Information processing system and information processing method

Abstract

[Problem] To improve the level of user satisfaction with technology that is provided using a topology map. [Solution] Provided is an information processing system comprising: a generation unit that generates, on the basis of travel data which has been acquired by a traveling vehicle, a first topology map which is a lane topology map and which corresponds to the vehicle; and a weighting unit that performs, for training using the first topology map, weighting in the training for each position of the first topology map in accordance with a tendency of driving of the vehicle by a user.

Description

Information processing system and information processing method

[0001] The present disclosure relates to an information processing system and an information processing method.

[0002] In recent years, various technologies related to vehicles have been developed. For example, Patent Literature 1 discloses a technology for selecting a trajectory of an automatically driven vehicle from a plurality of trajectories based on location information of a destination.

[0003] Such a map containing vehicle trajectories is also called a topology map, and technology for generating topology maps is expected to be developed. Topology maps can be used to provide various technologies such as autonomous driving and navigation.

[0004] Special Publication No. 2022-549952

[0005] It is conceivable that different users may have different driving tendencies when driving a vehicle. However, the technology disclosed in Patent Document 1 does not take into consideration the driving tendencies of each user.

[0006] Therefore, the present disclosure proposes a new and improved technique that can improve user satisfaction with the technology provided by utilizing a topology map.

[0007] According to the present disclosure, there is provided an information processing system including: a generation unit that generates a first topology map, which is a topology map of lanes corresponding to a traveling vehicle, based on driving data acquired by the vehicle; and a weighting unit that, for learning using the first topology map, assigns weights to each position of the first topology map in the learning according to the user's tendency to drive the vehicle.

[0008] Furthermore, according to the present disclosure, there is provided an information processing method executed by a computer, the method including: generating a first topology map, which is a topology map of lanes corresponding to a traveling vehicle, based on driving data acquired by the vehicle; and, for learning using the first topology map, weighting each position of the first topology map in the learning in accordance with the user's tendency to drive the vehicle.

[0009] 1 is a block diagram showing the overall configuration of an information processing system 1 according to the present embodiment. FIG. 2 is a block diagram showing the functional configuration of a vehicle 10 according to the present embodiment. FIG. 3 is a diagram showing an example of a local topology map 151. FIG. 4 is a diagram for explaining a method for generating the local topology map 151. FIG. 5 is a flowchart showing an example of the operation of the vehicle 10 in generating the local topology map 151. FIG. 6 is a flowchart showing an example of the operation of the vehicle 10 in transmitting the local topology map 151. FIG. 7 is a diagram for explaining a learning method of the lane topology recognition AI. FIG. 8 is a diagram for explaining the calculation of a user's stress value based on sensing data. FIG. 9 is a diagram showing a graph illustrating an example of a conversion table between stress values ​​and weights. FIG. 10 is a diagram showing an example of a display screen that is displayed on the operation display unit 130 and that accepts feedback from a user. FIG. 11 is a diagram for explaining the generation of an AI-recognition topology map by the map generation unit 147B. FIG. 12 is a flowchart showing an example of the operation of the vehicle 10 in learning the lane topology recognition AI 153. FIG. 13 is a block diagram showing the functional configuration of the server 20 according to the present embodiment. FIG. 14 is a diagram for explaining a method for calculating and statistically calculating the driving risk of each user. FIG. 15 is a flowchart showing an example of the operation of the server 20 in calculating and statistically calculating the driving risk of each user. FIG. 16 is a diagram showing an example of an architecture that realizes processing according to the present embodiment.

[0010] Preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted.

[0011] The explanation will be given in the following order: 1. Overview 2. Example of the configuration of the vehicle 10 3. Detailed functions of the vehicle 10 4. Example of the configuration of the server 20 5. Detailed functions of the server 20 6. Example of architecture 7. Example of the hardware configuration 8. Supplementary information

[0012] <<1. Overview>> The present disclosure relates to an information processing system that learns a topology map used as a vehicle travel trajectory. The topology map is a map showing lane topology, including a high-definition (HD) map showing road information such as lane separators, road boundaries, and crosswalks, and a vehicle travel trajectory (hereinafter also referred to as a "traveling line"). For example, in locations where lanes are defined, the traveling line may be a lane center line. In locations where lanes are not defined, the traveling line may be a line indicating the connection between lanes. The HD map includes vector data and position information representing each piece of road information. In addition, the topology map includes vector data and position information representing the traveling line.

[0013] Here, it is expected that road information is automatically recognized from sensing data acquired by a vehicle to generate a topology map, and the driving line is used as the trajectory of the vehicle, thereby enabling automatic driving of the vehicle or navigation of the vehicle. For example, it is conceivable to generate a topology map by using a recognizer that can output a topology map using sensing data acquired by the vehicle as input data. Hereinafter, such a recognizer is also referred to as "lane topology recognition AI (Artificial Intelligence)."

[0014] On the other hand, vehicle driving tends to differ for each user. For example, user tendencies are reflected in the way a user turns at an intersection, and the distance to an object when passing by such an object, such as a parked car or a bicycle traveling on the same road. Such tendencies reflect, for example, the user's driving preferences. Therefore, by outputting a topology map that reflects such tendencies for each user, when the topology map for each user is applied to the driving trajectory of a vehicle under automated driving, the vehicle will drive in a way that reflects the user's own preferences. This improves user satisfaction with automated driving.

[0015] In this embodiment, first, each vehicle collects its own traveling trajectory to generate a local topology map, which is a topology map specific to the vehicle. The local topology map is the first topology map according to this embodiment.

[0016] Each vehicle then generates a local topology map with user tendencies, with weights assigned to each position in the generated local topology map indicating the importance of the user's driving tendencies at that position to the learning of the lane topology recognition AI described below.

[0017] Using such a local topology map with user tendencies, a lane topology recognition AI is trained that can output an AI-recognized topology map that is a topology map that reflects the user's driving tendencies. The AI-recognized topology map is a second topology map according to this embodiment.

[0018] The overall configuration of an information processing system according to an embodiment of the present disclosure will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the overall configuration of an information processing system 1 according to this embodiment.

[0019] 1, the information processing system according to this embodiment includes a plurality of vehicles 10 (10A to 10C) and a server 20. The vehicles 10 and the server 20 are connected for communication via a network 30.

[0020] (Vehicle 10) The vehicle 10 is a vehicle that travels on a road. The type (model) of the vehicle 10 is not particularly limited, and may be a small, medium, or large passenger car, a motorcycle, a moped, a truck, a bus, a towing vehicle, or the like.

[0021] The vehicle 10 senses the surrounding environment while traveling using various sensors mounted on the vehicle 10. The sensing data acquired by the vehicle 10 includes sensing data that enables road recognition, such as images (still images or moving images) captured by an RGB camera, point cloud data acquired by LiDAR (Light Detection and Ranging) or Radar (Radio Detection and Ranging), etc.

