Remote support system, remote support method, and remote support program

Abstract

To provide a remote support system that gives reliability to performance evaluation of an operator who remotely supports automatic operation of a moving body.SOLUTION: A processor of a remote support system for remotely supporting automatic drive of a moving body is configured to execute the steps of: acquiring a support request requested from the moving body; generating instruction information instructed by an operator in response to the support request so as to be transmitted to the moving body; collecting determination information determined by the moving body in response to the instruction information; and outputting evaluation information Ie obtained by evaluating the operator based on a time gap Δt between an instruction timing to indicated by the instruction information and determination timing tj indicated by the determination information as transition timing of a dynamic drive task by the moving body.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present disclosure relates to a remote assistance technology that remotely assists autonomous driving of a moving object. [Background technology]

[0002] Patent Document 1 discloses a remote support technology that evaluates the ability of an operator who remotely supports the automatic driving of a moving object and stores the evaluation result. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-170191 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology disclosed in Patent Document 1, the ability of an operator is evaluated based on response time and processing time overruns. However, if the response time and processing time are short, it cannot necessarily be said that the operator's ability is appropriate, and there are concerns about the reliability of the evaluation results. In addition, in the technology disclosed in Patent Document 1, the ability of an operator is evaluated based on the status of oncoming vehicles and passengers. However, since the status of oncoming vehicles and passengers is not information that directly represents the status of the mobile object itself that is remotely supported, there are concerns about the reliability of the evaluation results.

[0005] An object of the present disclosure is to provide a remote assistance system that provides reliability in the evaluation of the ability of an operator who remotely assists the automatic driving of a moving object. Another object of the present disclosure is to provide a remote assistance method that provides reliability in the evaluation of the ability of an operator who remotely assists the automatic driving of a moving object. Yet another object of the present disclosure is to provide a remote assistance program that provides reliability in the evaluation of the ability of an operator who remotely assists the automatic driving of a moving object. [Means for solving the problem]

[0006] The technical means of the present disclosure for solving the problems will be described below. Note that the claims and the reference characters in parentheses in this section indicate the corresponding relationship with the specific means described in the embodiments described later in detail, and do not limit the technical scope of the present disclosure.

[0007] A first aspect of the present disclosure is A remote assistance system having a processor (12) for remotely assisting an automatic driving of a moving object (2), The processor Obtaining a request for assistance (Rd) from a mobile unit; generating instruction information (Io) instructed by an operator (8) in response to a request for assistance so as to be transmitted to the mobile unit; Judgment information (Ij) judged by the moving object in response to the instruction information The control system of the vehicle transmits, to the vehicle, a decision information including a plan information (Ip) planned by the control system based on the recognition information of the driving scene, so that the control system of the vehicle realizes a transition of the dynamic driving task represented by the instruction information when the control system of the vehicle makes a positive decision, and the control system realizes a transition of the dynamic driving task when the control system rejects the instruction information and makes a self-decision, from the vehicle capable of communication. To collect and The system is configured to output evaluation information (Ie) that evaluates the operator based on the time gap (Δt) between the instruction timing (to) represented by the instruction information and the judgment timing (tj) represented by the judgment information as the transition timing of the dynamic driving task by the moving body.

[0008] A second aspect of the present disclosure is A remote assistance method executed by a processor (12) for remotely assisting an autonomous driving of a moving object (2), comprising: Obtaining a request for assistance (Rd) from a mobile unit; generating instruction information (Io) instructed by an operator (8) in response to a request for assistance so as to be transmitted to the mobile unit; Judgment information (Ij) judged by the moving object in response to the instruction information The control system of the vehicle transmits, to the vehicle, a decision information including a plan information (Ip) planned by the control system based on the recognition information of the driving scene, so that the control system of the vehicle realizes a transition of the dynamic driving task represented by the instruction information when the control system of the vehicle makes a positive decision, and the control system realizes a transition of the dynamic driving task when the control system rejects the instruction information and makes a self-decision, from the vehicle capable of communication. To collect and This includes outputting evaluation information (Ie) that evaluates the operator based on the time gap (Δt) between the instruction timing (to) represented by the instruction information and the judgment timing (tj) represented by the judgment information as the transition timing of the dynamic driving task by the moving body.

