Autonomous driving vehicle
By integrating processors and memory in the vehicle, using the training model to simulate the reliability of traffic environment changes to candidate routes, the predictive problem of autonomous driving technology during environmental changes is solved, and efficient prediction and routes are achieved for whether autonomous driving is possible. choose.
Patent Information
- Application Number
- CN202410585900.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-22
- Filing Date
- 2024-05-13
- Publication Date
- 2024-11-22
AI Technical Summary
When the environment around the vehicle changes, the inference results of the training model may change, resulting in users needing to drive manually, and lacking predictability of the possibility of autonomous driving.
By integrating processor and memory in the vehicle, the training completion model for autonomous driving is used to simulate the reliability of traffic environment changes to candidate routes, and output simulation results to ensure the user's predictability of autonomous driving.
It provides high predictability of the ability of autonomous driving, helping users choose suitable routes to ensure the reliability of autonomous driving and avoid unnecessary manual driving operations.
Smart Images

Figure CN119002327A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to vehicles capable of autonomous driving. Background Art
[0002] In recent years, development of an autonomous driving technology has been advancing, which uses a trained model generated by machine learning to determine vehicle control based on data from onboard sensors, etc. Patent document 1 proposes a method for collecting training data that can be used in machine learning for generating a trained model.
[0003] Prior art literature
[0004] Patent Literature
[0005] Patent Document 1: International Publication No. 2019 / 116423
[0006] Patent Document 2: Japanese Patent Application Publication No. 2020-153939
[0007] Patent Document 3: Japanese Patent Application Publication No. 2019-074359
[0008] Patent Document 4: Japanese Patent Application Publication No. 2020-173264
[0009] However, if the environment around the vehicle changes, the inference results obtained by the trained model may change. Therefore, for example, the range in which the trained model can be used to appropriately perform vehicle control may change depending on the traffic environment such as weather, time period, and traffic volume. As a result, a scenario may occur in which a user who expects autonomous driving is forced to perform manual driving operations. Summary of the invention
[0010] One object of the present disclosure is to provide a technology for ensuring predictability of whether autonomous driving can be performed.
[0011] In order to achieve the above-mentioned purpose, the present disclosure provides a vehicle capable of automatic driving. The vehicle of the present disclosure comprises: at least one processor; and at least one memory storing a plurality of instructions executed by the at least one processor. The plurality of instructions cause the at least one processor to perform the following processing: select a candidate route to a destination, and obtain information related to the traffic environment of the selected candidate route. Then, the plurality of instructions cause the at least one processor to perform the following processing: based on the information related to the traffic environment, use a trained model for automatic driving to simulate the reliability of driving on the selected candidate route by automatic driving, and output the result of the simulation.
[0012] Effects of the Invention
[0013] Whether a vehicle can travel on a certain route through automatic driving depends on the traffic environment. In addition, the parameters of the trained model for automatic driving vary depending on the conditions under which the learning is performed. Therefore, even if the traffic environment is the same, not all vehicles can perform automatic driving, and conversely, not all vehicles can perform automatic driving. According to the vehicle disclosed in the present invention, by inputting information related to the traffic environment in the selected candidate route into the trained model for automatic driving, the reliability of driving on the candidate route through automatic driving can be simulated. And by outputting the results of the simulation, the predictability of the feasibility of automatic driving can be ensured for the user. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 This is a block diagram showing a configuration example associated with the automatic driving of a vehicle according to an implementation manner.
[0015] Figure 2 This is a conceptual diagram showing an example of the configuration of an automatic driving system according to an implementation method.
[0016] Figure 3 This is a block diagram showing a configuration example associated with a simulation of the reliability of autonomous driving according to an implementation method.
[0017] Figure 4A This is a conceptual diagram for explaining a first example of simulation results according to the embodiment.
[0018] Figure 4B This is a conceptual diagram for explaining a second example of the simulation result of the embodiment.
[0019] Figure 5A This is a conceptual diagram for explaining a third example of the simulation result of the embodiment.
[0020] Figure 5B This is a conceptual diagram for explaining a fourth example of the simulation result of the embodiment.
