# US 12,181,300 B2 · Systems and methods for dynamically generating optimal routes for vehicle operation management

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,181,300 B2
- Document ID: US12181300B2
- Status: Granted
- Kind: B2
- Application number: 17/895,804
- Filed: 2022-08-25
- Published: 2022-12-22
- Granted: 2024-12-31
- Earliest claimed: 2019-02-15
- Assignees: State Farm Mutual Automobile Insurance Company
- Applicants: State Farm Mutual Automobile Insurance Company
- Inventors: Aaron Williams; Ryan Michael Gross; Joseph Robert Brannan
- Web page: https://patentgrep.com/patent/US12181300B2

## CPC

- G01C 21/3492: {employing speed data or traffic data, e.g. real-time or historical (traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968)}
- B64C 39/024: {of the remote controlled vehicle type, i.e. RPV}
- G01C 21/20: Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence)
- G01C 21/3438: {Rendezvous; Ride sharing}
- G01C 21/3453: {Special cost functions, i.e. other than distance or default speed limit of road segments}
- G05D 1/00: Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots (drive control systems specially adapted for autonomous road vehicles B60W60/00)
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G05D 1/227: Handing over between remote control and on-board control; Handing over between remote control arrangements
- G06Q 10/047: Optimisation of routes or paths, e.g. travelling salesman problem
- G06Q 10/06316: {Sequencing of tasks or work}
- G06Q 10/0635: Risk analysis of enterprise or organisation activities
- G06Q 10/0639: Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q 10/08355: {Routing methods}
- G06Q 50/40: Business processes related to the transportation industry (shipping G06Q10/083)
- G08G 1/0112: {from the vehicle, e.g. floating car data [FCD]}
- G08G 1/0129: {for creating historical data or processing based on historical data}
- G08G 1/0133: {for classifying traffic situation}
- G08G 1/0145: {for active traffic flow control}
- G08G 1/096716: {where the received information does not generate an automatic action on the vehicle control}
- G08G 1/096725: {where the received information generates an automatic action on the vehicle control}
- G08G 1/096816: {where the complete route is transmitted to the vehicle at once}
- G08G 1/096844: {where the complete route is dynamically recomputed based on new data}
- G08G 1/202: {Dispatching vehicles on the basis of a location, e.g. taxi dispatching}
- H04W 4/024: Guidance services
- H04W 4/44: for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
- B64U 2101/60: for transporting passengers; for transporting goods other than weapons
- B64U 2101/64: for parcel delivery or retrieval
- B64U 2201/104: using satellite radio beacon positioning systems, e.g. GPS
- G05D 2101/10: using artificial intelligence [AI] techniques
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- B64C: AEROPLANES; HELICOPTERS
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR

## Abstract

A vehicle routing system includes a vehicle routing and analytics (VRA) computing device, one or more databases, and one or more vehicles communicatively coupled to the VRA computing device. The VRA computing device is configured to generate an optimal route for a vehicle to travel that maximizes potential revenue for operation of the vehicle, the optimal route including a schedule of a plurality of tasks, and generate analytics associated with operation of the vehicle. The VRA computing device is further configured to provide a management hub software application accessible by vehicle users associated with vehicles, tasks sources, and other users.

## Claims

### Claim 1

A vehicle routing and analytics (VRA) computing device for generating optimal routes for a vehicle, the VRA computing device comprising at least one processor in communication with a memory, wherein the at least one processor is programmed to:
retrieve availability parameters and delivery preferences associated with the vehicle;
retrieve, based in part on the vehicle definition, a plurality of known delivery tasks to be performed, each including a respective cargo to be delivered, pick-up time, delivery time, pick-up location, delivery location, and associated value;
retrieve a plurality of historical routes travelled by a plurality of vehicles including the vehicle and a plurality of completed delivery tasks completed by the plurality of vehicles during the plurality of historical routes;
using at least one of artificial intelligence and deep learning functionality:
identify one or more patterns in the plurality of historical routes and the plurality of completed delivery tasks;
identify a prospective new delivery task based upon the one or more patterns, the prospective new delivery task having a prospective pick-up location and a predicted pick-up time unrelated to any of the known delivery tasks; and
generate an optimal route for the vehicle that includes (i) a scheduled list of a subset of the known delivery tasks for the vehicle to perform, and (ii) instructions for the vehicle to travel to the prospective pick-up location the predicted pick-up time based upon a likelihood of the prospective new delivery task being associated with that prospective pick-up location at the predicted pick-up time; and
transmit the optimal route to the vehicle for operation of the vehicle according to the optimal route.

### Claim 2 (depends on 1)

The VRA computing device of claim 1, wherein the vehicle is an autonomous vehicle, and wherein the optimal route, when received by the autonomous vehicle, causes the autonomous vehicle to travel to pick-up and delivery locations associated with the subset of known delivery tasks and to the prospective pick-up location, according to the optimal route.