[0022] The vehicle 10 recognizes road information based on sensing data of the surrounding environment. The road information includes, for example, information indicating crosswalks, road boundaries, lane dividing lines, etc.

[0023] Here, the vehicle 10 may recognize road information based on an SD (Standard) map. The SD map is a map that is primarily used for navigation and has lower accuracy than the HD map. The SD map may be pre-stored in a storage unit provided in the vehicle 10, or an SD map of an area as needed may be downloaded from an external database or the like.

[0024] The vehicle 10 further acquires sensing data related to the vehicle 10. The sensing data related to the vehicle 10 may include, for example, the rotation speed of the wheels of the vehicle 10 acquired by a wheel speed sensor, the steering angle of the steering wheel of the vehicle 10 acquired by a steering angle sensor, the acceleration and angular velocity of the vehicle 10 acquired by an IMU (Inertial Measurement Unit), the vibration frequency of the vehicle 10 acquired by a vibration sensor, and position information of the vehicle 10 acquired by a GNSS (Global Navigation Satellite System) such as a GPS (Global Positioning System).

[0025] Vehicle 10 further acquires sensing results of the state of the user driving vehicle 10. The sensing data of the state of the user may include, for example, an image of the user captured by a camera that captures an image of the user, the amount of sweat of the user acquired by a humidity sensor mounted on the steering wheel or the backrest of vehicle 10, and the user's voice acquired by a microphone.

[0026] The vehicle 10 estimates its own position based on the recognized road information and sensing data related to the vehicle 10. The vehicle 10 derives the trajectory of the estimated own position as the traveling trajectory of the vehicle 10.

[0027] The vehicle 10 generates a local topology map of the locations where the vehicle has traveled based on the recognized road information and travel path. In the local topology map, the travel path of the vehicle 10 becomes the travel line.

[0028] The vehicle 10 transmits various types of sensing data and the generated local topology map to the server 20 via the network 30 .

[0029] (Server 20) The server 20 processes various data collected from the vehicles 10 via the network 30. For example, the server 20 reflects information contained in local topology maps collected from each of the multiple vehicles 10 in a global topology map. The global topology map is a general-purpose topology map, and may include, for example, a driving line appropriate for driving the vehicle 10.

[0030] (Network 30) The network 30 is a communication path between the vehicle 10 and the server 20. The network 30 may take any form, such as the Internet or a public line network.

[0031] <<2. Configuration Example of Vehicle 10>> Next, a configuration example of the vehicle 10 according to this embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the functional configuration of the vehicle 10 according to this embodiment.

[0032] As shown in FIG. 2 , the vehicle 10 according to this embodiment includes a sensor unit 110 , a communication unit 120 , an operation display unit 130 , a control unit 140 , and a storage unit 150 .

[0033] (Sensor unit 110) The sensor unit 110 is a sensor that acquires sensing data of the surrounding environment of the vehicle 10 while it is running, sensing data related to the vehicle 10, and sensing data of the state of a user riding in the vehicle 10. The sensing data of the surrounding environment of the vehicle 10 while it is running and the sensing data related to the vehicle 10 are running data acquired by the running vehicle.

[0034] The sensor unit 110 may include, for example, an RGB camera (hereinafter simply referred to as a camera) that acquires image data of the surrounding environment of the vehicle 10, a LiDAR and a Radar that acquire point cloud data of the surrounding environment of the vehicle 10, etc.

[0035] The sensor unit 110 may also include a wheel speed sensor that acquires the rotation speed of the wheels of the vehicle 10, a steering angle sensor that acquires the steering angle of the steering wheel of the vehicle 10, an IMU that acquires the acceleration and angular velocity of the vehicle 10, a vibration sensor that acquires the vibration frequency of the vehicle 10, and a GNSS sensor (or receiver) that acquires the position information of the vehicle 10.

[0036] The sensor unit 110 may also include a camera that captures images of the user, a humidity sensor that captures the amount of sweat of the user, and a microphone that captures the user's voice.

[0037] The sensors included in the sensor unit 110 are not limited to the above examples, and may include other sensors, such as an illuminance sensor, that acquire sensing data on the surrounding environment of the vehicle 10, sensing data related to the vehicle 10, or sensing data on the user's condition.

[0038] Furthermore, various types of sensing data are not limited to being acquired by the sensor unit 110. Sensing data on the state of the user, such as heart rate, may be acquired by an external device such as a wearable device worn by the user.

[0039] (Communication Unit 120) The communication unit 120 communicates information with the server 20 via the network 30. The communication unit 120 transmits, for example, various sensing data acquired by the sensor unit 110 to the server 20. The communication unit 120 may also acquire various sensing data by connecting for communication with an external device such as a wearable device worn by the user.

[0040] (Operation display unit 130) The operation display unit 130 has a function as an operation unit that detects operations by a user in the vehicle 10 and a function as a display unit that displays various information such as a navigation screen to the user. Such an operation display unit 130 may have, for example, a layered structure of a touch panel and a display. Note that the function as an operation unit and the function as a display unit may be realized separately.

[0041] (Control Unit 140) The control unit 140 functions as an arithmetic processing unit and a control device, and controls the overall operation inside the vehicle 10 according to various programs.

[0042] Furthermore, the control unit 140 according to this embodiment also functions as a surrounding information recognition unit 141, a self-position estimation unit 142, a local HD map generation unit 143, a reliability calculation unit 144, a map integration unit 145, a trend processing unit 146, and an AI control unit 147. The trend processing unit 146 includes a weight calculation unit 146A, a subjective evaluation processing unit 146B, and a trend integration unit 146C. The AI ​​control unit 147 includes an AI learning unit 147A and a map generation unit 147B. Details of the self-position estimation unit 142, the local HD map generation unit 143, the reliability calculation unit 144, the map integration unit 145, the trend processing unit 146, and the AI ​​control unit 147 will be described later.

[0043] (Storage Unit 150) The storage unit 150 stores various data used by the vehicle 10. For example, the storage unit 150 stores a local topology map 151, a local topology map with user tendencies 152, and a lane topology recognition AI 153.

[0044] The local topology map 151 is a topology map specific to the vehicle 10. The local topology map 151 is generated by the map integration unit 145, which will be described later.

[0045] Fig. 3 is a diagram showing an example of the local topology map 151. Fig. 3 shows the local topology map 151 and a legend 151n that is a legend for each line included in the local topology map 151.

[0046] 3 , the local topology map 151 includes a crosswalk recognition result, a road boundary recognition result, a lane separation line recognition result, and a driving line. As will be described in detail later, the driving line is reflected in the local topology map 151 based on the driving trajectory of the vehicle 10.

