Remote support system and remote support method

Abstract

The present disclosure relates to a remote support system and a remote support method. The remote support system is configured to, when a vehicle enters a remote operation request state, determine whether the vehicle will collide with an avoidance object. If the determination is negative, the remote support system is configured not to issue a remote operation request. If it is determined that the vehicle will collide with the avoidance object, the remote support system is configured to generate a first speed plan for continuing automatic driving of the vehicle at a predicted collision location and a second speed plan for stopping the vehicle before reaching the predicted collision location. The remote support system is configured to determine whether to issue a remote operation request based on the degree of deviation between these speed plans.

Description

Technical Field

[0001] The present disclosure relates to a remote support system and a remote support method for issuing a remote operation request of a vehicle to a remote operator. Background Art

[0002] Japanese Patent Application Laid-Open No. 2018-77649 discloses a technology related to a remote driving control device for enabling a remote operator to perform remote driving. In this device, a remote operator remotely controls a vehicle in response to a remote control request sent from an autonomous vehicle.

[0003] In the technology of Japanese Patent Application Laid-Open No. 2018-77649, a remote operation request is issued in response to a vehicle occupant pressing a button to request remote operation. Frequent issuance of such remote operation requests increases the burden on the remote operator. However, reducing the frequency of remote operation requests while ensuring the safety of an autonomous vehicle is not easy. Summary of the Invention

[0004] The present disclosure provides a remote support system and a remote support method that can reduce the burden on remote operators by reducing the frequency of remote operation requests for an autonomous vehicle.

[0005] A first aspect of the present disclosure is a remote support system configured to issue a remote operation request to a remote operator when a vehicle in autonomous driving enters a remote operation request state. The remote support system comprises: a storage device storing at least one program; and at least one processor connected to the at least one storage device. The at least one processor is configured to, when the vehicle enters a remote operation request state, execute a first determination process and a second determination process by executing the at least one program. The first determination process determines whether the vehicle will collide with an avoidance object associated with the remote operation request state. The second determination process determines whether to issue a remote operation request based on the result of the first determination process. The first determination process includes acquiring at least one of map information about the vehicle's surroundings, surrounding environment information related to the vehicle's surroundings, and vehicle motion information related to the vehicle's motion; and determining whether the vehicle will collide with the avoidance object based on at least one of the map information, vehicle motion information, and surrounding environment information. The second determination process includes not issuing a remote operation request if the first determination process determines that the vehicle will not collide with the avoidance object.

[0006] According to the first aspect, even if the vehicle enters a remote operation request state, if it is determined that the vehicle will not collide with the avoidance object, no remote operation request is issued. This configuration ensures vehicle safety while reducing the frequency of remote operation requests. This reduces the burden on the remote operator.

[0007] In the first scheme, the first judgment processing may also include: generating a future predicted trajectory of the avoidance object based on at least any one of the map information and the surrounding environment information; the first judgment processing may also include: generating a future driving trajectory of the vehicle based on at least any one of the map information, the vehicle motion information and the surrounding environment information; the first judgment processing may also include: calculating a predicted collision position where the avoidance object collides with the vehicle based on the predicted trajectory and the driving trajectory; the first judgment processing may also include: determining whether the vehicle will collide with the avoidance object based on the map information or the surrounding environment information at the predicted collision position.

[0008] In the first aspect, the first determination process may include determining that the vehicle will not collide with the avoidance object when the traffic environment at the predicted collision position gives priority to the travel of the vehicle over the travel of the avoidance object.

[0009] In the first aspect, the first determination process may include determining that the vehicle will not collide with the avoidance object when the avoidance object is a preceding vehicle of the vehicle at the predicted collision position.

[0010] In the first aspect, the first determination process may include determining that the vehicle will collide with the avoidance object in a traffic environment where the travel of an avoidance object takes priority over the travel of the vehicle at the predicted collision position.

[0011] According to the above configuration, whether the vehicle will collide with the avoidance object is determined based on the calculated map information or surrounding environment information at the predicted collision position. According to this configuration, a highly accurate collision determination can be performed based on the traffic environment or surrounding environment at the predicted collision position.

[0012] In the first solution, at least one processor may also be configured to: through the execution of at least one program, continue automatic driving of the vehicle based on the driving trajectory when it is determined in the first determination process that the vehicle will not collide with the avoidance object.

[0013] According to the above configuration, even when the vehicle enters a remote operation request state, if it is determined that the vehicle will not collide with the avoidance object, the vehicle's automatic driving will continue based on the driving trajectory. This configuration can prevent occupants of the vehicle or occupants of surrounding vehicles from feeling uncomfortable due to changes in vehicle behavior in preparation for a remote operation request.

[0014] In the first scheme, when it is determined in the first determination process that the vehicle will collide with the avoidance object, the second determination process may also include: generating a first speed plan, wherein the first speed plan is a speed plan for the vehicle to continue automatic driving at the predicted collision position, the second determination process may also include: generating a second speed plan, wherein the second speed plan is a speed plan for the vehicle to stop before reaching the predicted collision position, and the second determination process may also include: determining whether to issue a remote operation request based on the degree of deviation between the first speed plan and the second speed plan.

[0015] With the above configuration, a first speed plan is generated, representing the speed plan for when the vehicle continues autonomous driving, and a second speed plan is generated, representing the speed plan for stopping the vehicle before reaching the predicted collision location. The degree of deviation between the first and second speed plans serves as an indicator for determining the degree of deviation between the speeds when the vehicle continues autonomous driving and when the vehicle stops. Therefore, with this configuration, the time limit for issuing a remote operation request can be clearly identified.

[0016] In the first scheme, the second judgment processing may also include: calculating the remaining time until the speed difference between the first speed plan and the second speed plan reaches a specified threshold value, and the second judgment processing may also include: determining whether to issue a remote operation request based on whether the remaining time is greater than a judgment time predetermined as a judgment time of the remote operator.

[0017] According to the above configuration, the remote operation request can be issued in consideration of the remote operator's judgment time so that the remote operation can be started before the speed difference between the first speed plan and the second speed plan reaches a predetermined threshold value.

[0018] In the first aspect, the at least one processor may also be configured to, through execution of at least one program, continue the automatic driving of the vehicle based on the first speed plan when it is determined in the second determination process that no remote operation request is issued.

[0019] According to the above configuration, if it is determined that no remote operation request has been issued, the vehicle performs automated driving based on the first speed plan. With this configuration, the vehicle travels according to the speed plan that presupposes continued automated driving while no remote operation request has been issued, thereby preventing disruption to traffic flow.

[0020] In the first aspect, the at least one processor may also be configured to, through execution of at least one program, continue the automatic driving of the vehicle based on the second speed plan when it is determined in the second determination process that a remote operation request is issued.

[0021] According to the above configuration, when it is determined that a remote operation request has been issued, the vehicle is automatically driven based on the second speed plan. According to this configuration, the vehicle can be transitioned to a vehicle motion state suitable for starting remote operation by a remote operator.

[0022] A second aspect of the present disclosure is a remote support method for issuing a remote operation request to a remote operator when a vehicle in autonomous driving enters a remote operation request state. The remote support method may include: when the vehicle enters the remote operation request state, a processor executing at least one program performing a first determination process to determine whether the vehicle will collide with an avoidance object associated with the remote operation request state; and when the vehicle enters the remote operation request state, the processor executing at least one program performing a second determination process to determine whether to issue the remote operation request based on the result of the first determination process. The first determination process includes acquiring at least one of map information about the vehicle's surroundings, surrounding environment information related to the vehicle's surroundings, and vehicle motion information related to the vehicle's motion; and determining whether the vehicle will collide with the avoidance object based on at least one of the map information, vehicle motion information, and surrounding environment information. The second determination process includes not issuing a remote operation request if the first determination process determines that the vehicle will not collide with the avoidance object.

[0023] According to the second aspect, even if the vehicle enters a remote operation request state, if it is determined that the vehicle will not collide with the avoidance object, the remote operation request is not issued. This configuration ensures vehicle safety while reducing the frequency of remote operation requests. This reduces the burden on the remote operator.