[0009] A third aspect of the present disclosure is A remote assistance program for remotely assisting automatic driving of a moving body (2), the remote assistance program being stored in a storage medium (10) and including instructions to be executed by a processor (12), The command is, Acquiring a request for assistance (Rd) from a mobile unit; generating instruction information (Io) instructed by an operator (8) in response to a support request so as to be transmitted to the mobile unit; Judgment information (Ij) judged by the moving object in response to the instruction information The control system of the vehicle transmits, to the vehicle, a decision information including a plan information (Ip) planned by the control system based on the recognition information of the driving scene, so that the control system of the vehicle realizes a transition of the dynamic driving task represented by the instruction information when the control system of the vehicle makes a positive decision, and the control system realizes a transition of the dynamic driving task when the control system rejects the instruction information and makes a self-decision, from the vehicle capable of communication. To collect and This includes outputting evaluation information (Ie) that evaluates the operator based on the time gap (Δt) between the instruction timing (to) represented by the instruction information and the judgment timing (tj) represented by the judgment information as the transition timing of the dynamic driving task by the moving body.

[0010] In this way, in the first to third aspects, judgment information judged in response to the instruction information is collected from the moving body that generates and transmits the instruction information of the operator in response to the assistance request. According to the first to third aspects, evaluation information is output that evaluates the operator based on the time gap between the instruction timing represented by the instruction information and the judgment timing represented by the judgment information as the transition timing of the dynamic driving task by the moving body. According to this, the instruction timing that reflects the judgment ability of the operator can be appropriately evaluated based on the time gap as a comparison result with the judgment timing that is the direct judgment information of the moving body. Therefore, it is possible to provide reliability to the ability evaluation of the operator who remotely assists the automatic driving of the moving body.

[0011] A fourth aspect of the present disclosure is A remote assistance system having a processor (12) for remotely assisting an automatic driving of a moving object (2), The processor Obtaining a request for assistance (Rd) from a mobile unit; generating instruction information (Io) instructed by an operator (8) in response to a request for assistance so as to be transmitted to the mobile unit; Collecting plan information (Ip) planned by the mobile object in response to the instruction information; Collecting behavior information (Ia) of the moving object after planning for the instruction information; The system is configured to output evaluation information (Ie) that evaluates the operator based on the trajectory gap (ΔT) between the planned trajectory (Tp) represented by the planning information and the actual trajectory (Ta) represented by the behavior information as the traveling trajectory of the moving body.

[0012] A fifth aspect of the present disclosure is a method for manufacturing a semiconductor device comprising: A remote assistance method executed by a processor (12) for remotely assisting an autonomous driving of a moving object (2), comprising: Obtaining a request for assistance (Rd) from a mobile unit; generating instruction information (Io) instructed by an operator (8) in response to a request for assistance so as to be transmitted to the mobile unit; Collecting plan information (Ip) planned by the mobile object in response to the instruction information; Collecting behavior information (Ia) of the moving object after planning for the instruction information; The method includes outputting evaluation information (Ie) that evaluates the operator based on the trajectory gap (ΔT) between the planned trajectory (Tp) represented by the planning information and the actual trajectory (Ia) represented by the behavior information as the traveling trajectory of the moving body.

[0013] A sixth aspect of the present disclosure is a method for manufacturing a semiconductor device comprising: A remote assistance program for remotely assisting automatic driving of a moving body (2), the remote assistance program being stored in a storage medium (10) and including instructions to be executed by a processor (12), The command is, Acquiring a request for assistance (Rd) from a mobile unit; generating instruction information (Io) instructed by an operator (8) in response to a support request so as to be transmitted to the mobile unit; Collecting plan information (Ip) planned by a mobile object in response to the instruction information; Collecting behavior information (Ia) of the moving object after planning for the instruction information; The method includes outputting evaluation information (Ie) that evaluates the operator based on the trajectory gap (ΔT) between the planned trajectory (Tp) represented by the planning information and the actual trajectory (Ia) represented by the behavior information as the traveling trajectory of the moving body.