[0047] The local topology map with user tendency 152 is a topology map in which weights are assigned to each position on the local topology map 151 according to the user's vehicle driving tendency for learning using the local topology map 151. The local topology map with user tendency 152 is generated by the tendency processing unit 146, which will be described later.

[0048] The lane topology recognition AI 153 is an AI that receives sensing data acquired by the sensor unit 110 as input data and outputs a topology map for the position where the sensing data was acquired. The lane topology recognition AI 153 is trained by the AI ​​control unit 147 (described later) so as to be able to output a local topology map with user tendencies that reflects the user's driving tendencies.

[0049] <<3. Detailed Functions of the Vehicle 10>> Next, the functions of the vehicle 10 according to this embodiment will be described in detail.

[0050] <3.1. Generation of local topology map> First, a method for generating the local topology map 151 will be described with reference to Fig. 4. Fig. 4 is a diagram for explaining the method for generating the local topology map 151. In generating the local topology map 151, the surrounding information recognition unit 141, the self-position estimation unit 142, the local HD map generation unit 143, the reliability calculation unit 144, and the map integration unit 145 mainly perform processing.

[0051] (Surrounding Information Recognition Unit 141) The surrounding information recognition unit 141 processes sensing data of the surrounding environment of the vehicle 10 obtained by the sensor unit 110. The surrounding information recognition unit 141 recognizes road information such as crosswalks, road boundaries, and lane dividing lines.

[0052] Here, the surrounding information recognition unit 141 may recognize road information based on an SD map of the surrounding area where the sensing data is obtained.

[0053] For example, the surrounding information recognition unit 141 may acquire road information using a recognizer that has been trained in advance to output road information using sensing data of the surrounding environment of the vehicle 10 as input data. For example, the surrounding information recognition unit 141 may acquire road information by inputting sensing data of the surrounding environment of the vehicle 10 acquired by the camera, radar, and LiDAR that configure the sensor unit 110 into the recognizer.

[0054] The surrounding information recognition unit 141 may acquire sensing data of the surrounding environment of the vehicle 10 at predetermined time intervals. For example, Fig. 4 shows an example in which time T1 sensing data SD1, time T2 sensing data SD2, ..., and time Tn sensing data SDn are acquired at time T1, time T2, ..., and time Tn (n is a natural number; the same applies hereinafter). The surrounding information recognition unit 141 may acquire road information corresponding to each time based on the respective sensing data.

[0055] (Self-position estimation unit 142) The self-position estimation unit 142 estimates the self-position of the vehicle 10 based on road information recognized by the surrounding information recognition unit 141 and sensing data related to the vehicle 10. For example, FIG. 4 shows an example in which position information LD acquired by a GNSS sensor constituting the sensor unit 110 is input to the self-position estimation unit 142 as sensing data related to the vehicle. However, the sensing data related to the vehicle is not limited to the position information LD, and may include the number of rotations of the wheels acquired by a wheel speed sensor, the steering angle of the steering wheel of the vehicle 10 acquired by a steering angle sensor, the acceleration and angular velocity of the vehicle 10 acquired by the IMU, etc. Furthermore, the self-position estimation unit 142 may estimate the self-position of the vehicle 10 based only on sensing data related to the vehicle 10.

[0056] The self-position estimation unit 142 may acquire the self-position using, for example, an estimator that has been trained in advance to output the self-position using sensing data related to the vehicle as input data. For example, the self-position estimation unit 142 may acquire the self-position by inputting road information and position information LD into the estimator.

[0057] The self-position estimation unit 142 may acquire sensing data related to the vehicle acquired at predetermined time intervals. The self-position estimation unit 142 may also acquire road information generated by the surrounding information recognition unit 141 at predetermined time intervals. The self-position estimation unit 142 may then estimate the self-position of the vehicle 10 at each time based on the acquired sensing data related to the vehicle and the road information at each time. The self-position estimation unit 142 derives the trajectory of the continuously acquired self-position as the traveling trajectory of the vehicle 10.

[0058] (Local HD Map Generator 143) The local HD map generator 143 generates an HD map indicating each piece of road information by integrating the road information recognized by the surrounding information recognizer 141. Such an HD map unique to each vehicle 10 is also referred to as a "local HD map" hereinafter. The local HD map generator 143 generates a local HD map corresponding to each piece of road information recognized by the surrounding information recognizer 141 corresponding to each time.

[0059] (Reliability Calculation Unit 144) The reliability calculation unit 144 calculates the reliability of the local HD map corresponding to each time generated by the local HD map generation unit 143. The reliability may be calculated based on, for example, whether or not there is a contradiction in the sensing data from the multiple sensors that make up the sensor unit 110. For example, if it is determined that different objects are captured in an image that is sensing data from a camera and a point cloud that is sensing data from LiDAR, the reliability may be calculated to be lower. Furthermore, the reliability may be calculated based on the weather when the sensing data was acquired, etc.

[0060] (Map Integration Unit 145) The map integration unit 145 generates a local topology map 151 by combining the local HD maps generated by the local HD map generation unit 143.

[0061] Based on the reliability calculated by the reliability calculation unit 144, the map integration unit 145 determines whether or not to use an HD map corresponding to each reliability in generating the local topology map 151. For example, the map integration unit 145 may align and combine multiple local HD maps obtained within a predetermined time period and having corresponding reliability levels equal to or greater than a threshold.

[0062] If multiple HD maps are inconsistent, the map integration unit 145 may not generate the local topology map 151 using the multiple HD maps. Furthermore, if multiple HD maps are inconsistent, the map integration unit 145 may generate the local topology map 151 by excluding the inconsistent local HD maps. The consistency may be determined, for example, based on an overlap degree indicating the degree of overlap between the multiple local HD maps. The overlap degree may be calculated so that it decreases as the deviation between the lines indicated by the road information included in each HD map increases.

[0063] Here, it is assumed that there is a local HD map that is inconsistent due to lighting changes, occlusion, or the like, and that a region of the local HD map is included in the already-generated local topology map 151. In this case, the map integration unit 145 may use a map of the region in the already-generated local topology map 151 that corresponds to the inconsistent local HD map. More specifically, if the data for that region in the already-generated local topology map 151 is consistent with the multiple HD maps generated by the local HD map generation unit 143, the data for that region in the already-generated local topology map 151 may be used. Alternatively, if there is a local HD map that is inconsistent due to lighting changes, occlusion, or the like, the map integration unit 145 may correct the local HD map in accordance with parameters such as illuminance. Then, the map integration unit 145 may use the corrected local HD map to generate the local topology map 151.

[0064] The map integration unit 145 superimposes the driving trajectory acquired by the self-position estimation unit 142 as a driving line on the combined local HD map. Here, the driving line in a location where no lanes are set serves as information indicating the connection of lanes in that location. Examples of a location where no lanes are set include intersections where there are no lane dividing lines or alleys where there are no dividing lines that serve as road boundaries.

