WO2020140899A1

WO2020140899A1 - In-vehicle personalized route selection and planning

Info

Publication number: WO2020140899A1
Application number: PCT/CN2019/130618
Authority: WO
Inventors: Evan STALTER; Fei Xiao; Xiao Liu; Fangming YE
Original assignee: Byton Limited
Priority date: 2019-01-04
Filing date: 2019-12-31
Publication date: 2020-07-09

Abstract

In-vehicle personalized route selection and planning are disclosed for a vehicle mapping application. The mapping application (407) can provide route selection and planning that considers autonomous driving (AD) routing and and/or identifying points of interest specific to a particular a user along the way of the routes while reducing travel time and distance. The points of interest can be recommended using machine learning techniques such as content-based recommendation or collaborative filtering. AD routing can maximize a proportion of AD driving time or distance on roads considered or favorable for AD driving. Each user of a vehicle can have personalized routing service in which points of interest can be identified on a map between locations, e.g., restaurants, bars, hotels, theatres, shopping centers, and etc.

Description

IN-VEHICLE PERSONALIZED ROUTE SELECTION AND PLANNING

FIELD

Embodiments and examples of the invention are generally in the field of vehicles and vehicle data processing systems. More particularly, embodiments and examples of the invention relate to in-vehicle personalized route selection and planning.

BACKGROUND

Vehicles (electric, non-electric or hybrid vehicles) can have mapping applications that allow a user to obtain directions from a start location to a destination. Existing vehicle mapping applications, however, are not geared specifically for a particular user or vehicle type. For instance, one vehicle type is an autonomous driving (AD) vehicle that is capable of sensing its environment and driving the vehicle with minimum or no user input. Existing AD technology and AD technology in the foreseeable future tend to be limited in their capacity. Specifically, such AD technology can well only in specific driving conditions or circumstances, e.g., for parking, for specific routes (e.g., buses) or for driving on interstates, freeways, expressways, principal arterial roads and the like. For routing, however, current AD technology relies on vehicle mapping applications that are limited in its capabilities. For example, current mapping applications allow a user to input a start location and destination and the mapping applications provide directions or routes based solely on the shortest distance or fastest time to reach the destination.

SUMMARY

Embodiments and examples of in-vehicle personalized route selection and planning are disclosed. For example, a mapping application for a vehicle provides personalized route selection and planning that considers maximizing a proportion of a journey in time or distance for the vehicle to be on routes considered or favorable in autonomous driving (AD) mode and/or identifying points of interest of a user along the way while reducing travel time and distance. In this way, a user of a vehicle can have personalized routing service and enjoy points of interest, which can be visited between locations such as, e.g., restaurants, bars, hotels, theatres, shopping centers, etc. Adding points of interest specific to a user in a mapping application can thus aid in the enjoyment of driving trips for a user and, in particular, long trips which may require multiple stops or breaks.

For one example, a vehicle data processing system includes a display within a vehicle and an on-board computer coupled to the display. The on-board computer provides a mapping application on the display, and the mapping application receives inputs of a start location and one or more destinations for obtaining directions for a user in which the user can select intermediary destinations on the way to a final destination. The on-board computer processes the received inputs of the start location and the one or more destinations to obtain one or more routes for AD routing that maximize a proportion of autonomous driving (AD) driving in either time or distance on roads considered or favorable for AD driving. The on-board computer provides directions for the mapping application to display the one or more routes. AD routing can consider factors such as AD driving on interstates, freeways, expressways and principal arterial roads. AD routing can also consider factors such as varying vehicle types, AD driving mode capabilities of the vehicle, driving area and surrounding municipalities and road types. The mapping application provides a user interface to allow a user to select an option for AD routing directions.

For another example, the mapping application can receive inputs to obtain directions for routes between locations and display those routes along with points of interest specific to a user that may fall or be close to the routes. The on-board computer of the vehicle can be coupled to a cloud-based system which can use machine-learning techniques (e.g., content based recommendation or collaborative filtering) to provide personalized routing and recommendation services that identify points of interest for the mapping application. The mapping application can also receive advertisements from the routing and recommendation services related to points of interests and display those advertisements while traveling between locations. The points of interest can be favorite location or frequently visited places, which are stored and maintained in a user database. The mapping application can allow a user to selectively choose options for the mapping application to provide AD routing, points of interests or advertisements when obtaining directions for planning a trip between locations.

Other devices, systems, methods and computer-readable mediums for autonomous driving route selection and planning are described.

BRIEF DESCRIPTION OF THE DRAWINGS

The appended drawings illustrate examples and are, therefore, exemplary embodiments and not considered to be limiting in scope.

FIG. 1A illustrates one example of a vehicle environment showing a vehicle coupled to a cloud capable of providing personalized routing and recommendation services for a mapping application of the vehicle.

FIG. 1B illustrates one example of a network topology for the vehicle of FIG. 1A.

FIG. 2 illustrates one example interior control environment of a vehicle showing a mapping application interface.

FIG. 3 illustrates one example block diagram of an on-board computer which can implement a data processing or computing system architecture.

FIG. 4 illustrates one example of a block diagram of a routing and recommendation service system for a mapping application of a vehicle.

FIG. 5 illustrates one example of a database for the routing and recommendation service system of FIG. 4.

FIGS. 6A-6D illustrates exemplary tables for multiple users of a vehicle.

FIG. 7A illustrates one example flow diagram of a recommendation service operation.

FIG. 7B illustrates one example flow diagram of a routing service operation.

FIGS. 8A-8C illustrates example flow diagrams of operations to perform recommendation score calculations.

FIG. 9A illustrates one example of a map graph having nodes with variables representing scores for points of interests and autonomous driving (AD) routing.

FIG. 9B illustrates one example of a minimization operation to determine a recommended route.

FIGS. 10A-10D illustrates exemplary user interfaces for a mapping application to provide options AD routing, points of interest recommendations, or advertisements.

FIGS. 11A-11D illustrates exemplary maps for a mapping application showing AD routing, points of interest and advertisements.

DETAILED DESCRIPTION

In-vehicle personalized route selection and planning are described for a mapping application. The mapping application can provide personalized route selection and planning that considers maximizing a proportion of time or distance for a vehicle to be on roads considered or favorable for AD driving from one user-selected location to another and/or identifying points of interest of the user along the way of the routes while reducing travel time and distance. Each user of a vehicle can have a personalized routing service in which points of interest can be identified on a map between locations, e.g., restaurants, bars, hotels, theatres, shopping centers, etc., which are specific and personalized to the user.