[0024] In the second scheme, the first judgment processing may also include: generating a future predicted trajectory of the avoidance object based on at least any one of map information and surrounding environment information, the first judgment processing may also include: generating a future driving trajectory of the vehicle based on at least any one of map information, vehicle motion information and surrounding environment information, the first judgment processing may also include: calculating a predicted collision position where the avoidance object collides with the vehicle based on the predicted trajectory and the driving trajectory; and determining whether the vehicle will collide with the avoidance object based on the map information or surrounding environment information at the predicted collision position. In the case where it is determined in the first judgment processing that the vehicle will collide with the avoidance object, the second judgment processing may also include, through the processor: generating a first speed plan, wherein the first speed plan is a speed plan for the vehicle to continue automatic driving at the predicted collision position; generating a second speed plan, wherein the second speed plan is a speed plan for the vehicle to stop before reaching the predicted collision position; and determining whether to issue a remote operation request based on the first speed plan and the second speed plan.

[0025] With the above configuration, a first speed plan is generated, representing the speed plan for when the vehicle continues autonomous driving, and a second speed plan is generated, representing the speed plan for stopping the vehicle before reaching the predicted collision location. The degree of deviation between the first and second speed plans serves as an indicator for determining the degree of deviation between the speeds when the vehicle continues autonomous driving and when the vehicle stops. Therefore, with this configuration, the time limit for issuing a remote operation request can be clearly identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Hereinafter, features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described with reference to the accompanying drawings, wherein like reference numerals denote like elements, and wherein:

[0027] Figure 1 This is a block diagram showing an example configuration for explaining an outline of the remote support system according to the first embodiment.

[0028] Figure 2 This is a block diagram showing an example of the configuration of an autonomous driving vehicle.

[0029] Figure 3 This is a diagram for explaining an example of a situation in which a remote operation is performed in a remote support system according to a comparative example.

[0030] Figure 4 1 is a diagram showing an example of a traffic environment at an intersection in a remote operation request situation.

[0031] Figure 5 This is a functional block diagram showing part of the functions of the automatic driving control device.

[0032] Figure 6 This is a flowchart of the processing performed in the automatic driving control device.

[0033] Figure 7 This is a functional block diagram showing part of the functions of the automatic driving control device of embodiment 2.

[0034] Figure 8 This is a diagram showing the speed plans of plan A and plan B generated by the travel plan generation unit.

[0035] Figure 9 This is a flowchart of the processing performed in the automatic driving control device of embodiment 2.

[0036] Figure 10 This is a diagram showing a first application example of the remote support system.

[0037] Figure 11 This is a diagram showing an example of the speed plans of plan A and plan B generated in the first application example of the remote support system.

[0038] Figure 12 It is a diagram showing a second application example of the remote support system.

[0039] Figure 13 It is a diagram showing a third application example of the remote support system.

[0040] Figure 14 This is a diagram showing an example of the speed plans of plan A and plan B generated in the third application example of the remote support system.

[0041] Figure 15 It is a diagram showing a fourth application example of the remote support system.

[0042] Figure 16 It is a diagram showing a fifth application example of the remote support system.

[0043] Figure 17 It is a diagram showing a sixth application example of the remote support system.

[0044] Figure 18 This is a diagram showing an example of the speed plans of plan A and plan B generated in the sixth application example of the remote support system.

[0045] Figure 19 This is a diagram showing another example of the speed plans of plan A and plan B generated in the sixth application example of the remote support system.

[0046] Figure 20 It is a diagram showing a seventh application example of the remote support system.

[0047] Figure 21 It is a diagram showing an eighth application example of the remote support system. DETAILED DESCRIPTION

[0048] The following describes embodiments of the present invention with reference to the accompanying drawings. In the embodiments described below, when numerical values such as the number, quantity, amount, and range of various elements are mentioned, the present invention is not limited to such numerical values unless otherwise specified or clearly determined in principle. Furthermore, with respect to structures and steps described in the embodiments described below, unless otherwise specified or clearly determined in principle, such structures and steps are not necessarily required for the present invention.

[0049] Implementation Method 1

[0050] 1-1. Overall Configuration of Remote Support System in Embodiment 1

[0051] First, the schematic configuration of the remote support system according to the first embodiment will be described. Figure 1 This is a block diagram showing an example configuration for explaining an outline of the remote support system according to the first embodiment. Figure 1 The remote support system 100 shown is a system for remotely operating an autonomous vehicle 10, wherein the remote operation is used to control the driving of the autonomous vehicle 10. Hereinafter, the autonomous vehicle 10 used in the remote support system 100 will be simply referred to as "vehicle 10."

[0052] Remote operation not only includes remote driving, which includes instructions for any of the following: acceleration, deceleration, and steering operations, but also includes driving assistance that partially assists in the recognition or judgment of the vehicle 10's surrounding environment. Remote operation is performed by a remote operator on standby at a remote location. There is no limit on the number of remote operators used in the remote support system 100. Furthermore, there is no limit on the number of vehicles 10 used in the remote support system 100.

[0053] like Figure 1 As shown, remote support system 100 includes a vehicle 10 and a remote operation device 2. Remote operation device 2 includes a remote server 4 and a remote operator interface 6 for inputting remote operation commands. Remote server 4 is communicatively connected to vehicle 10 via a communication network N. Various information is transmitted from vehicle 10 to remote server 4. Remote operator interface 6 includes, for example, input devices simulating a vehicle's steering wheel, accelerator pedal, and brake pedal. Alternatively, remote operator interface 6 includes an input device for inputting judgment results during driving assistance.

[0054] In the remote support system 100, a remote operator performs remote operations via the remote operation device 2 in response to a remote operation request received from the vehicle 10. Typically, the remote operator inputs the remote operation request into the remote operator interface 6. The remote server 4 issues remote operation instructions to the vehicle 10 via the communication network N. The vehicle 10 drives according to the remote operation instructions received from the remote operation device 2. It should be noted that the configuration of the remote operation device 2 can employ related technologies, and therefore a detailed description thereof will be omitted.

[0055] 1-2. Configuration of the Autonomous Driving Vehicle in Embodiment 1

[0056] Next, an example of a configuration of autonomous driving of the autonomous driving vehicle 10 applied to the remote support system 100 according to the first embodiment will be described. Figure 2 This is a block diagram showing an example of the configuration of an autonomous vehicle 10. Vehicle 10 is capable of autonomous driving. The autonomous driving described here assumes Level 3 or higher, as defined by the Society of Automotive Engineers (SAE). It should be noted that there are no restrictions on the power source of vehicle 10.

[0057] Vehicle 10 includes an automatic driving control device 40. Automatic driving control device 40 has functions for automatically driving vehicle 10 and for remotely controlling vehicle 10 in accordance with remote control instructions from a remote operator. Information acquisition device 30, communication device 50, and travel device 60 are connected to automatic driving control device 40.

[0058] The information acquisition device 30 is configured to include a vehicle position sensor 31 , a peripheral condition sensor 32 , and a vehicle state sensor 33 .

[0059] The vehicle position sensor 31 detects the position and orientation of the vehicle 10. For example, the vehicle position sensor 31 includes a GPS (Global Positioning System) sensor. The GPS sensor receives signals transmitted from multiple GPS satellites and calculates the position and orientation of the vehicle 10 based on the received signals. The vehicle position sensor 31 can also perform localization to improve the accuracy of the vehicle 10's current position. Information detected by the vehicle position sensor 31 is constantly transmitted to the automatic driving control device 40 as part of the surrounding environment information.

[0060] The surrounding situation sensor 32 identifies information about the surroundings of the vehicle 10. Examples of the surrounding situation sensor 32 include a camera (photographic device), a laser radar (LIDAR), and a radar. The surrounding information includes information about objects identified by the surrounding situation sensor 32. Examples of objects include surrounding vehicles, pedestrians, roadside objects, obstacles, white lines, and traffic lights. Object information includes the relative position and relative speed of the object relative to the vehicle 10. The information identified by the surrounding situation sensor 32 is constantly transmitted to the automatic driving control device 40 as part of the surrounding environment information.

[0061] The vehicle state sensor 33 detects vehicle information indicating the state of the vehicle 10. Examples of the vehicle state sensor 33 include a vehicle speed sensor, a lateral acceleration sensor, and a yaw rate sensor. Information detected by the vehicle state sensor 33 is constantly transmitted to the automatic driving control device 40 as part of the vehicle motion information.