[0065] The map integration unit 145 generates the local topology map 151 by reflecting the map generated in this manner in the area of ​​the local topology map 151 that corresponds to the combined local HD map. Note that if data already exists for the area in the local topology map 151, the data may be updated to the latest data, or an average traveling trajectory may be generated and the traveling line may be updated to the generated traveling trajectory.

[0066] The method for generating the local topology map 151 has been described above with reference to FIG. 4 . The communication unit 120 may acquire from the server 20 a global topology map corresponding to an updated area in the local topology map 151. The map integration unit 145 may then align the updated area in the local topology map 151 with the acquired global topology map and compare the maps at the same position. The map integration unit 145 may correct the local topology map 151 so that differences in the maps due to the influence of lighting, etc., do not appear when comparing the maps. If there is a difference, the map integration unit 145 may transmit information about the difference to the server 20. The server 20 may update the global topology map to the road information included in the local topology map 151 based on the received information about the difference. The comparison process may be performed by the server 20.

[0067] (Example of Operation for Generating Local Topology Map) Next, a description will be given of an example of operation of the vehicle 10 in generating the local topology map 151. FIG.

[0068] First, the surrounding information recognition unit 141 recognizes road information around the vehicle 10 by processing sensing data of the surrounding environment of the vehicle 10 (S101). The local HD map generation unit 143 generates an HD map indicating each piece of road information by integrating the road information recognized by the surrounding information recognition unit 141 (S102).

[0069] The map integration unit 145 determines whether the reliability calculated by the reliability calculation unit 144 is equal to or greater than a threshold (S103). If the reliability is equal to or greater than the threshold (YES in S103), the process proceeds to S105. If the reliability is less than the threshold (NO in S103), the local HD map corresponding to the reliability less than the threshold is filtered (S104).

[0070] The map integration unit 145 determines whether or not a local HD map for a predetermined time period has been generated by the local HD map generation unit 143 (S105). If a local HD map for a predetermined time period has not been generated (S105 / NO), the process of S101 to S104 is repeated until a local HD map for a predetermined time period has been generated.

[0071] If the local HD maps for the predetermined time period have been generated (YES in S105), the map integration unit 145 aligns the multiple local HD maps (S106). Next, the map integration unit 145 determines whether the overlap degree of the multiple local HD maps is equal to or greater than a threshold (S107). If the overlap degree of the multiple local HD maps is less than the threshold (NO in S107), the process returns to S101.

[0072] If the degree of overlap between the multiple local HD maps is equal to or greater than a threshold (YES in S107), the map integration unit 145 superimposes the driving trajectory acquired by the self-position estimation unit 142 as a driving line on the map obtained by combining the multiple local HD maps. The map integration unit 145 saves the local topology map 151 that reflects the topology map generated by superimposing the driving line (S108).

[0073] Following S108, the server 20 transmits the local topology map 151 to update the global topology map. Fig. 6 is a flowchart showing an example of the operation of the vehicle 10 when the server 20 transmits the local topology map 151 to update the global topology map.

[0074] The communication unit 120 acquires from the server 20 a global topology map corresponding to the updated (saved) region in the local topology map 151 (S109). The map integration unit 145 aligns the region saved in the local topology map 151 with the acquired global topology map (S110). The map integration unit 145 also corrects the local topology map 151 so that differences in the maps due to the influence of lighting, etc., do not appear when comparing the maps (S111).

[0075] The map integration unit 145 compares the local topology map 151 and the global topology map at the same location to determine whether they are similar (S112). If the local topology map 151 and the global topology map at the same location are similar (S112 / YES), the processing ends. If the local topology map 151 and the global topology map at the same location are not similar (S112 / NO), the communication unit 120 transmits information on the differences between the maps to the server 20 (S113). Based on the received information on the differences, the server 20 may update the global topology map to the road information included in the local topology map 151.

[0076] 3.2. Learning of Lane Topology Recognition AI Next, a learning method of the lane topology recognition AI will be described with reference to Fig. 7. Fig. 7 is a diagram for explaining the learning method of the lane topology recognition AI. In learning of the lane topology recognition AI, the map integration unit 145, weight calculation unit 146A, subjective evaluation processing unit 146B, tendency integration unit 146C, and AI learning unit 147A mainly perform processing.

[0077] (Weight Calculation Unit 146A) The weight calculation unit 146A calculates a weight corresponding to the sensing data based on the sensing data acquired by the sensor unit 110. A weight is assigned to each position of the local topology map 151 according to the user's tendency to drive the vehicle 10, for the purpose of training the lane topology recognition AI 153 according to the user's tendency to drive the vehicle 10. More specifically, the weight may be a value assigned to better incorporate the user's tendency to drive the vehicle 10 when training the lane topology recognition AI 153.

[0078] For example, the weight calculation unit 146A may acquire sensing data on the state of the user and sensing data on the vehicle from the sensor unit 110.

[0079] The weight calculation unit 146A may then evaluate the stress on the user based on the sensing data. The weight calculation unit 146A may calculate a weight corresponding to the sensing data by converting a stress value representing the evaluated stress.

[0080] Calculation of weights corresponding to sensing data will be described with reference to Fig. 8 and Fig. 9. Fig. 8 is a diagram for explaining calculation of a user's stress value based on sensing data. In Fig. 8, an example of sensing data including the user's heart rate, which is sensing data on the user's state, a captured image of the user, and the vehicle vibration frequency of the vehicle 10, which is sensing data related to the vehicle, will be described.

[0081] The weight calculation unit 146A may evaluate the state of the user from each piece of sensing data. For example, the weight calculation unit 146A may evaluate the user's tension level as a tension level evaluation value by recognizing the user's facial expression in a captured image of the user.

[0082] The weight calculation unit 146A calculates the stress value by integrating the values ​​indicated by the respective sensing data or the values ​​evaluated from the respective sensing data. Specifically, the change in the stress value over time may be calculated based on a calculation formula using the values ​​indicated by the respective sensing data or the values ​​evaluated from the respective sensing data as parameters. For example, FIG. 8 shows an example in which the calculated stress value increases due to a change in the values ​​indicated by the respective sensing data or the values ​​evaluated from the respective sensing data caused by sudden braking.

[0083] The weight calculation unit 146A may convert the stress value into a weight using a conversion table. Fig. 9 is a diagram showing a graph of an example of a conversion table of stress values ​​and weights. As shown in Fig. 9, the stress value may be converted into a weight that is a value between 0 and 1. In the graph shown in Fig. 9, the higher the stress value, the lower the weight.

[0084] The calculation of weights by the weight calculation unit 146A has been described above. The map integration unit 145 acquires the weights calculated by the weight calculation unit 146A. Then, the map integration unit 145 assigns weights to the points at which sensing data has been acquired.