[0021] Fig. 6A and Figure 6B This is a conceptual diagram for explaining a fifth example of the simulation result of the embodiment.
[0022] Description of Reference Numerals
[0023] 1: Vehicle, 10: Sensor group, 20: Automatic driving device, 21: Identification unit, 22: Planning unit, 23: Control amount calculation unit, 25: Trained model, 30: Vehicle control device, 40: Display device, 50: Path planning unit, 60: Traffic environment information acquisition unit, 100: Automatic driving system, 120: Storage device, 150: Traffic environment information storage area, 200: Management server. DETAILED DESCRIPTION
[0024] 1. Autonomous driving of vehicles
[0025] Figure 1 This is a block diagram showing an example of a configuration associated with the automatic driving of the vehicle 1 of the present embodiment. Automatic driving refers to automatically performing at least one of steering, acceleration, and deceleration of the vehicle 1 without the aid of a driving operation performed by a user of the vehicle 1. Automatic driving is a concept that includes not only fully automatic driving but also risk avoidance control, lane keeping assist control, and the like.
[0026] The vehicle 1 includes a sensor group 10 , an automatic driving device 20 , and a vehicle control device 30 .
[0027] The sensor group 10 includes an identification sensor 11 for identifying the surrounding conditions of the vehicle 1. Examples of the identification sensor 11 include a camera, LiDAR (Laser Imaging Detection and Ranging), and a radar. In addition, the sensor group 10 may also include a state sensor 12 for detecting the state of the vehicle 1, a position sensor 13 for detecting the position of the vehicle 1, and the like. Examples of the state sensor 12 include a velocity sensor, an acceleration sensor, a yaw rate sensor, and a steering angle sensor. Examples of the position sensor 13 include a GNSS (Global Navigation Satellite System) sensor.
[0028] The sensor detection information SEN is information obtained by the sensor group 10. For example, the sensor detection information SEN includes an image captured by a camera. As another example, the sensor detection information SEN may also include point group information obtained by LiDAR. The sensor detection information SEN may also include vehicle state information indicating the state of the vehicle 1. The sensor detection information SEN may also include position information indicating the position of the vehicle 1.
[0029] The automatic driving device 20 includes a recognition unit 21 , a planning unit 22 , and a control amount calculation unit 23 .
[0030] The recognition unit 21 receives the sensor detection information SEN. The recognition unit 21 recognizes the surrounding conditions of the vehicle 1 based on the information obtained by the recognition sensor 11. For example, the recognition unit 21 recognizes objects around the vehicle 1. Examples of objects include pedestrians, other vehicles (preceding vehicles, parked vehicles, etc.), white lines, road structures (e.g., guardrails, curbs), fallen objects, traffic lights, intersections, signs, etc. The recognition result information RES indicates the recognition result obtained by the recognition unit 21. For example, the recognition result information RES includes object information indicating the relative position and relative speed of the object relative to the vehicle 1.
[0031] The planner 22 receives the recognition result information RES from the recognition unit 21. In addition, the planner 22 may also receive vehicle status information, position information, and pre-generated map information. The map information may be high-precision three-dimensional map information. The planner 22 generates a driving plan for the vehicle 1 based on the received information. The driving plan may be a plan for reaching a predetermined destination or a plan for avoiding risks. Examples of driving plans include maintaining the current driving lane, changing lanes, overtaking, turning right / left, steering, accelerating, decelerating, and stopping. Furthermore, the planner 22 generates a target trajectory TRJ required for the vehicle 1 to travel according to the driving plan. The target trajectory TRJ includes a target position and a target speed.
[0032] The control amount calculation unit 23 receives the target trajectory TRJ from the planning unit 22. The control amount calculation unit 23 calculates the control amount CON required for the vehicle to follow the target trajectory TRJ. The control amount CON can also be said to be a control amount requested to reduce the deviation between the vehicle 1 and the target trajectory TRJ. The control amount CON includes at least one of a steering control amount, a driving control amount, and a braking control amount.