### Claim 3 (depends on 1)

The VRA computing device of claim 1, wherein the VRA computing device is communicatively coupled to a database that stores available delivery tasks, and wherein to retrieve the plurality of known delivery tasks to be performed, the at least one processor is further programmed to:
identify, based upon the vehicle definition, an availability radius for the vehicle, the availability radius defining a bounded geographical area to which the vehicle is available to travel and a period of time over which the vehicle is available to travel;
generate a query including the availability radius; and
transmit, to the database, the query including the availability radius, wherein the query causes the database to identify and retrieve the plurality of known delivery tasks that can be completed within the availability radius of the vehicle.

### Claim 4 (depends on 1)

The VRA computing device of claim 1, wherein the VRA computing device is communicatively coupled to a database that stores vehicle availability parameters and delivery preference, including, for each respective vehicle, a period of time over which the vehicle is available to complete delivery tasks, a geographic range over which the vehicle is available to complete delivery tasks, cargo preferences set by the associated vehicle user, a capacity of the vehicle for cargo including persons, a capacity of the vehicle for cargo including objects, a make of the vehicle, a model of the vehicle, a manufacturing year of the vehicle, an identifier of the vehicle, a vehicle type, vehicle features, a vehicle class, current vehicle location, current vehicle capacity, a performance rating for the vehicle, and historical claim data for the vehicle.

### Claim 5 (depends on 1)

The VRA computing device of claim 1, wherein the at least one processor is further programmed to:
identify, from the identified patterns, at least one underserved location that has fewer than a threshold numbers of completed delivery tasks associated therewith; and
generate the optimal route to prioritize delivery tasks associated with the underserved location.

### Claim 6 (depends on 1)

The VRA computing device of claim 1, wherein the at least one processor is further configured to:
identify, from the identified patterns, a lull period of time over which the plurality of vehicles completed a lowest number of completed delivery tasks;
generate a service schedule including one or more services associated with the vehicle, a respective service time associated with each service, and a respective service vendor associated with each service, wherein each service time is within the lull period of time; and
transmit the service schedule to the vehicle for operation of the vehicle according to the service schedule.

### Claim 7 (depends on 6)

The VRA computing device of claim 6, wherein the vehicle is an autonomous vehicle, and wherein the service schedule, when received by the autonomous vehicle, causes the autonomous vehicle to travel to locations associated with the respective service vendors according to the service schedule.

### Claim 8 (depends on 1)

The VRA computing device of claim 1, wherein the at least one processor is further programmed to:
identify a first event occurring at the prospective pick-up location at the predicted pick-up time, wherein the first event is predicted to be associated with a plurality of prospective new event delivery tasks, wherein generating the optimal route includes scheduling operation of the vehicle at the prospective pick-up location at the predicted pick-up time to make the vehicle available to accommodate at least one prospective new event delivery task.

### Claim 9 (depends on 1)

The VRA computing device of claim 1, wherein the delivery preferences for the vehicle include a person-only cargo preference, wherein the at least one processor is further programmed to:
filter the plurality of known delivery tasks based upon the person-only cargo preference to identify a plurality of person-only cargo delivery tasks from the plurality of delivery tasks; and
generate the optimal route for the vehicle that includes the scheduled list of a subset of the plurality of person-only cargo delivery tasks for the vehicle to perform.

### Claim 10 (depends on 9)

The VRA computing device of claim 9, wherein the vehicle includes a first vehicle and the optimal route includes a first optimal route, and wherein the at least one processor is further programmed to:
identify a second vehicle operating according to a second optimal route, wherein the second vehicle is not associated with include the person-only cargo preference and operates within an availability radius similar to an availability radius of the first vehicle;
compare a predicted revenue associated with the second optimal route to a predicted revenue associated with the first optimal route;
calculate, based upon the comparing, a predicted loss associated with the first optimal route; and
transmit, to a vehicle user associated with the first vehicle, a recommendation message including the predicted loss and a recommendation that the vehicle user remove the person-only cargo preference.

### Claim 11 (depends on 1)

The VRA computing device of claim 1, wherein the delivery preferences for the vehicle include an object-only cargo preference, wherein the at least one processor is further programmed to:
filter the plurality of known delivery tasks based upon the object-only cargo preference to identify a plurality of object-only cargo delivery tasks from the plurality of delivery tasks; and
generate the optimal route for the vehicle that includes the scheduled list of a subset of the plurality of object-only cargo delivery tasks for the vehicle to perform.

### Claim 12 (depends on 11)

The VRA computing device of claim 11, wherein the vehicle includes a first vehicle and the optimal route includes a first optimal route, and wherein the at least one processor is further programmed to:
identify a second vehicle operating according to a second optimal route, wherein the second vehicle is not associated with the object-only cargo preference and operates within an availability radius similar to an availability radius of the first vehicle;
compare a predicted revenue associated with the second optimal route to a predicted revenue associated with the first optimal route;
calculate, based upon the comparing, a predicted loss associated with the first optimal route; and
transmit, to a vehicle user associated with the first vehicle, a recommendation message including the predicted loss and a recommendation that the vehicle user remove the object-only cargo preference.