For one example, a vehicle with autonomous driving (AD) capability includes an on-board computer to run or implement a mapping application on a display of the vehicle. In obtaining directions from one location to another, the user can request AD routing including directions from the mapping application to maximize a proportion of driving time or distance on roads considered or favorable for AD driving. For example, a vehicle with AD capabilities may be able to drive in AD mode when on interstates, freeways, expressways and principal arterial roads, or the like, but may not be able to so for other types of roads such as city streets or alleys. In another example, the user can request the mapping application to obtain directions for routes between locations and display those routes along with points of interest specific to a user that may fall on or be close to the routes. Such a mapping application can aid in enhancing the user’s driving experience by maximizing a proportion of time or distance on roads considered or favorable for AD driving and identifying and displaying points of interest specific to the user.

For one example, the on-board computer of the vehicle can be coupled to a cloud-based system providing routing and recommendation services identifying the points of interest for the mapping application. The mapping application can also receive advertisements from points of interest and display those advertisements while driving between locations for the user. The points of interest can be a favorite location or frequently visited place by a user, which can be stored and maintained in a database. As detailed herein, the mapping application can provide user interfaces to allow a user to selectively choose options for providing AD routing, points of interests and/or advertisements when obtaining directions for planning a trip and traveling between locations.

As set forth herein, various embodiments, examples and aspects will be described with reference to details discussed below, and the accompanying drawings will illustrate various embodiments and examples. The following description and drawings are illustrative and are not to be construed as limiting. Numerous specific details are described to provide a thorough understanding of various embodiments and examples. However, in certain instances, well-known or conventional details are not described in order to provide a concise discussion of the embodiments and examples.

Exemplary Vehicle with Personalized Routing and Recommendation Services

FIG. 1A illustrates one example of a vehicle environment 100 showing a vehicle 110 coupled to a cloud-based system (cloud) 117 capable of providing personalized routing and

recommendation services

120 and 121 for mapping application 107 of vehicle 110. For the example of FIG. 1A, vehicle 110 is shown as an electric vehicle, yet the personalized routing and

recommendation services

120 and 121 disclosed herein can be implemented for any type of vehicle such as a gasoline, hybrid or electric vehicle with varying degrees of autonomous or assisted driving capabilities. Referring to FIG. 1A, for one example, vehicle 110 includes an electric motor 108 receiving power from electric battery 104 to generate torque and turn wheels 109. Although vehicle 110 is shown with one electric motor 108 powered by electric battery 104 for a two-wheel drive implementation, vehicle 110 can have a second electric motor for a four-wheel drive implementation. In this example, electric motor 108 is located at the rear of vehicle 110 to drive back wheels 109 as a two-wheel drive vehicle. For other examples, another electric motor can be placed at the front of vehicle 110 to drive front wheels 109 as a four-wheel drive vehicle implementation.

For one example, electric motor 108 can be an alternating current (AC) induction motors, brushless direct-current (DC) motors, and brushed DC motors. Exemplary motors can include a rotor having magnets that can rotate around an electrical wire or a rotor having electrical wires that can rotate around magnets. Other exemplary motors can include a center section holding magnets for a rotor and an outer section having coils. For one example, when driving wheels 109, electric motor 108 contacts with electric battery 104 providing an electric current on the wire that creates a magnetic field to move the magnets in the rotor that generates torque to drive wheels 109. For one example, electric battery 104 can be a 120V rechargeable battery to power electric motor 108 or other electric motors for vehicle 110. Examples of electric battery 104 can include lead-acid, nickel-cadmium, nickel-metal hydride, lithium ion, lithium polymer, or other types of rechargeable batteries. For one example, electric battery 104 can be located on the floor and run along the bottom of vehicle 110. As a rechargeable battery, for one example, electric battery 104 can be charged by being plugged into an electrical outlet when vehicle 110 is not in operation. The location and number of high voltage rechargeable batteries are not limited to one and can be located throughout vehicle 110 in any location. For one example, vehicle 110 can be a hybrid, autonomous or non-autonomous vehicle or electric car.

For one example, a user of vehicle 110 can be authenticated to access cloud 117 and use personal routing service 120 and recommendation service 121 by way of login and password or by user biometric authentication. Once authenticated, a user of mapping application 107 in vehicle 110 can have access to personalized routing service 120, recommendation service 121 and database 122 for customized and personalized routing for the user. For example, personalized routing service 120 and recommendation service 121 can provide mapping application 107 seeking directions between locations with AD routing, points of interest specific to the user and/or advertisements germane or relevant to the user on a displayed map.

For one example, vehicle 110 includes an on-board computer 106 coupled to mapping application 107. On-board computer 106 can be a computer or data processing system including one or more processors, central processing units (CPUs) , system-on-chip (SoC) or micro-controllers and memory devices to run or implement mapping application 107. Within vehicle 110, on-board computer 106 can have wireless connectivity with cloud 117 using WiFi, cellular or Bluetooth communication or other communication protocols. In this way, on-board computer 106 can receive cloud-based services from personalized routing service 120 and recommendation service 121 for mapping application 107 as detailed herein.

For one example, a user of vehicle 110 can input a start location and one or more destinations to mapping application 107 that retrieves maps and mapping information from personalized routing service 120, which can provide the directions along with roads, routes, buildings, landmarks, terrain etc. on displayed maps such as those shown in FIG. 2 and 11A-11D. For one example, recommendation service 121 can access user specific information in database 122 (e.g., travel history, restaurant history, hotel history, browser history, shopping history, etc. ) and item information (e.g., location, category, review score, etc. ) to obtain personalized points of interest specific for each user. Each item for points of interest can refer to a favorite or frequently visited location such as, e.g., restaurants, bars, hotels, theaters, shopping centers, etc., stored in database 122. Routing service 120 can receive such points of interests from recommendation service 121 and forward them to mapping application 107, which are displayed on a map of geographical areas for vehicle 110.

For one example, vehicle 110 can be capable of AD driving. For AD driving, in obtaining directions from one location to another, a user can request AD routing from the mapping application 107. For example, AD routing can identify routes that maximize a proportion of AD driving time or distance on roads considered or favorable for AD driving. AD routing can consider factors such as AD driving on interstates, freeways, expressways and principal arterial roads. AD routing can consider other factors based on varying vehicle types, AD driving mode capabilities, driving area and surrounding municipalities, and road types and markers. Personalized routing service 120 can considers these factors to determine routes and directions for mapping application 107. For other examples, points of interest for a user can communicate with personalized routing service 120 and recommendation service 121 via cloud 117 and provide advertisements forwarded to mapping application 107 for display. For example, a bar or restaurant may be near or on routes between locations and can communicate with personalized routing service 120 and recommendation service 121 to advertise happy hour or daily specials. The advertisement can be displayed by mapping application 107 on a display within vehicle 110 as shown, e.g., in FIG. 11D.