[0085] The map integration unit 145 assigns weights calculated by the trend processing unit 146 to points at which sensing data is acquired in the local topology map 151 generated based on the local HD map generated by the local HD map generation unit 143 and the traveling trajectory of the vehicle 10 acquired by the self-position estimation unit 142. Here, the map integration unit 145 may generate maps corresponding to the respective local sections for which weights are calculated.

[0086] Although the example described here is one in which the generation of the local topology map 151 and the weighting process are performed independently, the weighting process may be performed in parallel with the process of generating the local topology map 151. For example, the weighting process may be performed when the map integration unit 145 combines local HD maps in the generation of the local topology map 151.

[0087] (Subjective evaluation processing unit 146B) The subjective evaluation processing unit 146B calculates weights corresponding to ranges for the driving process based on feedback representing the user's subjective evaluation of the driving process using the vehicle 10. For example, the user may provide feedback on the ride comfort of the vehicle 10, the degree of motion sickness, or the quality of the scenery during the driving process. Furthermore, user feedback may be received for multiple items. User feedback is received, for example, by the operation display unit 130.

[0088] 10 is a diagram showing an example of a display screen displayed on the operation display unit 130 and used to receive feedback from the user. As shown in FIG. 10, the operation display unit 130 displays a travel process 1301 that shows an overview of the travel process, and a feedback input bar 1302 for inputting feedback on the ride comfort of the vehicle 10 during the travel process. The travel process 1301 shows the travel process from a departure point (S) to an arrival point (E). The feedback input bar 1302 is a bar that allows the user to input an evaluation value from 0 to 100 on the ride comfort of the vehicle 10 during the travel process.

[0089] The subjective evaluation processing unit 146B links the driving process with an evaluation value, which is feedback from the user on the driving process, and outputs the linked evaluation value to the tendency integration unit 146C. The subjective evaluation processing unit 146B may further link the date, time period, weather, road congestion status, etc., when the vehicle 10 traveled the driving process to the tendency integration unit 146C.

[0090] (Tendency Integration Unit 146C) The tendency integration unit 146C functions as a generation unit that generates a local topology map 152 with user tendencies based on the maps corresponding to the respective local sections generated by the map integration unit 145 and user feedback on the driving process acquired from the subjective evaluation processing unit 146B.

[0091] More specifically, the trend integration unit 146C functions as a weighting unit that assigns weights to each position in the local topology map 151 based on the maps corresponding to each local section and the user's feedback on the driving process obtained from the subjective evaluation processing unit 146B.

[0092] The tendency integration unit 146C assigns weights to points at which sensing data was acquired, which are represented by maps corresponding to each local section, in the local topology map 151. The tendency integration unit 146C also assigns weights to ranges corresponding to travel routes linked to evaluation values ​​in the local topology map 151. The tendency integration unit 146C may assign weights using evaluation values ​​as weights, or may convert evaluation values ​​into weights using a conversion table or the like.

[0093] Furthermore, when the tendency integration unit 146C acquires information such as the date, time period, weather, and road congestion status when the vehicle 10 travels a travel process, the tendency integration unit 146C may associate this information with the travel process and store it in a database. Such a database may be transmitted to an external server or the like and used for big data analysis.

[0094] (AI learning unit 147A) The AI ​​learning unit 147A performs learning using the local topology map with user tendencies 152 as training data, thereby learning the lane topology recognition AI 153. The AI ​​learning unit 147A uses a weight assigned to each position in the local topology map with user tendencies 152 to better incorporate the driving tendencies of the user at that position.

[0095] More specifically, the AI ​​learning unit 147A learns the lane topology recognition AI 153 so that the driving line reflects the user's driving tendency. As a result, the lane topology recognition AI 153 is trained as a lane topology recognition AI that can output an AI-recognition topology map that reflects the user's driving tendency.

[0096] Here, the lane topology recognition AI 153 before learning by the AI ​​learning unit 147A may be a recognizer that outputs a topology map including a general-purpose driving line. The lane topology recognition AI 153 before learning by the AI ​​learning unit 147A may be acquired in advance from an external source, such as the server 20.

[0097] (Map Generation Unit 147B) The lane topology recognition AI 153 learned by the AI ​​learning unit 147A is used to generate an AI-recognized topology map by the map generation unit 147B. Fig. 11 is a diagram for explaining generation of an AI-recognized topology map by the map generation unit 147B.

[0098] The map generation unit 147B acquires sensing data SD acquired by the sensor unit 110. The sensing data SD may be sensing data of the surrounding environment of the vehicle 10, such as an image or a point cloud, acquired by the sensor unit 110.

[0099] The map generation unit 147B generates the AI-recognition topology map M by acquiring the AI-recognition topology map M output by inputting the sensing data SD to the lane topology recognition AI 153. Here, the AI-recognition topology map M includes each piece of information shown in the legend Mn shown in FIG.

[0100] The AI-recognition topology map M shows a driving line that reflects the driving tendencies of the user and is suitable as a driving trajectory around the vehicle's own position. By using such an AI-recognition topology map M to control the automatic driving of the vehicle 10 in real time along the driving line, it becomes possible to perform automatic driving of the vehicle 10 while reflecting the user's tendencies, thereby improving user satisfaction with automatic driving.

[0101] (Example of Learning Operation of Lane Topology Recognition AI) Next, a description will be given of an example of the operation of the vehicle 10 in learning the lane topology recognition AI 153. FIG.

[0102] First, the weight calculation unit 146A calculates weights corresponding to the sensing data based on the sensing data acquired by the sensor unit 110 (S201). Then, the map integration unit 145 generates maps corresponding to the local sections for which weights have been calculated, thereby weighting the local sections (S202).

[0103] The subjective evaluation processing unit 146B determines whether the vehicle 10 has finished traveling (S203). For example, the subjective evaluation processing unit 146B may determine that the vehicle 10 has finished traveling when the engine of the vehicle 10 has stopped. If the vehicle 10 has not finished traveling (S203 / NO), the process returns to S201, and the processes of S201 and S202 are repeated until the vehicle 10 has finished traveling. If the vehicle 10 has finished traveling (S203 / YES), the subjective evaluation processing unit 146B controls the display of the operation display unit 130 to receive feedback from the user about the completed traveling process (S204).

[0104] The tendency integration unit 146C generates a local topology map 152 with user tendencies that reflects the user's tendencies based on the map generated by the map integration unit 145 and the user's feedback on the driving process obtained from the subjective evaluation processing unit 146B (S205).

[0105] The AI ​​learning unit 147A performs learning using the local topology map 152 with user tendencies as training data, thereby training the lane topology recognition AI 153 (S206).

[0106] <<4. Configuration Example of Server 20>> Next, a configuration example of the server 20 according to this embodiment will be described with reference to Fig. 13. Fig. 13 is a block diagram showing the functional configuration of the server 20 according to this embodiment.