[0062] The communication device 50 communicates with the outside of the vehicle 10. For example, the communication device 50 sends and receives various information with the remote control device 2 via the communication network N. In addition, the communication device 50 communicates with external devices such as roadside devices, surrounding vehicles, and surrounding infrastructure. Roadside devices are, for example, beacon devices that transmit congestion information, traffic information for each lane, control information such as temporary stops, information on traffic conditions at blind spots, etc. In addition, when the external device is a surrounding vehicle, the communication device 50 performs vehicle-to-vehicle communication (V2V communication) with the surrounding vehicles. Moreover, when the external device is surrounding infrastructure, the communication device 50 performs vehicle-to-road communication (V2I communication) with the surrounding infrastructure.

[0063] The travel device 60 includes a steering device, a drive device, and a braking device. The steering device steers the wheels of the vehicle 10. The drive device is a driving source that generates driving force for the vehicle 10. Examples of the drive device include an engine or an electric motor. The braking device generates braking force for the vehicle 10. The travel device 60 controls the travel of the vehicle 10 based on travel control variables related to steering, acceleration, and deceleration of the vehicle 10.

[0064] The autonomous driving control device 40 is an information processing device that performs various processes for autonomous driving and remote autonomous driving. Typically, the autonomous driving control device 40 is a microcomputer equipped with at least one processor 42, at least one storage device 44, and at least one input / output interface 46. The autonomous driving control device 40 is also called an ECU (Electronic Control Unit).

[0065] The storage device 44 stores various information 442. For example, the various information 442 includes the aforementioned surrounding environment information and vehicle motion information. Examples of the storage device 44 include a volatile memory, a nonvolatile memory, and an HDD (Hard Disk Drive).

[0066] Storage device 44 stores a map database 444. Map database 444 is a database that stores map information. This map information includes traffic environment information such as road location information, road shape information, the number of lanes, lane widths, intersection and fork location information, and road priority. It should be noted that map database 444 may also be stored on a server capable of communicating with vehicle 10, such as remote server 4 of remote control device 2.

[0067] Processor 42 includes a CPU (Central Processing Unit). Processor 42 is coupled to a storage device 44 and an input / output interface 46. Storage device 44 stores at least one program 440 related to autonomous driving and remote autonomous driving. Processor 42 reads and executes program 440 stored in storage device 44 to implement various functions of autonomous driving control device 40.

[0068] The input / output interface 46 is an interface for exchanging information with the remote operation device 2 . Various information generated in the automatic driving control device 40 and a remote operation request described later are output to the remote operation device 2 via the input / output interface 46 .

[0069] 1-3. Features of the remote support system according to Embodiment 1

[0070] First, an example of a situation in which remote operation by a remote operator is performed in a remote support system of a comparative example will be described. Figure 3 This is a diagram for explaining an example of a situation in which a remote operation is performed in a remote support system of a comparative example. Note that, in the remote support system, elements common to the remote support system 100 of the first embodiment are denoted by the same reference numerals.

[0071] In the remote support system of the comparative example, when the vehicle 10 reaches a remote operation request state in which a remote operation request should be made to the remote operation device 2, a remote driving request is made to the remote operation device. The remote operation request state here can be pre-set to include, for example, a state element that can be determined based on map information. Typically, the remote operation request state is a state in which the vehicle 10 passes through a remote operation request location that can be determined based on map information accompanied by specific state elements. Examples of such remote operation request states include a state in which the vehicle 10 turns right at an intersection, a state in which the vehicle 10 starts after a temporary stop at a specific intersection, a state in which the vehicle 10 starts a lane change, a state in which the vehicle 10 passes through a specific narrow road, and a state in which the vehicle 10 passes through an intersection with a blind spot.

[0072] Figure 3 The traffic environment shown is an intersection I1 where lane L1 intersects lane L2. Lane L1 is a priority lane relative to lane L2. A vehicle 10 traveling in lane L1 is Figure 3 The illustrated situation of turning right at the intersection I1 is set as the remote operation request situation.

[0073] The automatic driving control device 40 of vehicle 10 generates a driving plan for turning right from lane L1 at intersection I1 and then traveling to lane L2. In this scenario, when vehicle 10 approaches intersection I1, the automatic driving control device 40 determines that a remote operation request has occurred. The automatic driving control device 40 issues a remote operation request to the remote operation device 2 and transmits various information acquired by the information acquisition device 30 as information required for remote operation of vehicle 10. Upon receiving the remote operation request, the remote operation device 2 performs remote automatic driving by a remote operator. Typically, the remote operator determines whether to pass through intersection I1 based on the various information received from the automatic driving control device 40. The remote operator then issues a remote operation instruction to vehicle 10 by operating the remote operator interface 6. This remote operation instruction can be an operation variable of the driving device 60 or an instruction indicating a decision result such as "go," "stop," or "turn right." Vehicle 10 passes through intersection I1 in accordance with the remote operation instruction received from the remote operation device 2.

[0074] Here, in Figure 3In the example traffic environment shown, when vehicle 10 enters intersection I1, another vehicle V1 traveling in lane L2 is traveling toward intersection I1. In this traffic environment, vehicle 10's travel takes precedence over that of other vehicle V1 under traffic regulations, so in principle, vehicle 10's travel will not be obstructed by other vehicle V1. Furthermore, if the oncoming vehicle is not traveling in the opposite lane of lane L1 from vehicle 10, vehicle 10 will not collide with the oncoming vehicle.

[0075] Even if a remote operation request is determined, the need for a remote operation request may be low depending on the dynamic surrounding environment. If a remote operation request is immediately made based on the initial determination, remote operation requests may be made even for situations that may seem unnecessary in hindsight. This results in increased burden on remote operators.

[0076] Therefore, the remote support system 100 according to the first embodiment is characterized in that, even when it is determined that a remote operation request situation has occurred, the remote operation request action is avoided according to the subsequent dynamic surrounding environment situation. Figure 4 1 is a diagram showing an example of a traffic environment at an intersection under a remote operation request situation. Note that the remote operation request situation here is a situation where a vehicle 10 traveling in lane L1 turns right at intersection I2 toward lane L3.

[0077] Figure 4 The example shown shows a traffic environment in which vehicle 10, operating in lane L1 and performing automated driving, is turning right at intersection I2, while oncoming vehicle V2, traveling in lane L2, on the opposite side of lane L1, is proceeding straight through intersection I2. If a remote operation request is determined, the automated driving control device 40 of vehicle 10 performs the following processing.

[0078] The automatic driving control device 40 generates a driving trajectory TR1 of the vehicle 10 and a predicted trajectory TR2 of a detection object (here, the oncoming vehicle V2) detected as an avoidance object associated with the remote operation request condition. The "driving trajectory" here is a predetermined future trajectory of the vehicle 10 that is undergoing automatic driving and will travel on the target route, including a path plan and a speed plan. The path plan of the driving trajectory includes a set of target positions within the road on which the vehicle 10 is traveling. In addition, the speed plan of the driving trajectory includes a target speed for each target position. The target route is, for example, a route set based on the destination, map information, and position information of the vehicle 10. The "predicted trajectory" is a trajectory on a future road predicted based on the position, speed, and map information of the avoidance object, and includes a path plan and a speed plan like the driving trajectory.

[0079] The automatic driving control device 40 calculates the point where the generated driving trajectory TR1 intersects the predicted trajectory TR2 as the predicted collision position CP. Based on the predicted collision position CP and map information, the automatic driving control device 40 determines whether a collision with the oncoming vehicle V2, which is the avoidance target, will occur. This process is also referred to as the "first determination process." Typically, in the first determination process, if the traffic environment conditions at the predicted collision position CP indicate that the vehicle 10 has priority over the oncoming vehicle V2, the vehicle 10 is determined not to collide with the oncoming vehicle V2. Alternatively, in the first determination process, if the traffic environment conditions at the predicted collision position CP indicate that the vehicle 10 does not have priority over the oncoming vehicle V2, the vehicle 10 is determined to be likely to collide with the oncoming vehicle V2. Alternatively, in the first determination process, if the avoidance target is a preceding vehicle in the same lane as the vehicle 10, the vehicle 10 is determined to be avoidable simply by adjusting its speed, and thus, the vehicle 10 is determined not to collide with the avoidance target.