[0014] In this way, in the fourth to sixth aspects, plan information planned for the instruction information and behavior information after the plan for the instruction information are collected from the moving body to which the instruction information of the operator is generated and transmitted. According to the fourth to sixth aspects, evaluation information is output that evaluates the operator based on the trajectory gap between the planned trajectory represented by the plan information and the actual trajectory represented by the behavior information as the traveling trajectory of the moving body. According to this, the content of the instruction that reflects the judgment ability of the operator can be properly evaluated based on the trajectory gap as a comparison result between the planned trajectory according to the instruction content and the actual trajectory that is the direct behavior information of the moving body. Therefore, it is possible to provide reliability to the evaluation of the ability of the operator to remotely support the automatic driving of the moving body. [Brief description of the drawings]

[0015] [Figure 1] 1 is a block diagram showing an overall configuration of an assistance system and a control system according to an embodiment; [Diagram 2] FIG. 2 is a block diagram showing a functional configuration of a control system according to an embodiment. [Diagram 3] FIG. 1 is a block diagram showing a functional configuration of a support system according to an embodiment. [Figure 4] 1 is a flowchart illustrating a real-time assistance flow according to an embodiment. [Diagram 5] FIG. 1 is a schematic diagram for explaining a real-time assistance flow according to an embodiment. [Figure 6] 1 is a flowchart showing an evaluation support flow according to an embodiment. [Figure 7] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 8] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 9] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 10] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 11] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 12] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 13] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 14] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 15] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 16] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. [Figure 17] FIG. 1 is a schematic diagram for explaining an evaluation support flow according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, one embodiment of the present disclosure will be described with reference to the drawings.

[0017] 1 is a management system for a moving object 2 that can be operated by a plurality of operators 8 at a remote center 9. The support system 1 is constructed so as to be capable of remotely supporting the autonomous driving of the plurality of moving objects 2.

[0018] The autonomous driving of the moving body 2 is controlled by the control system 3 of one embodiment while receiving remote assistance from the assistance system 1. Here, the moving body 2 is at least one of, for example, a car, a bus, and a truck that can travel on a road with an occupant on board. In such a moving body 2, autonomous driving control is realized, which is classified into levels according to the degree of manual intervention of the occupant in the driving task. The autonomous driving control may be realized by autonomous driving control, such as conditional driving automation, advanced driving automation, or complete driving automation, in which a system performs all driving tasks when activated. The autonomous driving control may be realized by advanced driving assistance control, such as driving assistance or partial driving automation, in which an occupant performs some or all driving tasks. The autonomous driving control may be realized by either one of the autonomous driving control and the advanced driving assistance control, a combination of them, or a switch between them.

[0019] The mobile object 2 is equipped with a sensor system 4, a communication system 5, an information presentation system 6, and a map database 7. The sensor system 4 acquires sensor information usable by the control system 3 by detecting the external and internal worlds of the mobile object 2. To this end, the sensor system 4 is configured to include an external sensor 40 and an internal sensor 42.

[0020] The external sensor 40 acquires external information as sensor information from the external world that is the surrounding environment of the mobile body 2. The external sensor 40 may acquire the external information by detecting a target object present in the external world of the mobile body 2. The external sensor 40 of the target detection type is at least one of a camera, a LiDAR (Light Detection and Ranging / Laser Imaging Detection and Ranging), a radar, a sonar, and the like.

[0021] The internal sensor 42 acquires internal information as sensor information from the internal world, which is the internal environment of the moving object 2. The internal sensor 42 may acquire the internal information by detecting a specific physical amount of motion in the internal world of the moving object 2. The internal sensor 42 of the physical amount detection type is at least one of a traveling speed sensor, an acceleration sensor, a gyro sensor, etc. The internal sensor 42 may acquire the internal information by detecting a specific state of an occupant in the internal world of the moving object 2. The internal sensor 42 of the occupant detection type is at least one of a driver status monitor (registered trademark), a biological sensor, a seating sensor, an actuator sensor, an in-vehicle equipment sensor, etc.