[0107] As shown in FIG. 13, the server 20 according to this embodiment includes a communication unit 210, a storage unit 220, and a control unit 230.

[0108] (Communication Unit 210) The communication unit 210 communicates information with the vehicles 10 via the network 30. The communication unit 210 acquires, for example, an AI-recognized topology map that is generated by each vehicle 10 and reflects the tendencies of the users corresponding to each vehicle 10.

[0109] (Storage Unit 220) The storage unit 220 stores various data used by the server 20. In addition, as shown in FIG.

[0110] (Global Topology Map 221) The global topology map 221 is a general-purpose topology map and may include, for example, driving lines appropriate for driving the vehicle 10. More specifically, the global topology map 221 may include driving lines with lower risk provided by an insurance company.

[0111] (Risk DB 222) The risk DB 222 is a database that accumulates driving risks of each user corresponding to each vehicle 10. The driving risks of each user will be described in detail later.

[0112] (Control unit 230) The control unit 230 functions as an arithmetic processing unit and a control device, and controls the overall operation of the server 20 in accordance with various programs. The control unit 230 according to this embodiment also functions as a map search unit 231, a difference calculation unit 232, a risk calculation unit 233, and a statistics unit 234. Details of the map search unit 231, the difference calculation unit 232, the risk calculation unit 233, and the statistics unit 234 will be described later.

[0113] <<5. Detailed Functions of the Server 20>> Next, the functions of the server 20 according to this embodiment will be described in detail. The server 20 calculates and compiles statistics on the driving risk of each user based on the difference between the global topology map 221 and the AI-recognized topology map that reflects the tendencies of the user corresponding to each vehicle 10, which is acquired from each vehicle 10.

[0114] 14 is a diagram for explaining a method for calculating and statistic-generating the driving risk of each user. Here, the map search unit 231, the difference calculation unit 232, the risk calculation unit 233, and the statistics unit 234 mainly execute the processing.

[0115] (Map search unit 231) The map search unit 231 acquires the AI-recognized topology map generated by the map generation unit 147B of the vehicle 10 based on the sensing data SD, via the communication unit 210. Then, the map search unit 231 searches the global topology map 221, and identifies a driving line in the global topology map 221 that is in the same range as the AI-recognized topology map.

[0116] (Difference calculation unit 232) The difference calculation unit 232 calculates the difference between a driving line in the same range as the AI-recognized topology map in the global topology map 221 acquired by the map search unit 231 and the driving line in the AI-recognized topology map. The difference calculation unit 232 obtains the difference, for example, by comparing corresponding vector information representing each driving line.

[0117] (Risk Calculation Unit 233) The risk calculation unit 233 calculates a risk value indicating the risk for the driving line based on the difference calculated by the difference calculation unit 232. If the driving line in the global topology map 221 is a driving line with a lower risk, the risk value may be calculated to be larger as the difference increases.

[0118] The risk calculation unit 233 stores the calculated risk value for each user in the risk DB 222 .

[0119] (Statistical Unit 234) The statistical unit 234 calculates the risk for each user based on the risk values ​​stored in the risk DB 222. The statistical unit 234 may perform statistical processing by, for example, averaging the risk values.

[0120] The statistical results of the risk for each user may be used, for example, to calculate vehicle insurance premiums. For example, vehicle insurance premiums may be calculated so that the lower the average risk value, the lower the vehicle insurance premium. This makes it possible to calculate appropriate vehicle insurance premiums for each user, thereby improving the usefulness of the information processing system 1 for insurance companies.

[0121] The statistical results of the risk for each user may be presented to the user. Furthermore, advice on how to improve the user's driving may be further presented to the user based on the difference obtained by the difference calculation unit 232. The statistical results of the risk for each user and the advice on how to improve the user's driving may be displayed on the operation display unit 130 of the vehicle 10 after being transmitted from the communication unit 210 to the vehicle 10, for example.

[0122] The above description has been given of an example in which a risk value is calculated by comparing the AI-recognized topology map acquired from each vehicle 10 with the global topology map 221. However, the map compared with the global topology map 221 may be the local topology map 152 with user tendencies generated by the vehicle 10.

[0123] (Example of operation of calculating and stating driving risk of each user) Next, an example of operation of the server 20 in calculating and stating driving risk of each user will be described. Fig. 15 is a flowchart showing an example of operation of the server 20 in calculating and stating driving risk of each user.

[0124] First, the communication unit 210 acquires an AI-recognized topology map recognized by the lane topology recognition AI from each vehicle 10 (S301). The map search unit 231 searches the global topology map 221 to identify a driving line in the global topology map 221 that is in the same range as the AI-recognized topology map (S302).

[0125] The difference calculation unit 232 calculates the difference between the driving line in the same range as the AI-recognized topology map in the global topology map 221 identified by the map search unit 231 and the driving line in the AI-recognized topology map (S303). The risk calculation unit 233 calculates a risk value indicating the risk to the driving line according to the difference calculated by the difference calculation unit 232 (S304). The risk calculation unit 233 accumulates the calculated risk value for each user in the risk DB 222.

[0126] The statistics unit 234 determines whether or not risks have accumulated in the risk DB 222 to a standard value or more (S305). The statistics unit 234 may determine whether or not a predetermined number of risks have accumulated for each user, or may determine whether or not risks corresponding to a driving line of a predetermined distance or more have accumulated.

[0127] If the risk DB 222 does not contain the risk equal to or exceeds the standard (S305 / NO), the process returns to S301, and the processes of S301 to S304 are repeated. If the risk DB 222 contains the risk equal to or exceeds the standard (S305 / YES), the statistics unit 234 calculates the risk for each user based on the risk contained in the risk DB 222 (S306).

[0128] <<6. Example Architecture>> Next, an example of an architecture for realizing the processing according to this embodiment will be described. Fig. 16 is a diagram showing an example of an architecture for realizing the processing according to this embodiment.

[0129] First, estimation of panoptic segmentation by sensor fusion using the camera 1101 and LiDAR 1103 will be described.

[0130] The RGB image acquired by the camera 1101 is subjected to feature extraction (RGB image feature extraction).

[0131] First, depth conversion is performed on the 3D point cloud acquired by the LiDAR 1103. Depth conversion is a process of converting the 3D point cloud acquired by the LiDAR 1103 into a 2D depth image. Next, feature extraction (depth image feature extraction) is performed from the depth image acquired as described above.

[0132] The RGB image feature extraction and the depth image feature extraction may be performed using a network configuration using a CNN (Convolutional Neural Network), a Deformable CNN, or a Transformer. A pixel decoder may be added after the CNN or the Transformer to aggregate features between multiscales. The network for extracting the depth image feature and the network for extracting the RGB image feature may be prepared separately or may be the same.

[0133] Next, feature fusion is performed to fuse the depth image feature and the RGB image feature, and fusion features are obtained.