[0080] The automatic driving control device 40 determines whether to issue a remote operation request based on the determination result of the first determination process. This process is also referred to as the "second determination process." In the second determination process, if the first determination process determines that the vehicle 10 will not collide with the avoidance object, the automatic driving control device 40 determines not to issue a remote operation request. On the other hand, if the vehicle 10 is determined to collide with the avoidance object, the automatic driving control device 40 determines to issue a remote operation request.

[0081] According to the remote support method of the remote support system 100, even if the vehicle enters a location determined as a remote operation request location, the remote operation request can be avoided based on the dynamic surrounding environment. This ensures the safety of the vehicle 10 and reduces the burden on the remote operator.

[0082] Hereinafter, the functional configuration and specific processing of the automatic driving control device 40 of the remote support system 100 according to the first embodiment will be described.

[0083] 1-4. Functional Structure of the Autonomous Driving Control System

[0084] Next, an example of the functional configuration of the automatic driving control device 40 will be described. Figure 5 4 is a functional block diagram showing a portion of the functions of the automatic driving control device 40. The automatic driving control device 40 includes a surrounding environment information acquisition unit 402, a vehicle motion information acquisition unit 404, a map information acquisition unit 406, a travel planning unit 410, and a remote operation request unit 420.

[0085] The surrounding environment information acquisition unit 402 and the vehicle motion information acquisition unit 404 are functional blocks for respectively acquiring surrounding environment information and vehicle motion information detected by the information acquisition device 30 . The map information acquisition unit 406 is a functional block for acquiring map information stored in the map database 444 .

[0086] The driving planning unit 410 performs driving plan generation processing for generating a driving trajectory TR1 as a driving plan for automatic driving of the vehicle 10 and remote operation necessity determination processing for determining whether remote operation by a remote operator is required.

[0087] Typically, the driving plan unit 410 includes a target object behavior prediction unit 412 , a collision position calculation unit 414 , a remote operation request determination unit 416 , and a driving plan generation unit 418 .

[0088] The object movement prediction unit 412 generates a predicted trajectory TR2 for an avoidance object that could collide with the autonomous vehicle 10. Examples of avoidance objects include oncoming vehicles, preceding vehicles, and vehicles crossing on intersecting roads. The object movement prediction unit 412 calculates the predicted trajectory TR2 for the avoidance object using the position and velocity of the avoidance object calculated based on surrounding environment information and map information. It should be noted that multiple predicted trajectories TR2 may be calculated if there are multiple predictions for the avoidance object, such as a right turn, a left turn, or straight travel. The calculated predicted trajectory TR2 is sent to the collision position calculation unit 414.

[0089] The collision position calculation unit 414 calculates the predicted collision position CP of the vehicle 10 and the avoidance object. Typically, the collision position calculation unit 414 generates a travel trajectory TR1 for the vehicle 10 using the target route, position, and speed of the vehicle 10, calculated based on the destination, vehicle motion information, and map information. Furthermore, the collision position calculation unit 414 calculates the predicted collision position CP where the predicted trajectory TR2 input from the collision position calculation unit 414 intersects the generated travel trajectory TR1. The calculated predicted collision position CP is transmitted to the remote operation request determination unit 416 and the travel plan generation unit 418.

[0090] Remote operation request determination unit 416 performs a first determination process to determine whether vehicle 10 will collide with an avoidance object based on predicted collision position CP, and a second determination process to determine whether a remote operation request should be issued to the remote operator based on the result of the first determination process. Typically, if predicted collision position CP does not exist, remote operation request determination unit 416 determines that a remote operation request is not necessary. If predicted collision position CP exists, remote operation request determination unit 416 uses map information or surrounding environment information to determine the traffic priority status at predicted collision position CP. If the traffic priority status at predicted collision position CP prioritizes vehicle 10, remote operation request determination unit 416 determines that a remote operation request is not necessary. If the traffic priority status at predicted collision position CP does not prioritize vehicle 10, remote operation request determination unit 416 determines that a remote operation request is necessary. The result of the determination on whether a remote operation request is necessary is transmitted to travel plan generation unit 418. Furthermore, the result of the determination on whether a remote operation request is necessary is also transmitted to remote operation request unit 420.

[0091] The driving plan generation unit 418 generates a driving trajectory TR as a driving plan for the vehicle 10. Typically, the driving plan generation unit 418 generates the driving trajectory TR for the vehicle 10 based on the vehicle 10's position and speed calculated from vehicle motion information, map information, the predicted collision position CP, and a determination of whether a remote control request is required. Typically, if a remote control request is determined to be necessary, the driving plan generation unit 418 generates a driving trajectory TR in which the vehicle 10 stops at a predetermined stop position SP immediately before the predicted collision position CP or before entering an intersection and awaits remote control. Alternatively, if a remote control request is determined not to be necessary, the driving plan generation unit 418 generates a driving trajectory TR in which the vehicle 10 avoids a collision with an avoidance target, taking into account the predicted collision position CP. The generated driving trajectory TR is transmitted to the driving device 60.

[0092] The remote operation request unit 420 is a device for issuing a remote operation request to a remote operator operating the remote operation device 2 via the communication network N. The remote operation request unit 420 issues a remote operation request REQ to the remote operation device 2 based on whether the remote operation request sent from the remote operation request determination unit 416 is necessary.

[0093] 1-5. Specific Processing Executed by the Automatic Driving Control Device

[0094] Figure 6This is a flowchart of the processing executed by the automatic driving control device 40. The automatic driving control device 40 always determines whether the vehicle 10 is in a remote operation request state based on the position and speed of the vehicle 10 calculated based on the vehicle motion information and the map information. When the vehicle 10 is in a remote operation request state, the automatic driving control device 40 executes Figure 6 The routine shown.

[0095] exist Figure 6 In step S100 of the routine shown, the object motion prediction unit 412 first generates a predicted trajectory TR2 for the avoidance target. In the next step S102, the predicted collision position CP at which the vehicle 10's travel trajectory TR1 intersects the predicted trajectory TR2 for the avoidance target is calculated. In the next step S104, the remote operation request determination unit 416 determines whether the travel trajectory TR1 and the predicted trajectory TR2 intersect. If a valid predicted collision position CP is received from the collision position calculation unit 414, the remote operation request determination unit 416 determines that the travel trajectory TR1 and the predicted trajectory TR2 will intersect.

[0096] If, in step S104, it is determined that the driving trajectory TR1 and the predicted trajectory TR2 will not intersect, then even in the case of a remote operation request, it can be determined that a remote operation request is not necessary. In this case, the process proceeds to step S106. In step S106, the driving plan generation unit 418 generates a driving trajectory TR using the driving trajectory TR1 calculated in step S102. The generated driving trajectory TR is transmitted to the driving device 60. The driving device 60 continues the automated driving of the vehicle 10 according to the driving trajectory TR.

[0097] On the other hand, if it is determined in step S104 that the travel trajectory TR1 and the predicted trajectory TR2 will intersect, the process proceeds to step S108. In step S108, the remote operation request determination unit 416 determines, based on the map information and the predicted collision position CP, whether the vehicle 10 is a non-priority vehicle at the predicted collision position CP relative to the traffic environment of the avoidance target. If the vehicle 10 is a non-priority vehicle at the predicted collision position, the process proceeds to step S110. If the vehicle 10 is not a non-priority vehicle at the predicted collision position, the process proceeds to step S112.

[0098] In step S110, the remote operation request unit 420 issues a remote operation request REQ to the remote operation device 2. Furthermore, in step S110, the travel plan generation unit 418 generates a travel trajectory TR for stopping the vehicle 10 at the predetermined stop position SP. The generated travel trajectory TR is transmitted to the travel device 60. The travel device 60 automatically drives the vehicle 10 according to the travel trajectory TR.