[0022] The communication system 5 acquires communication information usable by the control system 3 through wireless communication. The communication system 5 may receive a positioning signal from a satellite of a Global Navigation Satellite System (GNSS) existing in the external world of the mobile object 2. The positioning type communication system 5 is, for example, a GNSS receiver. The communication system 5 may transmit and receive a communication signal between the mobile object 2 and a V2X system existing in the external world of the mobile object 2. The V2X type communication system 5 is, for example, at least one of a Dedicated Short Range Communications (DSRC) communication device and a Cellular V2X (C-V2X) communication device. The communication system 5 may transmit and receive a communication signal between a terminal existing in the internal world of the mobile object 2. The terminal communication type communication system 5 is, for example, at least one of a Bluetooth (registered trademark) device, a Wi-Fi (registered trademark) device, and an infrared communication device.

[0023] The information presentation system 6 presents alarm information to the occupant inside the moving body 2. The information presentation system 6 may present the alarm information by stimulating the occupant's vision. The visual stimulation type information presentation system 6 is at least one of a head-up display (HUD), a multi-function display (MFD), a combination meter, a navigation unit, a light-emitting unit, etc. The information presentation system 6 may present the alarm information by stimulating the occupant's hearing. The auditory stimulation type information presentation system 6 is at least one of a speaker, a buzzer, a vibration unit, etc.

[0024] The map database 7 stores map information that can be used by the control system 3. The map database 7 includes at least one type of non-transitory tangible storage medium, such as a semiconductor memory, a magnetic medium, or an optical medium. The map database 7 may be a database of a locator that estimates the self-state quantity including the self-position of the mobile object 2. The map database 7 may be a database of a navigation unit that navigates the travel route of the mobile object 2. The map database 7 may be configured by combining a plurality of types of these databases.

[0025] The map database 7 acquires and stores the latest map information by, for example, communication with the remote center 9 via a V2X type communication system 5. Here, the map information is digitized in two dimensions or three dimensions as information representing the driving environment of the moving body 2. In particular, as the three-dimensional map information, digital data of a high-precision map is preferably adopted. The map information may include road information representing at least one of the position, shape, and road surface condition of the road itself. The map information may include marking information representing at least one of the positions and shapes of signs and dividing lines attached to the road. The map information may include structure information representing at least one of the positions and shapes of buildings and traffic lights facing the road.

[0026] The control system 3 includes at least one dedicated computer. The dedicated computer constituting the control system 3 is connected to a sensor system 4, a communication system 5, an information presentation system 6, and a map database 7 via at least one of a LAN (Local Area Network) line, a wire harness, an internal bus, and a wireless communication line, for example.

[0027] The dedicated computer constituting the control system 3 may be an integrated ECU (Electronic Control Unit) that integrates the driving control of the moving object 2. The dedicated computer constituting the control system 3 may be a judgment ECU that judges a driving task in the driving control of the moving object 2. The dedicated computer constituting the control system 3 may be a monitoring ECU that monitors the driving control of the moving object 2. The dedicated computer constituting the control system 3 may be an evaluation ECU that evaluates the driving control of the moving object 2.

[0028] The dedicated computer constituting the control system 3 may be a navigation ECU that navigates the travel route of the moving object 2. The dedicated computer constituting the control system 3 may be a locator ECU that estimates the self-state quantity of the moving object 2. The dedicated computer constituting the control system 3 may be an actuator ECU that controls a travel actuator of the moving object 2. The dedicated computer constituting the control system 3 may be an HCU (Human Machine Interface (HMI) Control Unit) that controls information presentation by an information presentation system 6 in the moving object 2. The dedicated computer constituting the control system 3 may be a computer other than the moving object 2 that constitutes a mobile terminal capable of communicating via, for example, a V2X type communication system 5.

[0029] The dedicated computer constituting the control system 3 has at least one memory 30 and one processor 32. The memory 30 is at least one type of non-transitory tangible storage medium, such as a semiconductor memory, a magnetic medium, or an optical medium, that non-temporarily stores computer-readable programs and data. The processor 32 includes at least one type of core, such as a central processing unit (CPU), a graphics processing unit (GPU), a reduced instruction set computer (RISC)-CPU, a data flow processor (DFP), or a graph streaming processor (GSP).