[0033] The recognition unit 21 includes at least one of a rule-based model and a machine learning model. The rule-based model performs recognition processing based on a predetermined rule group. As machine learning models, NN (Neural Network), SVM (Support Vector Machine), regression model, decision tree model, etc. are exemplified. NN can also be CNN (Convolutional Neural Network), RNN (Recurrent Neural Network) or a combination thereof. The type, number of layers, and number of nodes of each layer in NN are arbitrary. The recognition unit 21 performs recognition processing by inputting sensor detection information SEN into the model. Recognition result information RES is output from the model, or recognition result information RES is generated based on the output from the model.
[0034] The planning unit 22 also includes at least one of a rule-based model and a machine learning model. The planning unit 22 performs planning processing by inputting recognition result information RES to the model. The target trajectory TRJ is output from the model, or the target trajectory TRJ is generated based on the output from the model.
[0035] The control amount calculation unit 23 also includes at least one of a rule-based model and a machine learning model. The control amount calculation unit 23 performs control amount calculation processing by inputting the target trajectory TRJ into the model. The control amount CON is output from the model, or the control amount CON is generated based on the output from the model.
[0036] Two or more of the recognition unit 21, the planning unit 22, and the control amount calculation unit 23 may be integrally configured. The recognition unit 21, the planning unit 22, and the control amount calculation unit 23 may all be integrally configured (end-to-end configuration). For example, the recognition unit 21 and the planning unit 22 may be integrally configured by a NN that outputs a target trajectory TRJ based on sensor detection information SEN. Even in the case of an integral configuration, intermediate products such as recognition result information RES and target trajectory TRJ may be output. For example, in the case where the recognition unit 21 and the planning unit 22 are integrally configured by a NN, the recognition result information RES may be the output of an intermediate layer of the NN.
[0037] In the present embodiment, the machine learning model is used to constitute at least a part of the recognition unit 21, the planning unit 22, and the control amount calculation unit 23 of the automatic driving device 20. That is, at least one of the recognition unit 21, the planning unit 22, and the control amount calculation unit 23 includes a machine learning model. The automatic driving device 20 uses the machine learning model to perform at least a part of the information processing for the automatic driving of the vehicle 1.
[0038] The vehicle control device 30 includes a steering driver 31, a drive driver 32, and a brake driver 33. The steering driver 31 provides a control signal to a steering device that steers the wheels. For example, the steering device includes an electric power steering (EPS: Electric Power Steering) device. The drive driver 32 inputs a control signal to a drive device that generates a driving force. As a drive device, an engine, an electric motor, an in-wheel motor, etc. are given as examples. The brake driver 33 provides a control signal to a brake device that generates a braking force. The vehicle control device 30 receives a control amount CON output from the automatic driving device 20. The vehicle control device 30 operates at least one of the steering driver 31, the drive driver 32, and the brake driver 33 with the control amount CON as a target value. As a result, the vehicle 1 travels in a manner of following the target trajectory TRJ.
[0039] Figure 2 1 is a conceptual diagram showing an example of the configuration of an automatic driving system 100 according to the present embodiment. The automatic driving system 100 is mounted on a vehicle 1 and performs information processing for automatic driving of the vehicle 1. The automatic driving system 100 has at least the functions of the automatic driving device 20 described above. Furthermore, the automatic driving system 100 may also include a sensor group 10 and a vehicle control device 30.
[0040] The autonomous driving system 100 includes one or more processors 110 (hereinafter referred to as processor 110). The processor 110 performs various processes. As the processor 110, a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), etc. are exemplified. The recognition unit 21, the planning unit 22, and the control amount calculation unit 23 can be implemented by a single processor 110 or by separate processors 110. In addition, in the case where the autonomous driving system 100 includes a vehicle control device 30, the autonomous driving device 20 and the vehicle control device 30 can be implemented by a single processor 110 or by separate processors 110. It should be noted that the separate processors 110 may also include processors 110 of different types.