[0099] In step S112, the remote operation request unit 420 holds the remote operation request REQ and does not send the remote operation request REQ to the remote operation device 2. Furthermore, in step S112, the driving plan generation unit 418 generates a driving trajectory TR that includes deceleration and avoidance steering relative to the driving trajectory TR1 in preparation for avoiding a collision with an avoidance target at the predicted collision position CP. The generated driving trajectory TR is transmitted to the driving device 60. The driving device 60 automatically drives the vehicle 10 according to the driving trajectory TR.

[0100] Thus, the remote support system 100 of Embodiment 1 determines whether a remote operation request is necessary based on the surrounding environment even when the vehicle 10 is in a state requiring remote operation. This configuration reduces unnecessary remote operation requests, thereby reducing the burden on the remote operator.

[0101] 1-6. Modifications

[0102] The remote support system 100 according to the first embodiment may also adopt the following modified forms.

[0103] There is no limitation on the functional configuration of the automatic driving control device 40. In other words, some or all of the functions of the automatic driving control device 40 may be installed in the vehicle 10 or configured in the remote server 4 of the remote operation device 2. This modification can also be applied to the remote support system of the second embodiment described later.

[0104] Implementation Method 2

[0105] Next, the remote support system 100 according to Embodiment 2 will be described. The remote support system 100 according to Embodiment 2 has the same configuration as the remote support system 100 according to Embodiment 1, except for the functional configuration of the automatic driving control device 40. Descriptions of the elements common to the remote support system 100 according to Embodiment 1 will be omitted.

[0106] 2-1. Features of the remote support system according to Embodiment 2

[0107] In the remote support system of Embodiment 1, when a remote operation request is determined to be in place, the need for a remote operation request is determined based on subsequent information about the surrounding environment. When generating a predicted trajectory for an avoidance object, the farther the vehicle 10 is from the avoidance object, the further into the future the avoidance object's behavior needs to be predicted, resulting in greater uncertainty in the surrounding environment. Therefore, if the need for a remote operation request is determined at an earlier stage, multiple predicted trajectories TR2 based on uncertainty factors are generated, increasing the number of predicted collision positions CP that must be considered. As a result, the need for a remote operation request is more likely to be determined. Conversely, the closer the vehicle 10 is to the avoidance object, the less uncertainty in the surrounding environment. Therefore, the longer the timing of determining whether a remote operation request is necessary is delayed, the greater the likelihood of reducing the number of situations in which a remote operation request is determined to be necessary.

[0108] However, even when a remote operation request is issued to a remote operator, the remote operator who receives the request cannot immediately initiate remote operation of vehicle 10. This is because the remote operator needs time to determine the need for remote operation, understand the surrounding conditions of vehicle 10, support details, and other factors, and actually initiate remote operation. Therefore, if the remote operator determines that a remote operation request is necessary too late, vehicle 10 may approach the location of the remote operation request before remote operation can actually begin, necessitating the vehicle 10 to wait at a predetermined stop position SP in front of the location. In this situation, there is a risk of increased anxiety among vehicle 10 occupants and disruption to the traffic flow of following vehicles.

[0109] Therefore, the remote support system 100 according to the second embodiment is characterized in that it includes a function for optimizing the timing of determining whether remote operation is necessary when it is determined that the remote operation is requested.

[0110] Figure 7 This is a functional block diagram showing a portion of the functions of the automatic driving control device 40 according to Embodiment 2. The automatic driving control device 40 according to Embodiment 2 includes a surrounding environment information acquisition unit 402, a vehicle motion information acquisition unit 404, a map information acquisition unit 406, and a remote operation request unit 420 as components having functions common to the automatic driving control device 40 according to Embodiment 1. Furthermore, the automatic driving control device 40 according to Embodiment 2 includes a driving plan generation unit 430, a remote operation request determination unit 432, and a driving plan selection unit 434 as components having functions different from those of the automatic driving control device 40 according to Embodiment 1. Descriptions of components common to the automatic driving control device 40 according to Embodiment 1 are omitted.

[0111] The driving plan generation unit 430 is a functional block for generating driving plans for situations where a remote operation request is not required and for situations where a remote operation request is required. In the following description, the driving plan for situations where a remote operation request is not required is referred to as Plan A (Plan A), and the driving plan for situations where a remote operation request is required is referred to as Plan B (Plan B). Plan A is a driving plan that assumes no remote operation request will be made. It includes a first path plan and a first speed plan for avoiding a collision at the predicted collision position CP and passing through the location where remote operation is required through automated driving. Typically, Plan A includes collision avoidance with an avoidable object by decelerating immediately before the predicted collision position CP or by steering. Plan B is a driving plan that assumes a remote operation request will be made. It includes a second path plan and a second speed plan for stopping the vehicle 10 at a predetermined stop position SP immediately before the predicted collision position CP. Both Plan A and Plan B are sent to the remote operation request determination unit 432 and the driving plan selection unit 434.

[0112] The remote operation request determination unit 432 is a functional block for performing a second determination process for determining whether or not to issue the remote operation request REQ based on the plan A and the plan B sent from the travel plan creation unit 430 . Figure 8 This diagram shows the speed plans for Plan A and Plan B generated by the driving plan generation unit 430. In the example shown in this diagram, Plan A is a speed plan in which the vehicle 10 decelerates and passes through the predicted collision position CP, while Plan B is a speed plan in which the vehicle 10 stops just before the predicted collision position CP. Comparing Plans A and B, Plan B exhibits a greater deceleration than Plan A. Therefore, the speed difference Δv(t) between Plans A and B at time t increases over time.

[0113] As mentioned above, the predetermined judgment time, which is several tens of seconds, is required from the time the remote operator receives a remote operation request to the time the remote operation actually begins. Therefore, for example, if a remote operation request is made to cause vehicle 10 to travel according to Plan B, the remote operator's remote operation begins after the predetermined judgment time has elapsed from the remote operation request. Therefore, if the remote operator's remote operation is intended to change the speed from Plan B to Plan A without disrupting the traffic of following vehicles, the speed difference Δv(t) may cause vehicle 10 to accelerate suddenly, potentially causing passengers to feel uncomfortable. In other words, there is a permissible limit to the speed difference Δv(t) that prevents passengers from feeling uncomfortable after the remote operator's remote operation begins.

[0114] Therefore, remote operation request determination unit 432 calculates the time ta at which the speed difference Δv(t) reaches a predetermined threshold value Th corresponding to the permissible limit. Remote operation request determination unit 432 then determines whether a remote operation request is necessary by comparing the remaining time RT (=ta - tc) from the current time tc to the time ta with the remote operator's judgment time α. The judgment time α is predetermined as the time required by the remote operator before commencing remote operation. Typically, the judgment time α is between 10 and 15 seconds, for example.

[0115] If the remaining time RT is greater than the determination time α, it is determined that remote operation by the remote operator can be initiated before the speed difference Δv(t) reaches the permissible limit. While RT>α holds, the remote operation request determination unit 432 determines that a remote operation request is not necessary. Then, if RT>α no longer holds, the remote operation request determination unit 432 determines that a remote operation request is necessary. The result of the determination on whether a remote operation request is necessary is sent to the travel plan selection unit 434. Furthermore, the result of the determination on whether a remote operation request is necessary is also sent to the remote operation request unit 420.

[0116] The driving plan selection unit 434 selects a driving plan for the vehicle 10 based on the driving plan of plan A, the driving plan of plan B, and the determination result of whether a remote operation request is required. Typically, the remote operation request determination unit 432 selects the driving plan of plan A when receiving a determination result that a remote operation request is not required. On the other hand, the remote operation request determination unit 432 selects the driving plan of plan B when receiving a determination result that a remote operation request is required. The remote operation request determination unit 432 outputs the driving trajectory TR corresponding to the selected driving plan to the driving device 60.

[0117] 2-2. Specific Processing Executed by the Automatic Driving Control Device of Embodiment 2

[0118] Figure 9 Flowchart of the process executed in the automatic driving control device 40 of the second embodiment. Figure 6 Similarly to the routine shown, when the vehicle 10 is in a remote operation request state, the automatic driving control device 40 repeatedly executes the routine in a predetermined control cycle. Figure 9 The routine shown.

[0119] exist Figure 9 In steps S200, S202, S204 and S206 of the routine shown in FIG. Figure 6The same processing is performed as in steps S100, S102, S104, and S106 of the routine shown. Note that the first determination process for determining whether the vehicle 10 will collide with the avoidance object is executed by executing the processing of steps S200, S202, and S204.