[0030] In the control system 3, the processor 32 executes a plurality of instructions included in a control program stored in the memory 30 in order to perform automatic driving control of the moving body 2. In this way, the control system 3 constructs a plurality of function blocks for performing automatic driving control of the moving body 2. The plurality of function blocks constructed in the control system 3 include a recognition block 300, a planning block 320, a monitoring block 340, a driving control block 360, and a communication control block 380, as shown in FIG.

[0031] The recognition block 300 acquires sensor information from the external sensor 40 and the internal sensor 42 of the sensor system 4. The recognition block 300 acquires communication information from the communication system 5. The recognition block 300 acquires map information from the memory 30. The recognition block 300 fuses these acquired information as inputs to determine the internal and external environments of the moving object 2 and recognize the driving scene.

[0032] Specifically, the recognition block 300 recognizes objects including other road users, obstacles, and structures in the external world of the mobile body 2. At this time, the recognition block 300 may further recognize at least one of the following with respect to the recognized object: distance, relative speed, relative acceleration, and attributes. The recognition block 300 recognizes the current and future travel paths of the mobile body 2. At this time, the recognition block 300 may further recognize at least one of the following with respect to the recognized travel path: road surface, lane, road edge, free space, traffic light, and marking.

[0033] The recognition block 300 estimates the self-state quantity including the self-position of the moving object 2 by localization. At this time, the recognition block 300 may update map information related to the traveling route of the moving object 2 at the same time as recognizing the self-state quantity, and feed back the update result to the map database 7. The recognition block 300 recognizes the time of each traveling scene of the moving object 2. At this time, the recognition block 300 may output time information related to the recognized time in association with other recognition results.

[0034] The planning block 320 acquires recognition information representing the recognition result from the recognition block 300. The recognition block 300 acquires communication information including instruction information Io from the remote center 9 through the communication system 5. The planning block 320 judges and chronologically plans the future route, future trajectory, and dynamic driving task (DDT) in the future action of the moving body 2, as well as future transitions of interactions between the moving body 2 and other road users, for each driving scene based on the acquired recognition information and instruction information Io. At this time, the planning block 320 may execute the judgment and plan using a vehicle driving model such as a simulation model or a machine learning model. Here, the DDT among the planning targets may be defined as real-time operation functions and tactical functions for operating the moving body 2 in traffic, or may be defined as all real-time operation functions and tactical functions necessary for operating the moving body 2 in road traffic.

[0035] Specifically, in a driving scene where a support request Rd to the remote center 9 has not been generated, the planning block 320 executes the plan without waiting for instruction information Io from the remote center 9. However, at this time, in an unreasonable situation where it is determined that an unreasonable risk exists, the planning block 320 generates a support request Rd requesting support from the operator 8 of the remote center 9, and passes it to the communication control block 380 so that it is transmitted from the communication system 5 to the remote center 9. Here, the support request Rd includes at least request information regarding the necessity of transition, the type of the transition destination DDT, and the transition timing for transitioning the moving object 2 from the current DDT to another future DDT.

[0036] Therefore, in the driving scene where the assistance request Rd to the remote center 9 is generated, the planning block 320 executes the plan while waiting for the instruction information Io from the remote center 9. At this time, the planning block 320 judges whether or not the moving object 2 can transition to the DDT represented by the instruction information Io. As a result, when the planning block 320 judges the transition to be positive, the planning block 320 executes the plan to realize the transition to the DDT at the instruction timing to (see Figs. 7 to 9 described later) which is the transition timing of the moving object 2 to the DDT represented by the instruction information Io. On the other hand, when the planning block 320 judges the transition to be negative, the planning block 320 executes the plan to realize the transition to the DDT by its own judgment by rejecting at least the instruction timing to of the instruction information Io.

[0037] The monitoring block 340 acquires recognition information from the recognition block 300. The monitoring block 340 monitors the risk between the moving object 2 and other road users in time series, in a system separate from the judgment in the planning block 320, based on the acquired recognition information.