[0134] The fusion feature obtained as described above is input to the segmentation head, which is an output device that performs segmentation on the image region mask. The segmentation head outputs the results of semantic segmentation and instance segmentation.

[0135] Next, estimation of depth, 3D bounding box (3DBBox), velocity, and lane topology by sensor fusion using camera 1101, radar 1102, and LiDAR 1103 will be described.

[0136] First, the extracted fusion feature amount and camera parameters are input to the depth head, and an estimated depth is output.

[0137] The above camera parameters are various parameters for projecting the point cloud of LiDAR 1103 onto an RGB image, and include information such as the attitude (rotation matrix) and position (translation vector) of camera 1101, focal length, and center position of the lens.

[0138] Next, a Bird's Eye View (BEV) transform is performed based on the depth estimated as described above.

[0139] On the other hand, radar feature extraction is performed on the point cloud acquired by the radar 1102, and BEV Transform is performed based on the extracted radar feature.

[0140] Next, BEV feature fusion is performed based on the results of the depth-based BEV Transform and the radar feature-based BEV Transform, and the resulting fusion feature is input to a 3D Detection Head to obtain 3D BBox and velocity estimation results.Furthermore, the resulting fusion feature is input to a Lane Topology Head to obtain lane topology estimation results and their reliability.

[0141] Next, estimation of an HD map by sensor fusion using the camera 1101, radar 1102, LiDAR 1103, and SD map 1301 will be described.

[0142] The SD map 1301 is input to a map encoder and converted into a format that can be input to a map decoder. The converted SD map 1301 and the fusion feature obtained by BEV feature fusion are input to the map decoder, whereby an HD map is obtained.

[0143] 7. Hardware Configuration Example>> Each embodiment of the present disclosure has been described above. The above-described information processing is realized by cooperation between software and hardware. Below, a hardware configuration example that can be applied to the vehicle 10 and the server 20 will be described.

[0144] Fig. 17 is a block diagram showing an example of an information processing device 90. Note that the hardware configuration example of the information processing device 90 described below is merely an example of the hardware configuration of the vehicle 10 and the server 20. Therefore, the vehicle 10 and the server 20 do not necessarily have to have the entire hardware configuration shown in Fig. 17 . Furthermore, the vehicle 10 and the server 20 may not necessarily have some of the hardware configuration shown in Fig. 17 .

[0145] 17 , the information processing device 90 includes a CPU 901, a ROM (Read Only Memory) 903, and a RAM 905. The information processing device 90 may also include a host bus 907, a bridge 909, an external bus 911, an interface 913, an input device 915, an output device 917, a storage device 919, a drive 921, a connection port 923, and a communication device 925. Instead of or in addition to the CPU 901, the information processing device 90 may include a processing circuit such as a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), or an ASIC (Application Specific Integrated Circuit).

[0146] The CPU 901 functions as an arithmetic processing unit and control unit, and controls all or part of the operations within the information processing device 90 in accordance with various programs recorded in the ROM 903, RAM 905, storage device 919, or removable recording medium 927. The ROM 903 stores programs and calculation parameters used by the CPU 901. The RAM 905 temporarily stores programs used in the execution of the CPU 901 and / or parameters that change as appropriate during the execution. The CPU 901, ROM 903, and RAM 905 are interconnected by a host bus 907, which is composed of an internal bus such as a CPU bus. Furthermore, the host bus 907 is connected to an external bus 911, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 909.

[0147] The CPU 901, in cooperation with the ROM 903, RAM 905, and software, can realize the functions of the control unit 140 and the control unit 230, for example.

[0148] The input device 915 is a device operated by a user, such as a button. The input device 915 may include a mouse, a keyboard, a touch panel, a switch, a lever, or the like. The input device 915 may also include a microphone that detects the user's voice. The input device 915 may be, for example, a remote control device that uses infrared or other radio waves, or an externally connected device 929 such as a mobile phone that supports operation of the information processing device 90. The input device 915 includes an input control circuit that generates an input signal based on information input by the user and outputs the signal to the CPU 901. The user operates the input device 915 to input various data and instruct processing operations to the information processing device 90.

[0149] The input device 915 may also include an imaging device and a sensor. The imaging device is a device that captures real space and generates a captured image using an imaging element such as a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor, and various components such as a lens for controlling the formation of a subject image on the imaging element. The imaging device may capture still images or may capture moving images.

[0150] The sensors include various types of sensors, such as a distance measurement sensor, an acceleration sensor, a gyro sensor, a geomagnetic sensor, a vibration sensor, a light sensor, and a sound sensor. The sensors acquire information about the state of the information processing device 90 itself, such as the attitude of the housing of the information processing device 90, or information about the surrounding environment of the information processing device 90, such as the brightness or noise around the information processing device 90. The sensors may also include a GNSS sensor that receives GNSS signals and measures the latitude, longitude, and altitude of the device.

[0151] The output device 917 is configured with a device capable of visually or audibly notifying the user of acquired information. The output device 917 may be, for example, a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display, or an audio output device such as a speaker or headphones. The output device 917 may also include a PDP (Plasma Display Panel), a projector, a hologram, a printer, or the like. The output device 917 outputs the results obtained by the processing of the information processing device 90 as video such as text or images, or as sound such as voice or audio. The output device 917 may also include a lighting device that brightens the surrounding area.

[0152] The storage device 919 is a data storage device configured as an example of a storage unit of the information processing device 90. The storage device 919 is configured, for example, by a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, or a magneto-optical storage device. This storage device 919 stores programs or various data executed by the CPU 901, as well as various data acquired from the outside.

[0153] The drive 921 is a reader / writer for a removable recording medium 927 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and is built into or externally attached to the information processing device 90. The drive 921 reads information recorded on the attached removable recording medium 927 and outputs the information to the RAM 905. The drive 921 also writes information to the attached removable recording medium 927.

[0154] The connection port 923 is a port for directly connecting a device to the information processing device 90. The connection port 923 may be, for example, a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, or the like. The connection port 923 may also be an RS-232C port, an optical audio terminal, an HDMI (registered trademark) (High-Definition Multimedia Interface) port, or the like. By connecting an external device 929 to the connection port 923, various types of data can be exchanged between the information processing device 90 and the external device 929.

[0155] The communication device 925 is a communication interface configured with a communication device for connecting to a network 931, such as a local network or a communication network with a wireless communication base station. The communication device 925 may be, for example, a wired or wireless LAN, Bluetooth, Wi-Fi, or a communication card for WUSB (Wireless USB). The communication device 925 may also be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various communications. The communication device 925 transmits and receives signals, for example, between the Internet and other communication devices using a predetermined protocol such as TCP / IP. The local network or communication network with the base station connected to the communication device 925 is a wired or wireless network, such as the Internet, a home LAN, infrared communication, radio wave communication, or satellite communication.