[0120] If, during step S204, it is determined that the driving trajectory TR1 and the predicted trajectory TR2 will intersect, it can be determined that the vehicle 10 will collide with the avoidance object in the first determination process. In this case, the process proceeds from step S204 to step S208. In step S208, the driving plan generation unit 430 generates a driving trajectory TR1A that includes a plan A for decelerating or steering relative to the driving trajectory TR1 in preparation for avoiding a collision with the avoidance object at the predicted collision position CP. Upon completion of step S208, the process proceeds to step S210.

[0121] In step S210 , the travel plan generating unit 430 generates a travel trajectory TR1B for plan B, which causes the vehicle 10 to wait for remote control at a predetermined waiting point before the predicted collision position CP. When the process of step S210 is completed, the process proceeds to step S212 .

[0122] In step S212, remote operation request determination unit 432 calculates the time ta at which the speed difference Δv(t) between plan A and plan B at time t exceeds threshold value Th. In the next step S214, remote operation request determination unit 432 calculates the remaining time RT from the current time tc to time ta and determines whether the calculated remaining time RT is less than the remote operator's judgment time α.

[0123] If the result of the determination in S214 is that the determination is not satisfied, it is determined that a remote operation request is not necessary in this routine, and the process proceeds to step S216. In step S216, the remote operation request unit 420 does not issue a remote operation request REQ to the remote operation device 2. The driving plan selection unit 434 then selects the driving trajectory TR1A of plan A as the driving trajectory TR and transmits this driving trajectory TR to the driving device 60. The driving device 60 performs automatic driving of the vehicle according to the driving trajectory TR.

[0124] On the other hand, if the result of the determination in S214 is confirmation of the determination being made, it is determined that a remote operation request is necessary in this routine, and the process proceeds to step S218. In step S218, the remote operation request unit 420 issues a remote operation request REQ to the remote operation device 2 where the remote operator is on standby. Furthermore, in step S218, the driving plan selection unit 434 selects the driving trajectory TR1B of plan B as the driving trajectory TR and transmits this driving trajectory TR to the driving device 60. The driving device 60 performs automatic driving of the vehicle according to the driving trajectory TR.

[0125] Thus, according to the remote support method executed by the remote support system 100 of Embodiment 2, even if the vehicle 10's condition requires a remote operation, a remote operation request is not made while the remaining time RT is greater than the remote operator's judgment time α. Then, in the remote support system 100, a remote operation request is made when the remaining time RT is less than the remote operator's judgment time α. This configuration delays the determination of a remote operation request until the speed difference Δv(t) reaches the permissible limit, thereby preventing passengers from experiencing discomfort and reducing the frequency of remote operation requests. This reduces the burden on the remote operator.

[0126] 2-3. Application examples to specific traffic conditions

[0127] 2-3-1. First application example

[0128] Figure 10 FIG is a diagram showing a first application example of the remote support system. Figure 10 Vehicle 10 traveling in lane L1 is drawn in FIG. Vehicle 10 is scheduled to enter intersection I3. Oncoming vehicle V3 traveling in lane L2 is drawn on the opposite side of intersection I3 relative to vehicle 10. Like vehicle 10, oncoming vehicle V3 is also scheduled to enter intersection I3.

[0129] In the first application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10 to turn right at the intersection I3 and a predicted trajectory TR2 for the oncoming vehicle V3 to proceed straight through the intersection I3. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0130] exist Figure 10 In the illustrated traffic environment, when there is a predicted collision position CP where the driving trajectory TR1 intersects the predicted trajectory TR2 , the automatic driving control device 40 generates a driving trajectory TR1A based on scenario A and TR1B based on scenario B. Figure 11This diagram shows an example of speed plans for Plan A and Plan B generated in the first application example of the remote support system. Driving trajectory TR1A is the driving trajectory for vehicle 10 to decelerate and turn right at intersection I3. Typically, driving trajectory TR1A is the same as driving trajectory TR1. Driving trajectory TR1B is the driving trajectory for vehicle 10 to stop at a predetermined stop position SP before the predicted collision position CP.

[0131] While the remaining time RT exceeds the determination time α, the automatic driving control device 40 performs automatic driving of the vehicle 10 according to the travel trajectory TR1A of plan A. Furthermore, if the traffic environment changes to a state where the travel trajectory TR1 and the predicted trajectory TR2 do not intersect while the remaining time RT exceeds the determination time α, the automatic driving control device 40 performs automatic driving of the vehicle 10 according to the travel trajectory TR1.

[0132] If the traffic environment condition causing the intersection of the driving trajectory TR1 and the predicted trajectory TR2 has not yet been resolved and the remaining time RT < the judgment time α holds, the automatic driving control device 40 issues a remote control request and automatically drives the vehicle 10 according to the driving trajectory TR1B of plan B. The remote operator, having received the remote control request, initiates remote control before the elapse of time ta, as in the remote control example shown in the figure. For example, the remote operator accelerates and decelerates within a range that does not cause discomfort to the passengers and makes a right turn at the intersection.

[0133] 2-3-2. Second application example

[0134] Figure 12 : is a diagram showing a second application example of the remote support system. Figure 12 In addition to Figure 10 In addition to the traffic environment conditions of the first application example shown, a preceding vehicle V4 traveling in the lane L3 after the vehicle 10 turns right is also drawn.

[0135] In the second application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10 to avoid a collision with the preceding vehicle V4 after turning right at the intersection, and a predicted trajectory TR2 for the oncoming vehicle V3 to proceed straight through the intersection I3. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0136] exist Figure 12In the traffic environment shown, when the driving trajectory TR1 and the predicted trajectory TR2 intersect at the predicted collision position CP, the automatic driving control device 40 generates a driving trajectory TR1A based on scenario A and TR1B based on scenario B. In this case, the automatic driving control device 40 generates a driving trajectory TR1B that avoids a collision with the preceding vehicle V4. The subsequent processing is the same as in the first application example.

[0137] 2-3-3. Third application example

[0138] Figure 13 : is a diagram showing a third application example of the remote support system. Figure 13 Vehicle 10 is drawn in lane L1. Vehicle 10 is scheduled to enter intersection I4, which has a temporary stop line. Vehicle V6 is drawn in lane L3, which intersects lane L1, on the left front side of intersection I4 relative to vehicle 10. Like vehicle 10, vehicle V6 is also scheduled to enter intersection I4.

[0139] In the third application example, the automatic driving control device 40 generates a driving trajectory TR1 for vehicle 10 that stops at the temporary stop line at intersection I4 and then starts driving, and a predicted trajectory TR2 for vehicle V6 that proceeds straight through intersection I4. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0140] exist Figure 13 When there is a predicted collision position CP where the driving trajectory TR1 and the predicted trajectory TR2 intersect under the traffic environment conditions shown, the automatic driving control device 40 generates a driving trajectory TR1A based on scenario A and a driving trajectory TR1B based on scenario B. Figure 14 This diagram shows an example of speed plans for Plan A and Plan B generated in the third application example of the remote support system. Driving trajectory TR1A is the driving trajectory for vehicle 10 to start after stopping at the temporary stop line at intersection I4. Typically, driving trajectory TR1A is the same as driving trajectory TR1. Driving trajectory TR1B is the driving trajectory for vehicle 10 to stop and wait at the temporary stop line at intersection I4, which is set as stop position SP.

[0141] In the third application example, the longer vehicle 10 remains stopped at stop position SP along travel trajectory TR1B, the greater the value of Δv(t). Therefore, Δv(t) serves as an indicator of whether traffic flow will be disrupted for vehicles following vehicle 10. While remaining time RT exceeds determination time α, the automatic driving control device 40 automatically drives vehicle 10 along travel trajectory TR1A of scenario A. Furthermore, if the traffic environment changes to a state where travel trajectory TR1 and predicted trajectory TR2 do not intersect while remaining time RT exceeds determination time α, the vehicle 10 automatically drives along travel trajectory TR1.