### Claim 13 (depends on 1)

The VRA computing device of claim 1, wherein the vehicle includes a first vehicle having a first availability radius for the first vehicle that defines a bounded geographical area to which the first vehicle is available to travel and a period of time over which the first vehicle is available to travel, wherein the at least one processor is further programmed to:
identify a first known delivery task that extends beyond the first availability radius of the first vehicle;
retrieve availability parameters of other vehicles than the first vehicle that operate within a respective availability radius adjacent to the first availability radius;
select a second vehicle from the other vehicles having a second availability radius adjacent to the first availability radius;
generate the optimal route for the first vehicle to include a first optimal route and a second optimal route, wherein the first optimal route includes a first portion of the first delivery task, and wherein the first optimal route schedules the first vehicle to pick up cargo associated with the first delivery task at the pick-up location associated with the first delivery task and to drop off the cargo at the second vehicle at a second location between the pick-up location and the delivery location associated with the first delivery task;
generate the second optimal route for the second vehicle that includes a second portion of the first delivery task, wherein the second optimal route schedules the second vehicle to pick up the cargo associated with the first delivery task from the first vehicle at the second location and to drop off the cargo at one of (i) the delivery location associated with the first delivery task, or (ii) a third vehicle at a third location between the second location and the delivery location associated with the first delivery task; and
transmit the first optimal route to the first vehicle and the second optimal route to the second vehicle.

### Claim 14 (depends on 13)

The VRA computing device of claim 13, wherein the first and second vehicles are autonomous vehicles, wherein the first optimal route, when received by the first autonomous vehicle, causes the first autonomous vehicle to travel to the pick-up location and the second location associated with the first portion of the first delivery task according to the first optimal route, and wherein the second optimal route, when received the second autonomous vehicle, causes the second autonomous vehicle to travel to the second location and the one of (i) the delivery location, or (ii) the third location associated with the second portion of the first delivery task according to the second optimal route.

### Claim 15 (depends on 14)

The VRA computing device of claim 14, wherein the first optimal route further causes the first autonomous vehicle to arrive at the second location at a predetermined time, and wherein the second optimal route causes the second autonomous vehicle to arrive at the second location at substantially the same predetermined time.

### Claim 16 (depends on 1)

The VRA computing device of claim 1, wherein the one or more patterns include repeated completed delivery tasks with a daily, weekly, work-weekly, weekend, monthly, yearly, or seasonal periodicity.

### Claim 17

A computer-implemented method for generating optimal routes for a vehicle to travel that maximizes potential revenue for operation of the vehicle, the method implemented by a vehicle routing and analytics (VRA) computing device including at least one processor, the method comprising:
retrieving availability parameters and delivery preferences associated with the vehicle;
retrieving, based in part on the vehicle definition, a plurality of known delivery tasks to be performed, each including a respective cargo to be delivered, pick-up time, delivery time, pick-up location, delivery location, and associated value;
retrieving a plurality of historical routes travelled by a plurality of vehicles including the vehicle and a plurality of completed delivery tasks completed by the plurality of vehicles during the plurality of historical routes;
using at least one of artificial intelligence and deep learning functionality:
identifying one or more patterns in the plurality of historical routes and the plurality of completed delivery tasks;
identifying a prospective new delivery task based upon the one or more patterns, the prospective new delivery task having a prospective pick-up location and a predicted pick-up time unrelated to any of the known delivery tasks; and
generating an optimal route for the vehicle that includes (i) a scheduled list of a subset of the known delivery tasks for the vehicle to perform, and (ii) instructions for the vehicle to travel to the prospective pick-up location at the predicted pick-up time based upon a likelihood of the prospective new delivery task being associated with that prospective pick-up location at the predicted pick-up time; and
transmitting the optimal route to the vehicle for operation of the vehicle according to the optimal route.

### Claim 18 (depends on 17)

The computer-implemented method of claim 17, further comprising:
identifying, from the identified patterns, at least one underserved location that has fewer than a threshold numbers of completed delivery tasks associated therewith; and
generating the optimal route to prioritize delivery tasks associated with the underserved location.

### Claim 19 (depends on 17)

The computer-implemented method of claim 17, further comprising:
identifying, from the identified patterns, a lull period of time over which the plurality of vehicles completed a lowest number of completed delivery tasks;
generating a service schedule including one or more services associated with the vehicle, a respective service time associated with each service, and a respective service vendor associated with each service, wherein each service time is within the lull period of time; and
transmitting the service schedule to the vehicle for operation of the vehicle according to the service schedule.

### Claim 20 (depends on 17)

The computer-implemented method of claim 17, further comprising:
identifying a first event occurring at the prospective pick-up location at the predicted pick-up time, wherein the first event is predicted to be associated with a plurality of prospective new event delivery tasks,
wherein generating the optimal route includes scheduling operation of the vehicle at the prospective pick-up location at the predicted pick-up time to make the vehicle available to accommodate at least one prospective new event delivery task.