FIG. 1B illustrates one example of a network topology 150 for vehicle 110 in vehicle environment 100 of FIG. 1A. Vehicle 110 includes a plurality of networking areas such as network areas 150-A, 150-B and 150-C interconnecting any number of subsystems and electronic control units (ECUs) according to a network topology 150. Any number of networking areas can be located throughout vehicle 100 and each networking area can include any number of interconnected ECUs and subsystems. Referring to FIG. 1B, for one example, network topology 150 includes interconnected ECUs 151-156 for electronic subsystems of vehicle 100 by way of network busses 158 and 159. For one example, ECUs can be a micro-controller, system-on-chip (SOS) , or any embedded system that can run firmware or program code stored in one or more memory devices or hard-wired to perform operations or functions for controlling components within vehicle 110. For another example, on-board computer 106 can be coupled to network busses 158 and 159 and communicate with ECUs 151-156 within network topology 150.

For one example, one or more ECUs can be part of a global positioning system (GPS) or a wireless connection system or modem to communicate with cloud 117, including access to personalized routing service 120, recommendation service 121, and database 122, for vehicle 110 using any type of WiFi, Bluetooth or cellular connectivity communication protocols. Examples of communication protocols include Global System for Mobile Communications (GSM) , General Packet Radio Service (GPRS) , CDMAOne, CDMA2000, Evolution-Data Optimized (EV-DO) , Enhanced Data Rates for GSM Evolution (EDGE) , Universal Mobile Telecommunications System (UMTS) , Digital Enhanced Cordless Telecommunications (DECT) , Digital AMPS (IS-136/TDMA) , Integrated Digital Enhance Network (iDEN) , etc. and protocols including IEEE 802.11 wireless protocols, long-term evolution LTE 3G+ protocols, and Bluetooth and Bluetooth low energy (BLE) protocols.

For one example, each ECU can run firmware or code or hard-wired to perform its function and control any number of electronic components operating within vehicle 110. For example, ECUs network areas 150-A, 150-B and 150-C can have ECUs controlling electronic components or subsystems for braking, autonomous driving, ignition, powertrain, steering, stability, lighting, airbag, inertia measurement and etc. The ECUs in the different networking areas of vehicle 110 can communicate with each other by way of network topology 150 and network busses 158 and 159. Although two network busses are shown in FIG. 1B, any number of network busses may be used to interconnect the ECUs. For one example, network topology 150 includes network or

communication busses

158 and 159 interconnecting ECUs 151 through 156 and coupling the ECUs to a vehicle gateway 157. For one example, vehicle gateway 157 can include a micro-controller, central processing unit (CPU) , or processor or be a computer and data processing system to coordinate communication on network topology 150 between the ECUs 151-156. For one example, vehicle gateway 157 interconnects groups (or networks) and can coordinate communication between a group of ECUs 151-153 with another group of ECUs 154-156 on

busses

158 and 159. For one example, network topology 150 and busses 158 and 159 can support messaging protocols including Controller Area Network (CAN) protocol, Local Interconnect Protocol (LIN) , and Ethernet protocol.

Exemplary Interior Vehicle Controls and Displays

FIG. 2 illustrates one example interior control environment 200 of vehicle 110 showing a mapping application 207 on coast-to-coast display 202 of vehicle dashboard 237 having an on-board computer 206. Referring to FIG. 2, the interior control environment 200 is shown from a front seat view perspective. For one example, interior control environment 200 includes vehicle dashboard 237 with a driving wheel 212 and coast-to-coast display 202. Coast-to-coast display 202 includes three display areas: display area 1 (214) , 2 (216) and 3 (218) . Vehicle dashboard 237 can include one more computing devices (computers) such as on-board computer 206 to control user interfaces (e.g., user interface 257) on display areas 1 to 3 (214, 216, and 218) including mapping application 207. For example, user interface 257 can be a touch-panel interface for My Activities functions. The on-board computer can also receive voice commands that are processed to control interfaces on vehicle dashboard 237. Vehicle dashboard 237 includes a camera 201 that can identify drivers and passengers of vehicle 110. For example, driver 271 ( “Tim” ) and passenger ( “Jenny” ) can be authenticated and identified by on-board computer 206 using camera 201 for identifying “Tim” and “Jenny. ”

For one example, driving wheel 212 incorporates driver tablet 210. Driver tablet 210 can provide a driver interface to access controls including settings and preferences for vehicle 110. For one example, driver tablet 210 or on-board computer 206 (e.g., within dashboard 237) can configure settings and preferences for Tim including settings and preferences for control interfaces on coast-to-coast display 202. For example, as shown in display area 3 (218) , map settings may be set for Tim with preferences for “Maps” , “Calendar” and “Messages” as shown in display area 3 (218) and a corresponding user interface 257 for Tim which is a control interface for a user. A passenger, e.g., Jenny, can also have settings and preferences set designated for Jenny on coast-to-coast display 202 once recognized or authenticated. Examples of settings and preferences can include personalized user interfaces on coast-to-coast display 202, personalized seat controls, personalized steering wheel controls, pedal locations, personalized climate control, personalized phone interface, and personalized mapping application 207. For example, mapping application 207 can have points of interest specific to a user, e.g., Tim, shown or displayed by mapping application 207.

For one example, driver tablet 210 is a tablet computer and can provide a touch screen with haptic feedback and controls. A driver of vehicle 110 can use driver tablet 210 to access vehicle function controls such as, e.g., climate control settings. Driver tablet 210 can be coupled to on-board computer 206 or another vehicle computer or ECU (not shown) within dashboard 237 or user capture device 277 and gesture control device 227. Driver tablet 210, on-board computer 206 or both can be configured to recognize a driver (e.g., Tim) or a passenger (e.g., Jenny) and allow the driver or passenger to use gesture control device 227 and access coast-to-coast display 202. For one example, driver tablet 210 can provide any number of representations, objects, icons, or buttons on its touchscreen providing functions, navigation user interface, phone controls to answer phone calls via a Bluetooth connection with any type of mobile device.

Coast-to-coast display 202 can include a light emitting diode (LED) display, liquid crystal display (LCD) , organic light emitting diode (OLED) , or quantum dot display, which can run substantially from one side to the other side of vehicle dashboard 237. For one example, coast-to-display 202 can be a curved display integrated into and spans the substantial width of dashboard 237. One or more graphical user interfaces can be provided in a plurality of display areas such as display areas 1 (214) , 2 (216) , and 3 (218) of coast-to-coast display 202. Such graphical user interfaces can include status menus shown in, e.g., display areas 1 (214) and 3 (218) in which display area 3 (218) shows a mapping application 207 providing graphical map in which directions can be obtained between locations. For one example, display area 1 (214) can show rear view, side view, or surround view images of vehicle 110 from one or more cameras, which can be located outside or inside of vehicle 110.