[0142] If the traffic environment condition where the travel trajectory TR1 intersects the predicted trajectory TR2 has not yet been resolved and the remaining time RT < the judgment time α holds, the vehicle 10 is determined to be potentially disrupting the traffic flow of subsequent vehicles by waiting for remote control at the stop position SP. In this case, the automatic driving control device 40 issues a remote control request and automatically drives the vehicle 10 according to the travel trajectory TR1B of scenario B. The remote operator, having received the remote control request, initiates remote control before the elapsed time ta, as in the remote control example shown in the figure. This allows the vehicle 10 to start moving before disrupting the traffic flow of subsequent vehicles.

[0143] Note that, when there is an area that becomes a blind spot when viewed from the vehicle 10 at the intersection I4 , the third application example may be applied assuming that an avoidance target exists in the blind spot area.

[0144] 2-3-4. Fourth application example

[0145] Figure 15 : is a diagram showing a fourth application example of the remote support system. Figure 15 In addition to Figure 13 In addition to the traffic environment conditions of the third application example shown, a preceding vehicle V7 traveling in the lane L1 after the vehicle 10 travels straight through the intersection I4 is also drawn.

[0146] In the fourth application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10, after temporarily stopping at the temporary stop line at intersection I4, to start the vehicle 10 to avoid a collision with the preceding vehicle V7, and a predicted trajectory TR2 for the vehicle V6 to proceed straight through intersection I4. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0147] exist Figure 15In the traffic environment shown, when the driving trajectory TR1 and the predicted trajectory TR2 intersect at the predicted collision position CP, the automatic driving control device 40 generates a driving trajectory TR1A based on scenario A and TR1B based on scenario B. In this case, the automatic driving control device 40 generates a driving trajectory TR1B that avoids collision with the preceding vehicle V7. The subsequent processing is the same as in the first application example.

[0148] 2-3-5. Fifth application example

[0149] Figure 16 1 is a diagram showing a fifth application example of the remote support system. Figure 16 Vehicle 10 is drawn in lane L1. Lane L2, adjacent to lane L1, is a lane for vehicles traveling in the opposite direction of vehicle 10. A stopped vehicle V8 is drawn in front of vehicle 10, stopped in lane L1. Stopped vehicle V8 is an avoidance target object that obstructs the travel of vehicles in lane L1. An oncoming vehicle V9 is drawn in front of vehicle 10, traveling in lane L2.

[0150] In the fifth application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10 to diverge from lane L1 into lane L2 and overtake the stopped vehicle V8 from the right, and a predicted trajectory TR2 for the oncoming vehicle V9 to proceed straight through lane L2. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0151] exist Figure 16 In the traffic environment shown, when there is a predicted collision position CP where the driving trajectory TR1 intersects the predicted trajectory TR2, the automatic driving control device 40 generates a driving trajectory TR1A based on scenario A and TR1B based on scenario B. Driving trajectory TR1A is a driving trajectory in which the vehicle 10 decelerates and overtakes the stopped vehicle V8 from the right. Typically, driving trajectory TR1A is the same trajectory as driving trajectory TR1. Driving trajectory TR1B is a driving trajectory in which the vehicle 10 stops at a predetermined stop position SP in front of the stopped vehicle V8.

[0152] While the remaining time RT exceeds the judgment time α, the automatic driving control device 40 performs automatic driving of the vehicle 10 along the driving trajectory TR1A of scenario A. Furthermore, if the traffic environment changes to a state where the driving trajectory TR1 and the predicted trajectory TR2 do not intersect while the remaining time RT exceeds the judgment time α, the automatic driving control device 40 performs automatic driving of the vehicle 10 along the driving trajectory TR1. Furthermore, if the stationary vehicle V8 starts moving while the remaining time RT exceeds the judgment time α, the automatic driving control device 40 generates, for example, a driving trajectory TR1 in which the vehicle 10 decelerates and follows the stationary vehicle V8 without overtaking it. In this case, the driving trajectory TR1 does not intersect the predicted trajectory TR2, so the automatic driving control device 40 performs automatic driving of the vehicle 10 along the driving trajectory TR1.

[0153] If the traffic environment condition where the travel trajectory TR1 intersects the predicted trajectory TR2 has not yet been resolved and the remaining time RT < the judgment time α holds, the automatic driving control device 40 issues a remote control request and automatically drives the vehicle 10 according to the travel trajectory TR1B of plan B. The remote operator, having received the remote control request, begins remote control before the time ta elapses. For example, the remote operator accelerates and decelerates within a range that does not cause discomfort to the occupants, thereby avoiding a collision with the oncoming vehicle V9 and overtaking the stopped vehicle V8.

[0154] 2-3-6. Sixth Application Example

[0155] Figure 17 1 is a diagram showing a sixth application example of the remote support system. Figure 17 A vehicle 10 traveling in lane L1 is drawn in FIG. A lane L2 adjacent to lane L1 is a lane for vehicles traveling in the same direction as the traveling direction of vehicle 10. A vehicle V11 traveling in lane L2 is drawn behind vehicle 10.

[0156] In the sixth application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10 to change lanes from lane L1 to lane L2 while accelerating, and a predicted trajectory TR2 for the vehicle V11 to travel straight in lane L2. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 performs the lane change using automatic driving according to the driving trajectory TR1.

[0157] exist Figure 17 In the illustrated traffic environment, when there is a predicted collision position CP where the driving trajectory TR1 intersects the predicted trajectory TR2 , the automatic driving control device 40 generates a driving trajectory TR1A based on scenario A and TR1B based on scenario B. Figure 18This diagram shows an example of speed plans for Plan A and Plan B generated in the sixth application example of the remote support system. Driving trajectory TR1A is a driving trajectory for vehicle 10 to accelerate and change lanes to lane L2. Typically, driving trajectory TR1A is the same as driving trajectory TR1. Driving trajectory TR1B is a driving trajectory for vehicle 10 to maintain its speed in lane L1.

[0158] In the sixth application example, the longer vehicle 10 maintains its speed along driving trajectory TR1B, the greater the speed difference Δv(t) with driving trajectory TR1A. Therefore, Δv(t) serves as an indicator for determining the timing limit for accelerating ahead of vehicle V9 to change lanes. While remaining time RT exceeds judgment time α, the automatic driving control device 40 performs automatic driving of vehicle 10 along driving trajectory TR1A in scenario A in preparation for the lane change. Furthermore, if the traffic environment changes to a state where driving trajectory TR1 and predicted trajectory TR2 do not intersect while remaining time RT exceeds judgment time α, vehicle 10 performs automatic driving along driving trajectory TR1.

[0159] If the traffic environment condition where the driving trajectory TR1 intersects the predicted trajectory TR2 has not yet been resolved and the remaining time RT < the judgment time α holds, it is determined that vehicle 10 may find it difficult to safely change lanes in front of vehicle V9. In this case, the automatic driving control device 40 issues a remote control request and automatically controls vehicle 10 according to the driving trajectory TR1B of plan B. The remote operator, having received the remote control request, initiates remote control before the elapsed time ta, as in the remote control example shown in the figure. For example, the remote operator accelerates within a range that does not cause discomfort to the passengers and performs a lane change in front of vehicle V9.

[0160] Figure 19 This figure shows another example of speed plans for Plan A and Plan B generated in the sixth application example of the remote support system. As shown in this figure, driving trajectory TR1A can be a driving trajectory for vehicle 10 to maintain its current speed and change lanes to lane L2. In this case, for example, driving trajectory TR1B can be a driving trajectory for decelerating in lane L1 to allow vehicle V9 to pass and perform a remote operation request.

[0161] 2-3-7. Seventh application example

[0162] Figure 20 : is a diagram showing a seventh application example of the remote support system. Figure 20Vehicle 10 is drawn in lane L1. Lane L1 has a lane section L11 with a road width that allows vehicle 10 to travel in the opposite direction of an oncoming vehicle, and a lane section L12 with a road width that prevents vehicle 10 from traveling in the opposite direction of the oncoming vehicle. Vehicle 10 is traveling in lane L1 from lane section L11 toward lane section L12. In front of vehicle 10, an oncoming vehicle V12 is drawn, traveling in lane section L12 of lane L1 in the opposite direction of vehicle 10's travel.