[0041] The automatic driving system 100 includes one or more storage devices 120 (hereinafter, referred to as storage devices 120). Examples of the storage device 120 include a HDD (Hard Disk Drive), an SSD (Solid State Drive), a volatile memory, a non-volatile memory, and the like. The storage device 120 includes at least a program storage area 130, a model data storage area 140, and a traffic environment information storage area 150. The program storage area 130, the model data storage area 140, and the traffic environment information storage area 150 can be implemented by a single storage device 120 or by separate storage devices 120. It should be noted that the separate storage devices 120 can also include different types of storage devices 120.
[0042] One or more programs are stored in the program storage area 130. Each program is composed of a plurality of instructions. The program is a computer program for controlling the vehicle 1 and is executed by the processor 110. Various processes implemented by the automatic driving system 100 can be implemented by the cooperation between the processor 110 executing the program and the storage device 120. The program can also be recorded in a computer-readable recording medium.
[0043] Model data for autonomous driving is stored in the model data storage area 140. The model data is data of the models included in the recognition unit 21, the planning unit 22, and the control amount calculation unit 23. As described above, in the present embodiment, at least one of the recognition unit 21, the planning unit 22, and the control amount calculation unit 23 includes a machine learning model, but these machine learning models have been trained (hereinafter, the trained machine learning model is referred to as the trained model only). The machine learning model for autonomous driving that the autonomous driving device 20 pre-equips is a global model shared by all vehicles. The trained model is a local model obtained by performing adaptive learning on the global model. The learning data actually obtained by driving the vehicle 1 is used for adaptive learning. The parameters of the trained model are stored in the model data storage area 140 as model data.
[0044] The traffic environment information storage area 150 stores various information related to the traffic environment. Specifically, the traffic environment information includes weather information, information about sensors installed on the path, and information about on-board sensors of other vehicles traveling on the candidate route that may be selected by the vehicle 1. Weather information includes, for example, information about rain cloud radars and short-term weather forecasts. Information about sensors installed on the path includes, for example, information about surveillance cameras and information obtained from a road traffic information system. Information obtained from the road traffic information system includes, for example, congestion information, information related to the white line conditions of the road, information related to routes and places under construction, etc. Information about on-board sensors of other vehicles includes, for example, acceleration information, speed information, information related to identified objects, etc. These traffic environment information can be directly obtained through the vehicle-mounted device, or can be obtained from the management server 200 as needed.
[0045] The management server 200 is an external device existing outside the vehicle 1. The management server 200 communicates with one or more vehicles 1 via a communication network. The management server 200 has a database 220. The database 220 stores part or all of the traffic environment information required by the vehicle 1. The traffic environment information stored in the database 220 also includes information from on-board sensors uploaded from one or more vehicles 1. The processor 110 of the vehicle 1 can download the required information from the traffic environment information stored in the database 220 to the traffic environment information storage area 150 by accessing the management server 200.
[0046] 2. Simulation of the reliability of autonomous driving
[0047] The trained model is learned in various traffic environments. However, not all assumed traffic environments are reflected in the trained model, and the degree of reflection of the trained model of the traffic environment varies depending on the frequency encountered during training. That is, the parameters of the trained model differ depending on the conditions under which the learning is performed. Therefore, depending on the traffic environment encountered during autonomous driving, the reliability of autonomous driving using the trained model may decrease, and a scenario may occur that forces the user to drive manually. However, a situation in which autonomous driving cannot continue may also make it difficult for the user to drive.
[0048] Therefore, in this embodiment, in order to ensure the predictability of whether the autonomous driving can be performed, a simulation is performed on the reliability of driving the route from the current location to the destination by autonomous driving. By displaying the results of the simulation to the user, the user can select a route to be driven by autonomous driving after understanding the risks of driving alternation in advance.
[0049] Figure 3 1 is a block diagram showing a configuration example associated with the simulation of the reliability of the autonomous driving of the present embodiment. The simulation of the reliability of the autonomous driving is performed by the autonomous driving system 100. More specifically, the autonomous driving system 100 performs the simulation using the trained model 25 provided in the autonomous driving device 20. In the following description, it is assumed that the recognition unit 21, the planning unit 22, and the control amount calculation unit 23 each include a trained model, and the set of these trained models is the trained model 25.