[0156] <<8. Supplementary Information>> Although preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person skilled in the art of the present disclosure can conceive of various modified or altered examples within the scope of the technical idea described in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

[0157] For example, although the above describes an example in which the information processing system 1 is realized by the vehicle 10 and the server 20, the information processing system 1 may be realized by either the vehicle 10 or the server 20. Furthermore, part of the configuration included in the vehicle 10 may be provided in the server 20, or part of the configuration included in the server 20 may be provided in the vehicle 10.

[0158] It is also possible to create a computer program for causing hardware such as a CPU, ROM, and RAM built into the vehicle 10 or the server 20 to perform the functions of the vehicle 10 or the server 20. A computer-readable storage medium storing the computer program is also provided.

[0159] Furthermore, the effects described herein are merely descriptive or exemplary and are not limiting. In other words, the technology according to the present disclosure may achieve other effects that will be apparent to those skilled in the art from the description of this specification, in addition to or in place of the above-described effects.

[0160] The following configurations also fall within the technical scope of the present disclosure. (1) An information processing system comprising: a generating unit that generates a first topology map, which is a topology map of lanes corresponding to a traveling vehicle, based on driving data acquired by the vehicle; and a weighting unit that, for learning using the first topology map, assigns a weight in the learning to each position of the first topology map in accordance with a user's tendency to drive the vehicle. (2) The information processing system described in (1), in which the weighting unit assigns a weight to a point at which sensing data was acquired based on sensing data acquired by the vehicle. (3) The information processing system described in (2), in which the weighting unit assigns a weight to a point at which sensing data was acquired by evaluating stress on the user based on the sensing data. (4) The information processing system described in (2) or (3), in which the sensing data includes a sensing result of the user's state. (5) The information processing system described in any of (2) to (4), in which the sensing data includes a sensing result related to the vehicle. (6) The information processing system according to any one of (1) to (5), wherein the weighting unit weights a range corresponding to a travel journey of the vehicle based on feedback from the user regarding the travel journey of the vehicle. (7) The information processing system according to any one of (1) to (6), wherein the generation unit generates the first topology map by combining multiple maps, each including information indicating lane separation lines, road boundaries, and crosswalks, generated from the travel data acquired for each time series. (8) The information processing system according to (7), wherein the first topology map includes information indicating the connection of lanes in places where lanes are not set, and the generation unit generates the information indicating the connection of lanes based on a travel trajectory of the vehicle.(9) The information processing system according to (7) or (8), wherein the information processing system includes a reliability calculation unit that calculates a reliability for each of the plurality of maps, and the generation unit determines, based on the reliability calculated by the reliability calculation unit, whether or not to use the map corresponding to the reliability for generating the first topology map. (10) The information processing system according to any of (1) to (9), wherein the information processing system further includes a learning unit that uses sensor data from a traveling vehicle as input data and trains a recognizer that outputs a second topology map to be used as a trajectory along which the vehicle travels, and the learning unit performs learning using the first topology map that has been weighted by the weighting unit. (11) The information processing system according to (10), further includes a risk calculation unit that calculates a risk of driving by the user based on a difference between the second topology map and a predetermined topology map at the same position. (12) The information processing system according to (11), further comprising a statistics unit that calculates statistics of accumulated data of the risks calculated by the risk calculation unit. (13) An information processing method executed by a computer, comprising: generating a first topology map that is a topology map of lanes corresponding to a traveling vehicle based on driving data acquired by the traveling vehicle; and, for learning using the first topology map, weighting each position of the first topology map in the learning in accordance with a user's tendency to drive the vehicle.

[0161] DESCRIPTION OF SYMBOLS 1 Information processing system 10 Vehicle 120 Communication unit 130 Operation display unit 140 Control unit 141 Surrounding information recognition unit 142 Self-position estimation unit 143 Local HD map generation unit 144 Reliability calculation unit 145 Map integration unit 146 Trend processing unit 146A Weight calculation unit 146B Subjective evaluation processing unit 146C Trend integration unit 147 AI control unit 147A AI learning unit 147B Map generation unit 150 Memory unit 151 Local topology map 152 Local topology map with user tendency 153 Lane topology recognition AI 20 Server 210 Communication unit 220 Memory unit 221 Global topology map 222 Risk DB 230 Control unit 231 Map search unit 232 Difference calculation unit 233 Risk calculation unit 234 Statistics Department

Claims

1. An information processing system comprising: a generation unit that generates a first topology map, which is a topology map of lanes corresponding to a traveling vehicle, based on driving data acquired by the vehicle; and a weighting unit that, for learning using the first topology map, assigns weights to each position of the first topology map in accordance with the user's tendency to drive the vehicle.

2. The information processing system according to claim 1, wherein the weighting unit weights the location at which the sensing data was acquired based on the sensing data acquired by the vehicle.

3. The information processing system according to claim 2, wherein the weighting unit weights the location where the sensing data was acquired by evaluating the stress on the user based on the sensing data.

4. The information processing system according to claim 2, wherein the sensing data includes a result of sensing the state of the user.

5. The information processing system according to claim 2, wherein the sensing data includes sensing results relating to the vehicle.

6. The information processing system according to claim 1, wherein the weighting unit weights the range corresponding to the travel journey based on feedback from the user regarding the travel journey of the vehicle.

7. The information processing system of claim 1, wherein the generation unit generates the first topology map by combining multiple maps containing information indicating lane dividing lines, road boundaries, and crosswalks, generated from each of the driving data acquired in each time series.

8. The information processing system described in claim 7, wherein the first topology map includes information indicating the connection of the lanes in locations where no lanes are set, and the generation unit generates the information indicating the connection of the lanes based on the vehicle's driving trajectory.

9. The information processing system according to claim 7, further comprising a reliability calculation unit that calculates the reliability of each of the plurality of maps, and the generation unit determines, based on the reliability calculated by the reliability calculation unit, whether or not to use the map corresponding to the reliability in generating the first topology map.

10. The information processing system according to claim 1, further comprising a learning unit that uses sensing data from a moving vehicle as input data and trains a recognizer that outputs a second topology map that is used as a trajectory of the vehicle, and the learning unit performs learning using the first topology map that has been weighted by the weighting unit.

11. The information processing system according to claim 10, further comprising a risk calculation unit that calculates the risk of driving by the user based on the difference between the second topology map and a predetermined topology map at the same location.

12. The information processing system according to claim 11, further comprising a statistics section that compiles statistics on accumulated data of the risks calculated by the risk calculation section.

13. An information processing method executed by a computer, comprising: generating a first topology map, which is a topology map of lanes, corresponding to a traveling vehicle based on driving data acquired by the vehicle; and, for learning using the first topology map, weighting each position in the first topology map in the learning in accordance with the user's tendency to drive the vehicle.

Images