[0163] In the seventh application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10 traveling straight from lane section L11 to lane section L12, and a predicted trajectory TR2 for the oncoming vehicle V12 traveling straight in lane section L12. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0164] exist Figure 20 In the traffic environment conditions shown, when there is a predicted collision position CP where the driving track TR1 intersects the predicted track TR2, the automatic driving control device 40 generates a driving track TR1A based on plan A and TR1B based on plan B. The driving track TR1A is a driving track for the vehicle 10 to go straight from the lane section L11 to the lane section L12. Typically, the driving track TR1A is the same track as the driving track TR1. The driving track TR1B is a driving track for the vehicle 10 to stop at the roadside at the specified stop position SP before moving from the lane section L11 to the lane section L12. The speed plans of plan A and plan B generated here are the same as Figure 11 The speed plan of the first application example shown is the same. In addition, the subsequent processing is the same as that of the first application example.

[0165] 2-3-8. Eighth Application Example

[0166] Figure 21 FIG. 8 is a diagram showing an eighth application example of the remote support system. Figure 21 A vehicle 10 traveling in lane L1 is drawn in FIG. The vehicle 10 is scheduled to cross the crosswalk CW. A pedestrian H1 is drawn on the crosswalk CW as an avoidance target who is predicted to cross the crosswalk CW.

[0167] In the eighth application example, the automatic driving control device 40 generates a driving trajectory TR1 for the vehicle 10 to pass through the crosswalk CW and a predicted trajectory TR2 for the pedestrian H1 to cross the crosswalk CW. If the driving trajectory TR1 and the predicted trajectory TR2 do not intersect, the automatic driving control device 40 automatically drives the vehicle 10 according to the driving trajectory TR1.

[0168] exist Figure 21In the traffic environment shown, when there is a predicted collision position CP where the driving track TR1 intersects the predicted track TR2, the automatic driving control device 40 generates a driving track TR1A based on plan A and TR1B based on plan B. The driving track TR1A is a driving track for the vehicle 10 to decelerate and pass through the crosswalk CW. Typically, the driving track TR1A is the same track as the driving track TR1. The driving track TR1B is a driving track for the vehicle 10 to stop at the specified stop position SP in front of the crosswalk CW. The speed plans of plan A and plan B generated here are the same as those of plan A and plan B. Figure 11 The driving plan shown is the same as that of the first application example.

[0169] It should be noted that the eighth application example can also be applied to a situation where a vehicle traveling from a branch road to the lane L1 is set as an avoidance target instead of the pedestrian H1 crossing the crosswalk CW.

[0170] 2-4. Modification

[0171] The remote support system 100 according to the second embodiment may also adopt the following modified forms.

[0172] The index value used to determine the remote operation request is not limited to the speed difference Δv(t). In other words, any index value that can evaluate the degree of deviation of the speed plan of plan A from the speed plan of plan B may be used, or other index values such as the speed ratio may be used.

[0173] Similar to the remote support system 100 of the first embodiment, the automatic driving control device 40 may further determine whether the vehicle 10 will collide with the avoidance object based on the traffic priority condition at the predicted collision position CP.

Claims

1. A remote support system configured to issue a remote operation request to a remote operator when a vehicle in autonomous driving enters a remote operation request state, the remote support system comprising: a storage device storing at least one program; as well as At least one processor is connected to the at least one storage device, wherein: The at least one processor is configured to: when the vehicle enters the remote operation request state, perform a first determination process and a second determination process by executing the at least one program; The first determination process is a process of determining whether the vehicle will collide with an avoidance object associated with the remote operation request situation. The second determination process is a process of determining whether to issue the remote operation request based on the result of the first determination process. The first determination process includes: acquiring at least any one of map information of the periphery of the vehicle, surrounding environment information related to the surrounding environment of the vehicle, and vehicle motion information related to the motion of the vehicle; and determining whether the vehicle will collide with an avoidance object based on at least one of the map information, the vehicle motion information, and the surrounding environment information, The second determination process includes: if it is determined in the first determination process that the vehicle will not collide with the avoidance object, not issuing the remote operation request; The first determination process includes: generating a predicted future trajectory of the avoidance object based on at least one of the map information and the surrounding environment information; generating a future driving trajectory of the vehicle based on at least any one of the map information, the vehicle motion information, and the surrounding environment information; calculating a predicted collision position where the avoidance object collides with the vehicle based on the predicted trajectory and the travel trajectory; and determining whether the vehicle will collide with the avoidance object based on the map information or the surrounding environment information at the predicted collision position, If it is determined in the first determination process that the vehicle will collide with the avoidance object, the second determination process includes: generating a first speed plan, wherein the first speed plan is a speed plan for the vehicle to continue the automatic driving at the predicted collision location; generating a second speed plan, wherein the second speed plan is a speed plan for stopping the vehicle before reaching the predicted collision position; and Whether to issue the remote operation request is determined based on a degree of deviation between the first speed plan and the second speed plan.

2. The remote support system according to claim 1, wherein: The first determination process includes determining that the vehicle will not collide with the avoidance object when the traffic environment at the predicted collision position gives priority to the travel of the vehicle over the travel of the avoidance object.

3. The remote support system according to claim 1, wherein: The first determination process includes determining that the vehicle will not collide with the avoidance object when the avoidance object is a preceding vehicle of the vehicle at the predicted collision position.

4. The remote support system according to claim 1, wherein: The first determination process includes determining that the vehicle is likely to collide with the avoidance object when the traffic environment at the predicted collision position gives priority to the travel of the avoidance object over the travel of the vehicle.

5. The remote support system according to any one of claims 1 to 4, characterized in that: The at least one processor is configured to, through execution of the at least one program, continue automatic driving of the vehicle based on the driving trajectory when it is determined in the first determination process that the vehicle will not collide with the avoidance object.

6. The remote support system according to claim 1, wherein: The second determination process includes: calculating a remaining time from the current time to a time when the speed difference between the first speed plan and the second speed plan reaches a predetermined threshold; If a condition is met that the remaining time is greater than a judgment time predetermined as a judgment time of a remote operator, not issuing the remote operation request; and If the condition is not met, the remote operation request is issued.

7. The remote support system according to claim 1 or 6, characterized in that: The at least one processor is configured to, through execution of the at least one program, continue the automatic driving of the vehicle based on the first speed plan when it is determined in the second determination process that the remote operation request is not issued.

8. The remote support system according to claim 1 or 6, characterized in that: The at least one processor is configured to, through execution of the at least one program, continue the automatic driving of the vehicle based on the second speed plan when it is determined in the second determination process that the remote operation request is issued.

9. A remote support method for issuing a remote operation request to a remote operator when a vehicle in autonomous driving enters a remote operation request state, the remote support method comprising: When the vehicle enters the remote operation request state, a processor executing at least one program performs a first determination process for determining whether the vehicle will collide with an avoidance object associated with the remote operation request state; as well as When the vehicle reaches the remote operation request state, a processor executing at least one program executes a second determination process for determining whether to issue the remote operation request based on a result of the first determination process, wherein: The first determination process includes: acquiring at least any one of map information of the periphery of the vehicle, surrounding environment information related to the surrounding environment of the vehicle, and vehicle motion information related to the motion of the vehicle; and determining whether the vehicle will collide with an avoidance object based on at least one of the map information, the vehicle motion information, and the surrounding environment information, The second determination process includes: if it is determined in the first determination process that the vehicle will not collide with the avoidance object, not issuing the remote operation request; The first determination process includes: generating a predicted future trajectory of the avoidance object based on at least one of the map information and the surrounding environment information; generating a future driving trajectory of the vehicle based on at least any one of the map information, the vehicle motion information, and the surrounding environment information; calculating a predicted collision position where the avoidance object collides with the vehicle based on the predicted trajectory and the travel trajectory; and determining whether the vehicle will collide with the avoidance object based on the map information or the surrounding environment information at the predicted collision position, Furthermore, if it is determined in the first determination process that the vehicle will collide with the avoidance object, the second determination process includes: generating a first speed plan, wherein the first speed plan is a speed plan for the vehicle to continue the automatic driving at the predicted collision location; generating a second speed plan, wherein the second speed plan is a speed plan for stopping the vehicle before reaching the predicted collision position; and Whether to issue the remote operation request is determined based on a degree of deviation between the first speed plan and the second speed plan.

Images