Exemplary Data Processing and Computing System Architecture

FIG. 3 illustrates one example block diagram of a computing system 300 for the on-

board computer

106 and 206 as shown in FIGS. 1A-2. Although FIG. 3 illustrates various components of a data processing or computing system, the components are not intended to represent any particular architecture or manner of interconnecting the components, as such details are not germane to the disclosed examples or embodiments. Other data processing systems or other consumer electronic devices, which have fewer components or perhaps more components, may be used with the disclosed examples and embodiments.

Referring to FIG. 3, computing system 300, which is a form of a data processing or computer, includes a bus 301 coupled to processor (s) 302 coupled to cache 304, display controller 314 coupled to a display 315, network interface 317, non-volatile storage 306, memory controller 308 coupled to memory devices 310, I/O controller 318 coupled to I/O devices 320, and database (s) 312. Processor (s) 302 can include one or more central processing units (CPUs) , graphical processing units (GPUs) , a specialized processor or any combination thereof. Processor (s) 302 can retrieve instructions from any of the memories including non-volatile storage 306, memory devices 310, or database 312, and execute the instructions to perform operations described in the disclosed examples and embodiments.

Examples of I/O devices 320 include external devices such as a pen, Bluetooth devices and other like devices controlled by I/O controller 318. Network interface 317 can include modems, wired and wireless transceivers and communicate using any type of networking protocol including wired or wireless WAN and LAN protocols including LTE and Bluetooth standards. Memory device 310 can be any type of memory including random access memory (RAM) , dynamic random-access memory (DRAM) , which requires power continually in order to refresh or maintain the data in the memory. Non-volatile storage 306 can be a mass storage device including a magnetic hard drive or a magnetic optical drive or an optical drive or a digital video disc (DVD) RAM or a flash memory or other types of memory systems, which maintain data (e.g. large amounts of data) even after power is removed from the system.

For one example, memory devices 310 or database 312 can store user information and parameters related to using

mapping application

107 or 207 including user information for applications on coast-to-coast display 202. Although memory devices 310 and database 312 are shown coupled to system bus 301, processor (s) 302 can be coupled to any number of external memory devices or databases locally or remotely by way of network interface 317, e.g., database 312 can be secured storage in a cloud environment. For one example, processor (s) 302 can implement techniques and operations described herein. Display 315 can represent coast-to-coast-display 202.

Examples and embodiments disclosed herein can be embodied in a data processing system architecture, data processing system or computing system, or a computer-readable medium or computer program product. Aspects, features, and details of the disclosed examples and embodiments can take the hardware or software or a combination of both, which can be referred to as a system or engine. The disclosed examples and embodiments can also be embodied in the form of a computer program product including one or more computer readable mediums having computer readable code which can be executed by one or more processors (e.g., processor (s) 302) to implement the techniques and operations disclosed herein.

Exemplary Personalized Routing and Recommendation System

FIG. 4 illustrates one example of a block diagram of a personalized routing and recommendation system 400 for a mapping application 407 of a vehicle 110. Referring to FIG. 4, for one example, personalized routing and recommendation service system 400 includes a front end 435 which is at vehicle 110 side having mapping application 407 coupled to display 402 (e.g., coast-to-coast display 202 in FIG. 2) . The front end 435 communicates with the backend 430, which can be implemented in-vehicle or in the cloud 117. For one example, backend 430 is in the cloud, e.g., cloud 117, having personalized routing service 420, recommendation service 421, and database 422. One or more servers or computers, e.g., as shown in FIG. 3, in cloud 117 or backend 430 can implement personalized routing service 420 and recommendation service 421 and for accessing and processing user information in database 423.

For one example, once a user has been authenticated and accesses controls for mapping application 407 within vehicle 110, the user can enter a starting location and one or more destinations to the mapping application 407 in order to obtain directions and routes. The mapping application 407 forwards the starting location and destination (s) to personalized routing service 420 and recommendation service 421. Recommendation service 421 can retrieve user profile 411 of a user of mapping application 407 and item information (item info) 412 in database 422 for any relevant points of interest (items) near or along the routes between the starting location and destination (s) . For one example, based on the retrieved user profile 511 and item info 412, recommendation service 421 can calculate or generate a personalized recommendation score and item list 417 for the relevant points of interest between the start location and destination. For one example, recommendation service 521 can calculate a score using content-based or collaborative filtering 401 using known or existing techniques. The personalized recommendation score can indicate a user interest level on each item or points of interest. For one example, the personalized recommendation score can range from 0 to 1 wherein 1 indicates the highest level of interest for the item and 0 means no interest for the item.

For one example, routing service 420 can determine routes based on user preferences such as minimizing travel time or distance, or maximizing time for AD routing, or maximizing user satisfaction by identifying relevant items or points of interest having the highest recommendation score from the item list and score 417. These points of interest can be shown on a map by the mapping application 407 on display 402 along the routes between a starting location and destination. Personalized routing service 420 can provide directions to maximize a proportion of travel time or distance for AD routing on roads considered favorable for AD driving. Personalized routing service 520 can receive advertisements from points of interest that are forwarded to mapping application displayed on a map on display 402. For one example, personalized routing service 420 can forward one or more pieces of information 477 to mapping application 407 including personalized routes or AD routes, recommendations/points of interest and/or advertisements. Mapping application 407 can display all or some of information 477 on maps shown on display 402 as shown in FIGS. 11A-11D.

(Exemplary Database for Personalized Routing)

FIG. 5 illustrates one example of a database 422 for the routing and recommendation service system 400 of FIG. 4. For one example, database 422 can include a number of tables for each user of vehicle 110 including a user table 501, interests table 502, gourmet history table 503, stay/history table 504, restaurants table 505 and hotel table 506. These tables are exemplary and any number of sub-tables can be associated with the tables and other types of data can be stored in database 422 for any number of users, e.g., authenticated drivers or passengers of vehicle 110. The tables in database 422 can include any number of primary keys and foreign keys that link or cross-reference a table with a primary key.

For one example, user table 501 includes three fields userID, username and password. The userID can be as a primary key (PK) for table 501. For one example, interests table 502 can include information relating to restaurant interests and hotel interests of each user. Interests table 502 can include four fields such as interestID, which can be a primary key (PK) , userID, which can be a foreign key (FK) , interest and interest type. Each user can have multiple rows, corresponding to multiple interests and interest type (e.g., “Hilton” can be an interest, and “Hotel” is interest type, “Food” can be an interest, and “Sushi” an interest type, etc. ) .