[0050] In order to simulate the reliability of the autonomous driving, the autonomous driving system 100 is further provided with a path planning unit 50 and a traffic environment information acquisition unit 60. The path planning unit 50 has map information, receives the input of the destination, and retrieves one or more candidate routes from the current location to the destination. The path planning unit 50 may also be a vehicle-mounted navigation device. The traffic environment information acquisition unit 60 acquires traffic environment information for each candidate route retrieved by the path planning unit 50. The traffic environment information includes both information that can be acquired by the vehicle-mounted device of the vehicle 1 and information that can be acquired from the management server 200. The acquired traffic environment information is temporarily stored in the traffic environment information storage area 150.
[0051] One or more candidate routes retrieved by the path planning unit 50 are input to the trained model 25 of the automatic driving device 20 together with the traffic environment information of each candidate route acquired by the traffic environment information acquisition unit 60. In the trained model 25, a simulation is performed for determining whether automatic driving is possible for each candidate route based on the traffic environment information. In determining whether automatic driving is possible, not only the traffic environment information and prediction information at the time of determination but also past performance information can be considered.
[0052] The trained model 25 performs adaptive learning based on the learning data obtained during driving. Therefore, the vehicle status such as whether the vehicle 1 is entangled with a chain, whether the tires are customized, and the degree of tire wear are reflected in the trained model 25. Whether the vehicle 1 can travel on a certain route through automatic driving depends largely on the relationship between the vehicle status and the traffic environment. Therefore, by using the trained model 25 that has completed adaptive learning to simulate the reliability of automatic driving, a high predictability of whether automatic driving is possible can be ensured.
[0053] The results of the simulation performed by the trained model 25 are displayed on the display device 40. The display device 40 may be, for example, an information display provided on a dashboard. An example of the simulation results displayed on the display device 40 will be described below.
[0054] 2-1. The first example
[0055] Figure 4A : is a conceptual diagram for explaining a first example of simulation results displayed on the display device 40. In the first example, a simulation based on traffic environment information is performed for each candidate route to determine a section where automatic driving can be performed and a section where automatic driving cannot be performed, that is, a section where driving assistance by the user is requested. In addition, the time until the vehicle 1 reaches the destination and the time for driving assistance assumed to be performed by the user (hereinafter referred to as driving assistance assumed time) are calculated for each candidate route.
[0056] The candidate routes are displayed on the display device 40. The sections where the automatic driving can be performed and the sections where the automatic driving cannot be performed are distinguished and displayed by, for example, changing the display color. In addition, the time until reaching the destination and the driving assistance estimated time are displayed on the display device 40 for each candidate route.
[0057] exist Figure 4AIn the example shown, two candidate routes are displayed on the display device 40. When route 1 is selected, the destination can be reached in a shorter time than when route 2 is selected. However, route 1 includes a section where automatic driving is not possible, so the user needs to drive the vehicle 1 by himself during the route. Based on this information, the user selects any candidate route from the candidate routes displayed on the display device 40. If the user is not good at driving, the user selects route 2, whereby the user can move to the destination by automatic driving even if it takes a long detour.
[0058] 2-2. Second example
[0059] Figure 4B This is a conceptual diagram for explaining a second example of the simulation result displayed on the display device 40. In the second example, a simulation based on traffic environment information is performed for each candidate route to determine sections where automatic driving is possible and sections where automatic driving is not possible. Whether automatic driving is possible or not is determined by the probability of driving assistance performed by the user (hereinafter referred to as the driving assistance occurrence probability). If the driving assistance occurrence probability is less than or equal to the threshold value, it is determined that automatic driving is possible. If the driving assistance occurrence probability is greater than the threshold value, it is determined that automatic driving is not possible. The threshold value of the driving assistance occurrence probability can be set to an arbitrary value (for example, 30%).
[0060] The candidate routes are displayed on the display device 40. In addition, the sections in each candidate route where autonomous driving is possible and the sections where autonomous driving is not possible are displayed, for example, by changing the display color. The sections in which autonomous driving is possible are sections in which the probability of driving assistance is less than or equal to a threshold. The sections in which autonomous driving is not possible are sections in which the probability of driving assistance is greater than a threshold. In addition, the time until reaching the destination and the maximum probability of driving assistance in the route are displayed on the display device 40 for each candidate route.