[0038] Specifically, the monitoring block 340 sets a safety envelope based on the acquired recognition information for each driving scene, for example, taking into account a vehicle-level safety strategy. Here, the safety envelope may be defined as a set of limitations and conditions designed to operate the system as a constraint or control target in order to maintain the operation of the moving object 2 within an acceptable level of risk. Such a safety envelope may be set as a physically based margin around the moving object 2 and each road user including other road users, for example, a margin related to at least one type of physical quantity of motion among distance, speed, and acceleration.

[0039] The monitoring block 340 performs a safety judgment between the moving body 2 and other road users based on the set safety envelope and the acquired recognition information for each driving scene. That is, the monitoring block 340 realizes the safety judgment by testing whether or not there is a violation of the safety envelope in a driving scene interpreted based on the recognition information between the moving body 2 and other road users. Therefore, when the monitoring block 340 judges that there is a violation of the safety envelope, it sets appropriate actions to be taken for each transition state of the moving body 2 as an appropriate response as constraints on the moving body 2. Here, the constraints may be functional constraints or degraded constraints.

[0040] The driving control block 360 acquires planning information Ip representing the planning result from the planning block 320. The driving control block 360 controls the automatic driving of the moving body 2 so as to realize the DDT according to the acquired planning information Ip. At this time, the driving control block 360 gives control commands determined to realize the respective behaviors to the multiple traveling actuators that cause the moving body 2 to behave in accordance with the planning information Ip.

[0041] Specifically, the driving control block 360 acquires judgment information related to the safety envelope from the monitoring block 340. When the driving control block 360 acquires judgment information indicating that the safety envelope is not violated, the driving control block 360 realizes the DDT in the automatic driving control of the moving object 2 according to the plan information Ip without any constraints. On the other hand, when the driving control block 360 acquires judgment information indicating that the safety envelope is violated, the driving control block 360 imposes constraints based on the judgment information on the DDT in the automatic driving control of the moving object 2. At this time, the driving control block 360 may execute constraint processing on the automatic driving control by limiting the control command.

[0042] Here, acquisition of the judgment information from the monitoring block 340 may be performed by the planning block 320 instead of the operation control block 360. In this case, when the planning block 320 acquires judgment information indicating that the safety envelope is not violated, it executes the plan as described above. On the other hand, when the planning block 320 acquires judgment information indicating that the safety envelope is violated, it imposes a constraint based on the judgment information regarding the safety envelope to the DDT in the planning stage prior to the control stage without requesting an assistance request Rd to the remote center 9.

[0043] The communication control block 380 acquires recognition information from the recognition block 300. The communication control block 380 acquires the support request Rd and the plan information Ip from the plan block 320. The communication control block 380 acquires, from the driving control block 360, control command information representing a control command, as well as behavior information Ia representing an actual behavior Ba exhibited by the moving object 2 as a control result in response to the control command. The communication control block 380 controls the transmission of such acquired information to the remote center 9 by the communication system 5. At the same time, the communication control block 380 controls the reception of instruction information Io from the remote center 9 by the communication system 5.

[0044] As shown in FIG. 1, the support system 1 installed in the remote center 9 includes a support device 1a and a communication system 1b, and is mainly composed of at least one of a cloud server and an edge server. The communication system 1b forms at least a part of a V2X system capable of communicating with the communication system 5 of each moving object 2. The support device 1a is connected to the communication system 1b via at least one of a wired communication line and a wireless communication line. The support device 1a is configured to include at least one dedicated computer. In the support device 1a, an output control process is executed so that acquired information from each moving object 2 that can communicate through the communication system 1b is displayed and output to an operator 8 of the remote center 9. In the support device 1a, an input control process is executed so that instruction information Io (see FIG. 2) to be fed back to each moving object 2 that can communicate through the communication system 1b is input and received from the operator 8.

[0045] The dedicated computer constituting the support device 1a has at least one memory 10 and one processor 12. The memory 10 is at least one type of non-transitory tangible storage medium, such as a semiconductor memory, a magnetic medium, or an optical medium, that non-temporarily stores computer-readable programs and data. The processor 12 includes at least one type of core, such as a CPU, a GPU, or a RISC-CPU.