For one example, gourmet/history table 503 can include information of visited restaurants by a user. Gourmet/history table 503 can include four fields such as gourmetID, which can be a primary key (PK) , userID, which can be a foreign key (FK) , restaurantID, which can be a foreign key (FK) , and time of visit. For this table, each user can have multiple rows which can correspond to each visit by a user. For one example, gourmet/history table 503 includes a sub-table identified as restaurants table 505 which stores information about each restaurant in gourmet/history table 503. Restaurants table 503 can include ten fields such as restaurantID, which can be a primary key (PK) , longitude and latitude, address, open_time and close_time, price, interests, yelp_url and image_url. For one example, the interest field can be a comma-separated string, which includes all the labels that describes the restaurant, e.g., “Chinese, Sichuan, Asian, Buffet” , etc.

For one example, stay/history table 504 can store information related to hotels visited by a user. Stay/history table 504 can include four fields such as stayID, which can be a primary key (PK) , userID, which can be a foreign key (FK) , hotelID, which can be a foreign key (FK) , and time. For one example, each user can have multiple rows corresponding to each visit by a user. For one example, stay/history table 504 includes a sub-table identified as hotels table 506 which can store information about the visited hotels. Hotels table 506 can include ten fields such as hotelID, which can be a primary key (PK) , longitude and latitude, address, price, brand, yelp_url, and image_url. Each of the tables in database 422 are extendable capable of having any number of additional fields and sub-tables.

FIGS. 6A-6D illustrates exemplary tables 622 for multiple users of vehicle 110. Tables 622 can be stored in database 422 of FIG. 5 in tables specific to multiple users of vehicle 110. Referring to FIGS. 4 and 6A, for one example, users table 622 contains items 612 to 614 of points of interest data (items 1-N) for each of a plurality of users 611 (users 1-N) . Each of the users 1-N can be authenticated by vehicle 110 and mapping application 407 can be personalized for each user 1-N after authentication. For one example, points of interest items 1-N can be related to types of restaurants that are a favorite or frequently visited by users 1-N. Referring to FIGS. 4 and 6B, for one example, users table 622 shows types of restaurants for items 612 to 614 as “Sushi, ” “Mexican, ” and “Italian. ” For this example, user 1 identifies Sushi and Italian as favorite types of restaurants or frequently visited, user 2 identifies Mexican and Italian, and user N identifies Sushi, Mexican, and Italian as favorite types or frequently visited restaurants. Any number of items and types can be used for each user 1-N. Referring to FIGS. 4 and 6C, for example, each item marked with an “X” in FIG. 6B, is identified with a specific restaurant. For user 1, under Sushi and Italian the restaurants “Abe Sushi” and “Mia’s” are identified. For user 2, under Mexican and Italian, the restaurants “El Burro” and “Basil” are identified. For user N, under Sushi, Mexican and Italian, the restaurants “Uni Sushi” , “CeCelia’s” and “LaTomate” are identified. Users table 622 can store other types of attributes including location of each open, operating hours, telephone numbers and addresses. Referring to FIGS. 4 and 6D, for one example, other types of user points of interest can be stored in users table 622. For this example, the points of interest items 612-614 for users 611 (users 1-N) relate to types of drinking places such as “Coffee” , “Bar” and “Boba. ” For each item marked “X” a specific item can be identified for each user 1-N.

For one example, recommendation service 421 can filter items in database 422 using content-based recommendation or collaborative filtering 401 to obtain specific item 411 for user information 412 that is passed to routing service 420. For one example, recommendation service 421 can use techniques as described in FIG. 7A to obtain a recommendation score in making predictions about interests of user based on preferences, viewpoints, etc. from many users to identify items as points of interest to be displayed by mapping application 407. Referring to FIGS. 4 and 6C, for example, vehicle 110 can authenticate that

users

1, 2 and N are in vehicle 110. One of the users can input directions to mapping application 407 to travel from one location to another. Along the routes for directions, one of the Italian restaurants, e.g., Mia’s, in users table 622 is along or near one of the routes. Because all three users indicated a preference for Italian restaurants, recommendation service 421 can calculate a recommendation score that identifies “Mia’s” as a point of interest for routing service 420, which can forward “Mia’s” to mapping application 407 that displays “Mia’s” as part of the directions and routes on display 402.

For other examples, recommendation service 421 can calculate a recommendation score use a rating for each item in user database 422. The ratings can be trained or maintained by recommendation service 421 based on the item being visited or rated by the user. Ratings can be established based on social media comments, previous visits, etc. Recommendation service 421 can calculate scores and make predictions based on the ratings to identify specific items 612 for user 611. Referring to FIGS. 4 and 6C, for one example, user N indicated a preference for Sushi, Mexican and Italian and if all the identified restaurants were on or near routes for directions, a rating or score can be provided for each of the restaurants. For example, user N may have a high rating or score for Sushi, medium rating or score for Mexican, and low rating or score for Italian. In this case, because Sushi had a high rating or score, the restaurant “Uni Sushi” would be the item 612 selected for user 611 (user N) . Under each class or type, any number of items can be associated with the class or type with corresponding ratings or scores. For example, user N can have a second favorite Sushi restaurant such as Abe Sushi that may have a slightly lower rating or score than Uni Sushi. If Abe Sushi was near or fell on determined routes, Abe Sushi would be passed to routing service 420 and mapping application 407 for display on display 402.

(Exemplary Recommendation Score Generation)

FIG. 7A illustrates one example flow diagram of a recommendation service operation 700 including operation blocks 711, 712, 721 and 717. Operation 700 can be performed by recommendation service 421 with a recommendation of FIG. 4.

For one example, at

blocks

711 and 712, a user personal favorite profile can be stored in database 422 of FIG. 5. The user personal profile can store favorite types of restaurants such as, e.g., Sushi, Chinese, Fast Food, Indian, Japanese, Vegan, Brunch etc. The profile can store other types of favorite categories such as Hotel Brands including, e.g., Weston, Hilton, Marriott, Four Seasons, Holiday Inn etc. At block 711, each item for the favorite types of restaurants and hotel brands can have a specific restaurant/hotel ID and its type information, e.g., Sushi, and review and price. Additional information can be included for item information at block 711. The information from

blocks

712 and 711 are passed to block 721 for the recommendation engine process, which can be part of the recommendation service 421 of FIG. 4, to generate a recommendation score. At block 721, the recommendation engine can take a user personal favorite profile (e.g., Sushi, Chinese, etc. ) and all item information (e.g., restaurant type, review, and price) and perform content-based recommendation or collaborative filtering to generate a recommendation/favorite score for each item from block 711. At block 717, along with the score, the recommendation engine can provide a restaurant or hotel ID and location of the time which can be used for placement on a map by mapping application 407.

