Search

US-12623685-B2 - Autonomous driving vehicle

US12623685B2US 12623685 B2US12623685 B2US 12623685B2US-12623685-B2

Abstract

The vehicle of the present disclosure includes at least one processor and at least one memory storing a plurality of instructions executed on the at least one processor. The plurality of instructions causes the at least one processor to select a candidate route to a destination and acquire information on a traffic environment of the selected candidate route. The plurality of instructions further causes the at least one processor to simulate, based on the information on the traffic environment, reliability in a case where the vehicle travels on the selected candidate route by the autonomous driving using a trained model for autonomous driving, and output a result of the simulation.

Inventors

  • Taiki Kawano

Assignees

  • TOYOTA JIDOSHA KABUSHIKI KAISHA

Dates

Publication Date
20260512
Application Date
20240517
Priority Date
20230522

Claims (4)

  1. 1 . A vehicle travelable by autonomous driving, comprising: at least one processor; and a memory storing a plurality of instructions executed on the at least one processor, wherein the plurality of instructions are configured to cause the at least one processor to execute: selecting one of a plurality of candidate routes to autonomously drive to a destination, controlling the vehicle to autonomously drive in accordance with the selected one of the plurality of candidate routes, acquiring information on a traffic environment of the selected candidate route, calculating, for each of the plurality of candidate routes, a time until the vehicle arrives at the destination and a time during which a user is expected to assist in driving, simulating reliability in a case where the vehicle travels on the selected candidate route by the autonomous driving based on the information on the traffic environment by using a trained model for autonomous driving, the trained model reflecting a vehicle state including whether the vehicle is wound with a chain, whether a tire of the vehicle is custom, and a degree of wear of the tire, outputting a result of the simulation, updating the information on the traffic environment after a time has elapsed from execution of the simulation, re-simulating the reliability using the trained model for the autonomous driving based on the updated information on the traffic environment, outputting a result of the re-simulation, recalculating a time until the vehicle arrives at the destination and an assumed driving assistance time every time the re-simulation is performed, controlling the vehicle to autonomously drive in at least one route including a section in which the autonomous driving is not possible, and controlling the vehicle to autonomously drive to the destination in response to selecting another candidate route that corresponds to a detour from the at least one route, and determining whether the autonomous driving is possible by a probability that the driving assistance by the user occurs, the autonomous driving is possible corresponding to a case in which a driving assistance occurrence probability is equal to or less than a threshold value that is set at 30%.
  2. 2 . The vehicle according to claim 1 , wherein the plurality of instructions are configured to cause the at least one processor to further execute: performing adaptive learning on a model for the autonomous driving based on learning data obtained during traveling, and using an adaptive learned model for the autonomous driving as the trained model for the autonomous driving.
  3. 3 . The vehicle according to claim 1 , wherein the outputting the result of the simulation comprises: dividing the selected candidate route into the section in which the autonomous driving is possible and another section in which the autonomous driving is not possible based on the reliability, and displaying each section on the selected candidate route.
  4. 4 . The vehicle according to claim 3 , wherein the plurality of instructions are configured to cause the at least one processor to further execute: identifying an inoperable section in which driving itself is not possible based on the information on the traffic environment, and displaying the inoperable section on the selected candidate route.

Description

CROSS-REFERENCE TO RELATED APPLICATION The present application claims priority under 35 U.S.C. § 119 to Japanese Patent Application No. 2023-083950, filed on May 22, 2023, the contents of which application are incorporated herein by reference in their entirety. BACKGROUND Field The present disclosure relates to a vehicle travelable by autonomous driving. Background Art In recent years, an autonomous driving technique for determining vehicle control based on information from an in-vehicle sensor or the like by using a trained model generated by machine learning has been developed. In WO 2019/116423, a method is proposed for collecting training data that can be used in the machine learning to generate the trained model. However, when the environment surrounding the vehicle changes, the inference result by the trained model may change. Therefore, the range in which the vehicle control can be appropriately executed using the trained model may change according to the traffic environment such as weather, time zone, and traffic volume. As a result, a situation may occur in which a user who expects autonomous driving is forced to perform manual driving operation. As documents showing the technical level of the technical field related to the present disclosure, JP2020-153939A, JP 2019-074359A, and JP2020-173264A can be exemplified in addition to WO2020/116423A. SUMMARY An object of the present disclosure is to provide a technique for ensuring predictability of whether or not autonomous driving is executable. In order to achieve the above object, the present disclosure provides a vehicle travelable by autonomous driving. The vehicle of the present disclosure includes at least one processor and at least one memory storing a plurality of instructions executed on the at least one processor. The plurality of instructions causes the at least one processor to select a candidate route to a destination and acquire information on a traffic environment of the selected candidate route. The plurality of instructions further causes the at least one processor to simulate, based on the information on the traffic environment, reliability in a case where the vehicle travels on the selected candidate route by the autonomous driving using a trained model for autonomous driving, and output a result of the simulation. Whether the vehicle can travel on a certain route by autonomous driving depends on the traffic environment. In addition, parameters of the trained model used for automated driving differ depending on the conditions under which trained model was trained. Therefore, even if the traffic environment is the same, all vehicles are not necessarily equally capable of autonomous driving, and conversely, are not necessarily equally incapable of autonomous driving. According to the vehicle of the present disclosure, by inputting information on the traffic environment of a selected candidate route to the trained model for autonomous driving, it is possible to simulate the reliability in a case where the vehicle travels on the candidate route by autonomous driving. Then, by outputting the result of the simulation, it is possible to ensure predictability of whether or not autonomous driving is executable. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram illustrating a configuration example related to autonomous driving of a vehicle according to an embodiment. FIG. 2 is a conceptual diagram illustrating a configuration example of an autonomous driving system according to the embodiment. FIG. 3 is a block diagram illustrating a configuration example related to simulation of reliability of autonomous driving according to the embodiment. FIG. 4A is a conceptual diagram for explaining a first example of simulation results according to the embodiment. FIG. 4B is a conceptual diagram for explaining a second example of simulation results according to the embodiment. FIG. 5A is a conceptual diagram for explaining a third example of simulation results according to the embodiment. FIG. 5B is a conceptual diagram for explaining a fourth example of simulation results according to the embodiment. FIG. 6A is a conceptual diagram for explaining a fifth example of simulation results according to the embodiment. FIG. 6B is another conceptual diagram for explaining the fifth example of simulation results according to the embodiment. DETAILED DESCRIPTION 1. Autonomous Driving of Vehicle FIG. 1 is a block diagram illustrating a configuration example related to autonomous driving of a vehicle 1 according to the present embodiment. The autonomous driving is to autonomously perform at least one of steering, acceleration, and deceleration of the vehicle 1 without depending on a driving operation by the user of the vehicle 1. The autonomous driving is a concept including not only fully autonomous driving but also risk avoidance control, lane keep assist control, and the like. The vehicle 1 includes a sensor group 10, an autonomous driving device 20, an