises, or is based on, using a casual inference methodology or process.

11 . The method according to claim 10 , wherein the casual inference methodology or process uses, or is based on, Bayesian inference, Frequentist statistical inference, or any combination thereof.

12 . The method according to claim 10 , wherein the casual inference methodology or process uses, or is based on, a causal pie model (component-cause), a Pearl's structural causal model (causal diagram+do-calculus), a structural equation modeling, a Rubin causal model (potential-outcome), or any combination thereof.

13 . The method according to claim 1 , wherein the generating further comprises, or is based on, solving a Travelling Salesman Problem (TSP).

14 . The method according to claim 13 , wherein the TSP is a symmetric or asymmetric TSP.

15 . The method according to claim 13 , wherein the TSP solving comprises using an exact or a heuristic algorithm.

16 . The method according to claim 13 , wherein the TSP problem definition replaces cities with charging-stations locations and target locations.

17 . The method according to claim 1 , wherein the generating further comprises, or is based on, solving an integer Linear Programming (LP) problem.

18 . The method according to claim 17 , wherein the LP solving comprises, or is based on, the simplex algorithm.

19 . The method according to claim 17 , wherein the LP solving comprises, or is based on, using heuristic or combinatorial search method.

20 . The method according to claim 1 , wherein the generating is based on, or satisfies, a restriction of a defined low-level threshold of the battery in the electric car, so that the battery charge along the optimal route is above the defined low-level threshold.

21 . The method according to claim 20 , wherein the low-level threshold is at least 1%, 2%, 3%, 5%, 7%, 10%, 12%, 15%, 20%, 25%, or 30% of a maximum charge capacity of the battery.

22 . The method according to claim 21 , wherein the low-level threshold is less than 2%, 3%, 5%, 7%, 10%, 12%, 15%, 20%, 25%, 30%, or 35% of the maximum charge capacity of the battery.

23 . The method according to claim 22 , wherein the low-level threshold is at least 1, 2, 3, 5, 7, 10, 12, 15, or 20 KwH.

24 . The method according to claim 18 , wherein the low-level threshold is less than 2, 3, 5, 7, 10, 12, 15, 20, or 30 KwH.

25 . The method according to claim 20 , wherein the low-level threshold corresponds to an estimated travel of at least 1, 2, 3, 5, 7, 10, 12, 15, or 20 miles or Kilometers.

26 . The method according to claim 25 , wherein the low-level threshold corresponds to an estimated travel of less than 2, 3, 5, 7, 10, 12, 15, 20, or 30 miles or Kilometers.

27 . The method according to claim 1 , further comprising executing, by the electric car, the generated optimal route, by travelling along the generated optimal route or a part thereof.

28 . The method according to claim 27 , further comprising obtaining or monitoring a battery data that comprises the State of Charge (SoC), the discharging rate, or a combination thereof, of the rechargeable battery, as part of, or in response to, the executing.

29 . The method according to claim 28 , further comprising updating or adjusting the unsupervised clustering as part of the Machine Learning (ML) scheme.

30 . The method according to claim 1 , wherein the car data further comprises a car weight.

31 . The method according to claim 1 , wherein the car weight comprises a weight of a payload.

32 . The method according to claim 1 , wherein the car data comprises an estimated or measured pressure of at least one of the tires in the electric car.

33 . The method according to claim 1 , wherein the driver data comprises a style, a habit, an experience, an aggressiveness, a skill, or any combination thereof, of the driver.

34 . The method according to claim 1 , wherein the driver data comprises an age, a gender, a number of years as a driver, of any combination thereof, or wherein the driver data is based on, or uses, data of former trips of the driver.

Assignments (1)

Continuity (3)

References Cited (225)