(Content-Based Recommendation and Collaborative Filtering)

Referring to FIGS. 4 and 7A, at block 721, the recommendation engine of recommendation service 421 can implement machine learning techniques and algorithms, namely content-based recommendation and collaborative filtering. For content-based recommendation, for example, the recommendation engine can use a user’s personal favorite profile and item information stored in database 422 to implement a two-level recommendation algorithm. For one example, at a first level, the recommendation engine can use a keyword-matching method. For example, given a user’s interest (e.g., records in Interests Table 502 in FIG. 5) , the recommendation engine can use a wildcard matching method to search through field “interests” in interests table 502 for Restaurants or Hotels. For one example, a user can have multiple favorites Restaurants or Hotels and each favorite can have a same weight value. For each restaurant or hotel item, the recommendation engine can assign a score of from 0 to 1 based on whether the item matches a user’s interest. For one example, the recommendation engine can rank the items based on score and, alternatively, the routing service 420 can rank items. For one example, at a second level, if the recommendation engine cannot find a keyword match at a first level, the recommendation engine resort to a fuzzy-matching method using a “word2vec” algorithm that give a value based on the similarity between two words by representing word as vector. For example, “Japanese” is closer in relation to “ramen” than, e.g., “tacos” using data in database 422 or users tables 622. The model can be trained based on a large dataset of user reviews, social media, other reviews related to, e.g., restaurants or hotel or daily services. A score then can be assigned to items (e.g., a restaurant or a hotel) that match a user’s favorites.

For collaborative filtering, for example, the recommendation engine can use a user’s history as well as other user histories. Taking restaurants, for example, the recommendation engine can provide restaurant suggestions based on current users’ past visited restaurants elsewhere and other user’s past visited restaurants in the targeted location. For example, the recommendation engine can implement collaborating filtering that if two or more users visited the same or similar restaurants in the past and assume the two users tend to visit same or similar restaurants in the future. Thus, given a current user’s history, the recommendation engine can recommend one or more local restaurants that find similar users visiting it before.

For one example, recommendation engine can implement group recommendation for more than one user (e.g., a driver and multiple passengers) that are driving in vehicle 100. The recommendation engine can give the same weight to each user’s multiple favorites in determining recommendations. The recommendation engine can also consider other factors to rank items, e.g., distance to restaurant and review of the restaurant. The recommendation engine can implement majority-weighted-voting to rank items that have the most users identify the item as a favorite. For example, the recommendation engine can sum-up and sort the favorite list by its single favorite’s frequency and pick the favorite with the highest frequency. The recommendation engine can also rely on user feedback to adjust the recommendation.

(Exemplary Personalized Routing Operation)

FIG. 7B illustrates one example flow diagram of a personalized routing service operation 730 including operation blocks 732 through 742. Operation 730 can be performed by personalized routing service 420 of FIG. 4 and receives input from recommendation service 421. For one example, operation 730 implements an A Star ( “A*” ) algorithm based on heuristics to find paths between a start location and one or more destinations on a geographical map to minimize travel time or distance. Alternatively, operation 730 can implement a Dijkstra algorithm to find the shortest path or travel time between locations. Operation 730 can factor in other considerations such as scores for points of interests or items as well as autonomous driving (AD) designated routes in determining routes for a mapping application of vehicle 110.

At block 732, a starting node (i.e., the starting location of the route) is assigned with a cost or value 0 and pushed into a priority queue.

At block 734, a determination is made if the priority queue is empty. If yes, operation 730 returns to block 734. If no, at block 736, the node with minimum cost is popped as the current node.

At block 738, a determination is made if the current node is the destination. If yes, at block 739, the operation terminates and outputs the recorded path or route. If no, at block 740, a cost of the neighbor node is calculated by adding the value to neighbor node to the cost function f (n) as follows:

(Cost Function)

f (n) =w1×g (n) +w2×h (n)

where g (n) is the cost of the path from the starting node to current node n and h (n) is a heuristic function that estimates the cost of the cheapest path from n to the destination node. At block 742, if the neighbor node cost is reduced, the neighbor node cost is updated and pushed to the priority queue. Operation 730 can terminate when the priority queue is empty and no path is found to reach the destination node. Operation 730 can be used to find the minimal distance or travel time between nodes or start location and destination.

The above operation can modify the cost function to add in personalized recommendation factors to obtain routes that minimize the cost function in connection with personalized recommendations (e.g., points of interest) as follows:

(Modified Cost Function with Personalized Recommendation Factor)

wherein rs (n) is the personalized recommendation score for a current node n (i.e., location in the route) . By including the recommendation score factor, the cost function is modified to the find the route with minimum cost or travel time together with maximum personalized recommendation score (i.e., personal points of interests) . For other examples, an autonomous route (AD) factor or score can be another factor to modify the cost function to maximize driving on AD designated routes such as.

For one example, several weight parameters (e.g., w1, w2 and w3) can be used to tune the cost function algorithm to trade-off between efficiency, travel time and personal points of interests. For example, the weight w1 can indicate importance of travel time reduction, w2 can indicate importance of efficiency of the algorithm, and w3 can indicates importance of personal points of interests for each user. These parameters can have the constraint of totaling to 1:

w1+w2+w3=1

Other additional factors can be added such as, e.g., w4 that can indicate the importance of AD designated routes which with the other weights total 1. These weights can be user configurable and obtained by training known machine learning models.

Personalized Route Determination Examples

FIG. 8A-8C illustrate example of flow diagrams of

operations

800, 810 and 815 to in making route determinations 805. Personalized routing service 420 and recommendation service 421 can work in tandem to implement

operations

800, 810 and 815 as described herein. Initially, for

operations

800, 810 and 815, a start location ( “A” ) and destination ( “B” ) are entered by a user of vehicle 110 using mapping application 407 seeking directions and routes between the locations.