[0061] exist Figure 4B In the example shown, two candidate routes are displayed on the display device 40. There is no section where automatic driving cannot be performed in both route 1 and route 2. However, when comparing the probability of driving assistance, the probability of driving assistance in route 1 is higher than the probability of driving assistance in route 2. If the user wishes to move to the destination by automatic driving, the user selects route 2, which allows the user to move to the destination more reliably by automatic driving.
[0062] 2-3. The third example
[0063] Figure 5A4 is a conceptual diagram for explaining a third example of the simulation result displayed on the display device 40. In the third example, a simulation based on traffic environment information is performed for each candidate route to determine the section where automatic driving can be performed and the section where automatic driving cannot be performed. In addition, for the section where automatic driving cannot be performed, it is determined whether it is a section where automatic driving cannot be performed but driving support implemented by the driving support system can be performed. It should be noted that the driving support implemented by the driving support system refers to low-level automatic driving below level 2.
[0064] The candidate routes are displayed on the display device 40. And, for example, the sections in each candidate route where automatic driving is possible, the sections where automatic driving is not possible, and the sections where driving support is possible are displayed to be distinguished by changing the display color. The section where automatic driving is not possible refers to a section where neither automatic driving nor driving support by a driving support system can be performed. The section where driving support can be performed refers to a section where automatic driving is not possible but driving support by a driving support system can be performed. In addition, the time until arrival at the destination and the assumed driving support time are displayed on the display device 40 for each candidate route. The assumed driving support time also includes the time when the user receives driving support from the driving support system to drive.
[0065] exist Figure 5A In the example shown, two candidate routes are displayed on the display device 40. Regardless of whether Route 1 or Route 2 is selected, the user needs to drive the vehicle. When Route 1 is selected, the destination can be reached in a shorter time than when Route 2 is selected. In addition, the time that the user needs to drive the vehicle 1 is shorter in Route 1 than in Route 2. However, in Route 2, the sections that require driving by the user are sections where driving support can be performed, while Route 1 includes sections where neither automatic driving nor driving support can be performed. The user can determine which candidate route to select based on such displayed content.
[0066] 2-4. The fourth example
[0067] Figure 5B Conceptual diagram for explaining a fourth example of simulation results displayed on the display device 40. In the fourth example, a simulation based on traffic environment information is performed for each candidate route to determine a section where automatic driving is possible and a section where automatic driving is not possible. In addition, for a section where automatic driving is not possible, it is determined whether it is a section where driving is dangerous. A section where driving is dangerous is a section where the vehicle is dangerous even if the vehicle is manually driven by the user. In a situation where automatic driving is not possible, the vehicle may not be driven safely even if the driving is handed over to the user.
[0068] The candidate routes are displayed on the display device 40. And, for example, by changing the display color, the sections in each candidate route where automatic driving is possible, the sections where automatic driving is not possible, and the sections where driving is dangerous are displayed to be distinguished. For the sections where driving is dangerous, the reasons for judging them to be dangerous are displayed, and the driving performance based on manual driving in the past is displayed. It should be noted that the displayed driving performance may also include the time period when driving was performed and the weather at that time. In addition, the time until reaching the destination and the assumed driving assistance time are displayed for each candidate route on the display device 40. The assumed driving assistance time also includes the time when the user manually drives in the driving dangerous section.
[0069] exist Figure 5B In the example shown, two candidate routes are displayed on the display device 40. When route 1 is selected, the destination can be reached in a shorter time than when route 2 is selected. However, there is a section in the middle of route 1 where the user must drive the vehicle 1, and this section includes a section determined to be dangerous to drive. In such a case, whether to select route 1 depends on the user's judgment. The reason for judging that it is dangerous to drive and the presence or absence of driving performance in this section are useful information for the user to judge which candidate route to select.