Referring to FIG. 8A, in seeking directions, operation 800 includes minimizing travel time or distance 810 and maximizing satisfaction 802, which are combined to make a route determination 805. For one example, maximizing satisfaction 802 includes identifying points of interest with a high rating or recommendation score that a user may want to visit while traveling between locations A and B. For example, referring to FIG. 9A, a map graph 900 having nodes C ₁ (901) to C ₅ (905) between locations A (910) and B (911) with factors that include recommendation score RS (n) 908 for points of interest and autonomous driving (AD) score AS (n) 909 associated with each node. For this example, there are three routes that can be taken between A and B which are (C ₁ and C ₂) , (C ₃, C ₄ and C ₅) and (C ₃ and C ₂) . Each of the nodes C ₁ to C ₅ can be associated with points of interest and, for this example, points of interest are restaurants which can have a restaurant recommendation RS (n) 908 and an AD route score AS (n) 909 at each node. For example, nodes C ₁ to C ₅ (901 to 905) can have restaurant recommendation scores RS (1) , RS (2) , RS (3) , RS (4) and RS (5) and AD route scores AS (1) , AS (2) , AS (3) , AS (4) and AS (5) .

For one example, referring to FIG. 9B, in making a route determination 805 for operation 800 of FIG. 8A, a minimize operation (MIN) 910 is performed for the three possible routes between A and B. The MIN operation 910 finds the route with cost function (Cost ₁ to Cost ₅) of the nodes (C ₁ to C ₅) including Factors _n 920. For operation 800, the cost function described above can be used along with the factor that is associated with maximizing satisfaction based on restaurant preferences core RS (n) 908, which can be inverted as 1/RS (n) 931 for the MIN operation 910 and a weight W _RS 934 associated with 1/ (RS (n) 931. This allows a high preference score to have minimum value for the MIN operation in selecting lowest score route. Thus, the MIN operation 910 can be performed to find that route that minimizes the cost (e.g., distance or time) for the three routes and maximize satisfaction by identifying preferred restaurant along the routes or directions as follows:

MIN [ (Cost ₁ + W _RS*1/RS (1) ) + (Cost ₂ + W _RS*1/RS (2) ) ]

[ (Cost _3 + W _RS*1/RS (3) ) + (Cost ₄ + W _RS*1/RS (4) ) + (Cost ₅ + W _RS*1/RS (R ₅) ) ]

[ (Cost _3 + W _RS*1/RS (3) ) + (Cost ₂ + W _RS*1/RS (2) ) ]

For one example, the W _RS factor can refer to the weight w3 for the cost function as noted above. For purposes of discussion, a route including C ₃ (which can be associated with a favorite Sushi restaurant such as “Uni Sushi” ) provides the minimal score, e.g., (route C ₃ and C ₂) that can provide the best route for route determination 805 using MIN operation 910. Personalized routing service 420 can pass the points of interest of “Uni Sushi” to mapping application 407 that can display the points of interest, e.g., Uni Sushi, on a map of a geographical area showing the routes between A and B.

For another example, referring to FIG. 9B, in making a route determination 805 for operation 810 of FIG. 8B, a minimize operation (MIN) 910 can be performed for the three possible routes between nodes A and B to minimize travel time or distance 801 and maximize time on autonomous driving (AD) routes 803. For operation 810, the factor AS (n) 909 is used, which can be inverted as 1/AS (n) 932 for the MIN operation 910 if a high score indicates a high preference for AD routes and a weight W _AS 935 associated with 1/ (AS (n) 932. For example, an AD route can have a score of . 99 and a non-AD route can have a score of . 1 such that 1/. 99 provides a low score relative to 1/. 1 for the MIN operation 910. Thus, the MIN operation 910 can be performed to minimize the distance or time for the three routes and maximize time on AD routes for routes or directions between A and B as follows:

MIN [ (Cost ₁ + W _AS*1/AS (1) ) + (Cost ₂ + W _AS*1/AS (2) )

[ (Cost _3 + W _AS*1/AS (3) ) + (Cost ₄ + W _AS*1/AS (4) ) + (Cost ₅ + W _AS*1/AS (R ₅) ) ]

[ (Cost _3 + W _AS*1/AS (3) ) + (Cost ₂ + W _AS*1/AS (2) ) ]

For this example, W _AS 935 can refer to the weight w4 as described above for the cost function. W _AS 935 can a certain weight for AD designated routes in order to modify the cost function and route C ₃ and C ₂ can be designated with low scores for 1/AS (N) 933 while providing the shortest distance or time between A and B. Personalized routing service 520 can pass this route (C ₃ and C ₂) as AD routes between A and B to mapping application 407 that can display the AD routes on a map of a geographical area showing the routes between A and B to maximize time on AD designated roads.

For another example, referring to FIG. 9B, in making a route determination 805 for operation 815 of FIG. 8C, a minimize operation (MIN) 910 can be performed for the three possible routes between nodes A and B to minimize travel time or distance 801 and maximize satisfaction 802 and maximize time on AD routes 803. For operation 815, Factors _n 920 is associated with maximizing satisfaction restaurant preference score RS (n) 908, which can be inverted as 1/RS (n) 931 and maximizing time on AD route score AS(n) 909, which can also be inverted as 1/AS (n) 932 for the MIN operation 910. In this example, Factors _n 920 can be 1/RS (n) + 1/AS (n) 933 having respected weight W _RS and W _AS 936 such that operation 910 uses W _RS*1/RS (n) + W _AS*1/AS (n) . Here, the MIN operation 910 can be performed to minimize the distance or time for the three routes and maximize satisfaction and time on AD routes for routes or directions between A and B as follows:

MIN [ (Cost ₁ + (W _RS*1/RS (1) + W _AS*1/AS (1) ) ) + (Cost ₂ + (W _RS*1/RS (2) + W _AS*1/AS (2) ) ) ]

[ (Cost ₃ + (W _RS*1/RS (3) + W _AS*1/AS (3) ) ) + (Cost ₄ + (W _RS*1/RS (4) + W _AS*1/AS (4) ) ) +

(Cost ₅ + (W _RS*1/RS (5) + W _AS*1/AS (5) ) ) ]

[ (Cost _3 + (W _RS*1/RS (3) + W _AS*1/AS (3) ) ) + (Cost ₂ + (W _RS*1/RS (2) + W _AS*1/AS (2) ) ) ]

For this example, W _RS can refer to w3 and W _AS can refer to the weight w4 for the cost function described above, which can be used for the combination of AD designated routes and points of interest. W _RS and W _AS 936 can be used as factors to modify the cost function and route C ₃ and C ₂ can be designated with low scores for 1/RS (n) + 1/AS (n) 933 while providing the shortest distance or time between A and B. Personalized routing service 421 can pass route C ₃ and C ₂ that identifies node C ₃ as having a selected restaurant recommendation score, e.g., Uni Sushi. Personalized routing service 420 forward this information to mapping application 407 that can display the AD routes along with Uni Sushi on a map of a geographical area showing the routes between A and B that maximize time on AD designated roads.