[0070] 2-5. The fifth example
[0071] Fig. 6A and Figure 6B 4 is a conceptual diagram for explaining a fifth example of a simulation result displayed on the display device 40. In the fifth example, a simulation based on traffic environment information is performed for each candidate route to determine a section where automatic driving can be performed and a section where automatic driving cannot be performed. Moreover, after the start of driving, the candidate routes are re-searched regularly or irregularly. And, for the candidate routes obtained by the re-search, a simulation based on the updated traffic environment information is performed to determine a section where automatic driving can be performed and a section where automatic driving cannot be performed. In addition, each time the simulation is re-calculated, the time until the vehicle 1 reaches the destination and the driving assistance assumed time are recalculated.
[0072] exist Fig. 6A In the example shown, two candidate routes are displayed on the display device 40. At this point in time, it is estimated that no matter whether Route 1 or Route 2 is selected, the vehicle can be moved to the destination by automatic driving without requiring driving by the user. In addition, it is estimated that the vehicle can reach the destination in a shorter time when Route 1 is selected than when Route 2 is selected. Fig. 6A In the example shown, it is assumed that Route 1 is selected by the user.
[0073] exist Figure 6B In the example shown, Fig. 6AAfter the time from the state shown has passed, two newly retrieved candidate routes are displayed on the display device 40. Route 1 is the candidate route selected at the current time point, and Route 3 is the newly retrieved candidate route. As time passes, the traffic environment may change. Therefore, the section that was capable of automatic driving at the last judgment may become incapable of automatic driving at the current time point. Conversely, the section that was not capable of automatic driving at the last judgment may become capable of automatic driving at the current time point. For example, in the last judgment, Route 1 did not include the section that was not capable of automatic driving, but in this judgment, Route 1 includes the section that was not capable of automatic driving. On the other hand, the newly retrieved Route 3 does not include the section that was not capable of automatic driving. Compared with the case where Route 1 is selected, when Route 3 is selected, the time to reach the destination becomes longer, but it is possible to move to the destination by automatic driving. Based on this information, the user reselects any candidate route from the candidate routes displayed on the display device 40.
[0074] 2-6. The sixth example
[0075] It can also be a combination of two or more of the first to fifth examples mentioned above. For example, it can be set as follows: in the third to fifth examples, the probability of driving assistance is displayed instead of the assumed time of driving assistance, as in the second example. In addition, it can also be set as follows: in the third to fourth examples, the candidate routes are re-retrieved regularly or irregularly as in the fifth example, and each re-retrieved candidate route is re-simulated based on the updated traffic environment information. In addition, it can also be set as follows: in the third example, the driving risk interval is displayed as in the fourth example.
Claims
1. A vehicle capable of automatic driving, characterized in that: have: at least one processor; and a memory storing a plurality of instructions executed by the at least one processor, The plurality of instructions are configured to cause the at least one processor to perform the following processes: selecting candidate routes to the destination; Acquiring information related to the traffic environment of the candidate route; Based on the information related to the traffic environment, using a trained model for autonomous driving to simulate the reliability of the autonomous driving when driving on the candidate route; as well as The results of the simulation are output.
2. The vehicle according to claim 1, characterized in that The plurality of instructions are configured to cause the at least one processor to perform the following processes: Adaptive learning of the model used for autonomous driving based on learning data obtained during driving; as well as The model for autonomous driving that has completed adaptive learning is used as the trained model for autonomous driving.
3. The vehicle according to claim 1 or 2, characterized in that: Outputting the results of the simulation includes: dividing the candidate routes into sections where the autonomous driving can be performed and sections where the autonomous driving cannot be performed based on the reliability; and Each section is displayed on the candidate route.
4. The vehicle according to claim 3, characterized in that The plurality of instructions are configured to cause the at least one processor to perform the following processes: determining a non-drivable section in which driving itself is not possible based on the information related to the traffic environment; and The driving-incapable section is displayed on the candidate route.
5. The vehicle according to claim 1 or 2, characterized in that: The plurality of instructions are configured to cause the at least one processor to perform the following processes: updating the information related to the traffic environment after a time has passed from execution of the simulation; resimulating the reliability using the trained model for autonomous driving based on the information related to the updated traffic environment; as well as The results of the resimulation are output.