Exemplary Interfaces and Maps for Personalized Routing

FIGS. 10A-10D illustrate

exemplary user interfaces

1000, 1010, 1015 and 1020 for a mapping application to request directions along with requests for AD routes or points of interest recommendations. Referring to FIG. 10A, for one example, mapping application can provide user interface 1000 having two options for autonomous routing (time to be) 1001 and points of interest recommendation 1002.

Options

1003 and 1004 allow a user to enter an address for location A and location B and an option to get directions 1005. For this example, a user can enter the addresses for locations A and B and select the option for autonomous routing 1001 and to get directions 1005. For example, referring to FIG. 11A using the techniques disclosed herein, a mapping application can provide map 1107 that provides AD routing 1117 for directions between locations such as, e.g., highway 1 and main arterial roads. In contrast, non-AD routing 1113 may provide a faster travel time, but is limited to secondary roads, which may not be favorable for AD driving.

Referring to FIG. 10B, for one example, mapping application user interface 1010 also provides two options for autonomous routing (time to be) 1001 and points of interest recommendation 1002 in which points of interest recommendation 1002 is selected to displayed along with directions 1005 for locations A and

B

1003 and 1004. For one example, referring to FIG. 11B using the techniques disclosed herein, a mapping application can provide a map 1107 that provides directions from location A in Sacramento to location B in Santa Ana, which can be recommended using route determination techniques disclosed herein. Referring to FIG. 11B, points of interest for ABC BBQ and Jay’s BBQ, which can have a high recommendation score for a user and fall or be near the route between locations A and B, are displayed on map 1107. For example, on the route from A and B, ABC BBQ can be located in Modesto and Jay’s BBQ is located in Taft which may be considered a relevant point of interest for the user.

Referring to FIG. 10C, for one example, mapping application user interface 1015 also provides two options for autonomous routing (time to be) 1001 and points of interest recommendation 1002 which are both selected in getting directions 1005 for locations A and B 1103 and 1104. For one example, referring to FIG. 11C using the techniques disclosed herein, a mapping application can provide a map 1107 that provides directions from location A to location B in San Francisco, CA, which can be recommended using the route determination techniques disclosed herein. Referring to FIG. 11C, AD routing 1117 can provided for directions between A and B and a point of interest such as “Uni Sushi” is displayed with item information such as address 111 HW1 and telephone number (415) 220-1111. Uni Sushi is identified with a high recommendation score that is located near or along AD routing 1117.

Referring to FIG. 10D, for one example, mapping application user interface 1020 provides three options for autonomous routing (time to be) 1101, points of interest recommendation 1002, and advertising 1007, which are selected in getting directions 1005 for locations A and

B

1003 and 1004. For one example, referring to FIG. 11D using the techniques disclosed herein, a mapping application can provide a map 1107 that provides directions from location A to location B in San Francisco, CA, which can recommend using AD routing 1117 and identify “Uni Sushi” as a recommended point of interest displayed on map 1107.

For one example, Uni Sushi can communicate with personalized routing service 420 and recommendation service 421 in cloud 117 and provide advertisements that identified of points of interest in database 422. For example, Uni Sushi can inform recommendation service 421 that there is a special from 3-6pm for one dollar sushi. Personalized routing service 420 can send this advertisement to mapping application 507 which can display the advertisement in map 1107 as shown in FIG. 11D. For other examples, any location (e.g., store, bar, restaurant, coffee shop, electric charging stations etc. ) can communicate with recommendation service 421 and request advertisements to be displayed on map 1107 if vehicle approaches or is near the location by way of personalized routing service 420.

In the foregoing specification, the invention has been described with reference to specific examples and exemplary embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of disclosed examples and embodiments. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims

A vehicle data processing system comprising:

a display within a vehicle; and

an on-board computer coupled to the display and configured to

provide a mapping application on the display, the mapping application to receive inputs of a start location and one or more destinations for obtaining directions for a user,

process the received inputs of the start location and the destinations to obtain one or more routes for autonomous driving (AD) routing that maximize a proportion of AD driving time or distance on roads considered or favorable for AD driving, and

provide AD routing directions to the mapping application on the display.
The vehicle data processing system of claim 1, wherein AD routing considers factors including type of vehicle, AD driving mode capabilities of the vehicle, driving area and surrounding municipalities and road types.
The vehicle data processing system of claim 2, wherein AD routing considers factors including AD driving on interstates, freeways, expressways and principal arterial roads.
The vehicle data processing system of claim 1, wherein the on-board computer is configured to receive the one or more routes from a cloud-based service for AD routing.
The vehicle data processing system of claim 1, wherein the mapping application is configured to provide a user interface to allow a user to select an option for AD routing.
A vehicle data processing system comprising:

a display;

an on-board computer coupled to the display and configured to

receive inputs to obtain directions for routes between locations for a mapping application, and

display the routes along with one or more points of interest recommended for a specific user.
The vehicle data processing system of claim 6, wherein the one or more points of interest provide advertisements to the mapping application that displays the advertisements on the display.
The vehicle data processing system of claim 6, wherein the one or more points of interest fall on or are close to the routes.
The vehicle data processing system of claim 6, wherein the one or more points of interest are recommended by a cloud-based service using machine learning techniques.
The vehicle data processing system of claim 6, wherein the machine learning techniques include content-based recommendation or collaborative filtering.
A vehicle, comprising:

a display;

a wireless interface to communication with a cloud-based personalized routing service;

an on-board computer coupled to the display and wireless interface and configured to run a mapping application, the mapping application configured to

provide an interface to obtain routes between locations and options for a user to select an option for autonomous driving (AD) routing or points of interest recommendations specific to a user, and

display a map on the display with the routes for AD routing or the points of interest recommendations specific to the user based on the option selected by the user.
The vehicle of claim 11, wherein AD routing considers factors including type of vehicle, AD driving mode capabilities of the vehicle, driving area and surrounding municipalities and road types.
The vehicle of claim 11, wherein AD routing considers factors including AD driving on interstates, freeways, expressways and principal arterial roads.
The vehicle of claim 11, wherein the points of interest recommendations fall on or are close to the routes.
The vehicle of claim 14, wherein one or more of the points of interest recommendations provide advertisements to the mapping application that displays the advertisements on the display.
The vehicle of claim 11, wherein the points of interest recommendations are recommended by a cloud-based service using machine learning techniques.
The vehicle of claim 16, wherein the machine learning techniques include content-based recommendation or collaborative filtering.
The vehicle of claim 17, wherein the cloud-based service calculates a recommendation score to determine the points of interest recommendations.
The vehicle of claim 18, wherein the recommendation score is calculated using weights for AD routing and points of interests specific to the user.
The AD vehicle of claim 11, wherein points of interest are stored in a cloud-based database.