[0046] In the assistance device 1a, the processor 12 executes a plurality of instructions included in a remote assistance program stored in the memory 10 in order to carry out a remote assistance method for remotely assisting the autonomous driving of the moving body 2 by the assistance system 1. At this time, the instructions of the remote assistance program are executed in cooperation with instructions of a control program in the control system 3. In this way, the assistance device 1a constructs a plurality of functional blocks for carrying out the remote assistance method for the moving body 2 by the assistance system 1. The plurality of functional blocks constructed in the assistance device 1a include an assistance assignment block 100, an assistance execution block 110, an information collection block 120, a gap acquisition block 130, and an evaluation output block 140, as shown in FIG.

[0047] In the assistance device 1a, the processor 12 executes a remote assistance method for the moving body 2 by constructing these blocks 100, 110, 120, 130, and 140. Among these remote assistance methods, a real-time assistance method that supports the autonomous driving of the moving body 2 in real time is executed according to the real-time assistance flow shown in Fig. 4. Note that each "S" in the real-time assistance flow represents multiple steps executed by multiple commands included in the remote assistance program.

[0048] In S100, the assistance allocation block 100 in Fig. 3 judges whether or not an assistance request Rd requested from any of the moving objects 2 has been acquired through the communication system 1b. As a result, when it is judged that an assistance request Rd has been acquired, the real-time assistance flow proceeds to S101 as shown in Fig. 4.

[0049] In S101, the support allocation block 100 in Fig. 3 allocates an operator 8 to support the mobile unit 2 that has issued the support request Rd, based on the acquired support request Rd. At this time, the support allocation block 100 determines the priority of the support request Rd with respect to other support requests Rd based on at least one of the recognition information, the plan information Ip, the control command information, and the behavior information Ia acquired together with the support request Rd from the mobile unit 2 to be supported through the communication system 1b. Furthermore, the support allocation block 100 selects an operator 8 that matches the determined priority based on the operating status of each operator 8 and the evaluation information Ie for each operator 8, which will be described later. At this time, the support allocation block 100 may receive an input of an allocation instruction from a management operator who manages other operators 8 among all the operators 8 by requesting the management operator to allocate support.

[0050] 4, in the next S102, the support execution block 110 in FIG. 3 outputs the support request Rd to the operator 8 assigned to the support request Rd. At this time, the support execution block 110 outputs at least one of the recognition information, the plan information Ip, the control command information, and the behavior information Ia acquired together with the support request Rd by the support assignment block 100 in S101 to the assigned operator 8.

[0051] As shown in FIG. 4, in the next S103, the support execution block 110 in FIG. 3 receives an input of an instruction for the support destination moving object 2 from the operator 8 assigned to the support request Rd as a judgment result for the support request Rd. At this time, the instruction information Io generated according to the input from the operator 8 includes instruction information of the contents judged regarding at least the instruction timing to among the necessity of transition, the type of the transition destination DDT, and the instruction timing to as the transition timing (see FIGS. 7 to 9 described later) for transitioning the support destination moving object 2 from the current DDT to another future DDT. Here, an example of the type of the transition destination DDT is, for example, a departure task of the moving object 2 stopped at an intersection or a stopping position, and in this case, an example of the instruction timing to is the transition timing to the departure task. In particular, in this embodiment, the instruction information Io may be instructed by inputting an instruction from the operator 8 by remotely operating the moving object 2 at a remote cockpit or the like of the remote center 9.

[0052] In S103, the instruction information Io thus generated is stored in the memory 10 in association with the support request Rd. Particularly in S103 of this embodiment, a response time tr (see FIG. 13 described later) from the allocation of an operator 8 to the reception of an input of an instruction is stored in the memory 10 in association with the support request Rd and the instruction information Io.

[0053] 4, in the next S104, the support execution block 110 in FIG. 3 transmits, via the communication system 1b, instruction information Io generated according to an input from an operator 8 assigned to the support request Rd, to the support destination mobile body 2. Thus, in the previous S103, the instruction information Io is generated so that it can be transmitted to the support destination mobile body 2 in the subsequent S104.

[0054] As shown in Fig. 4, in the next S105, the information collection block 120 in Fig. 3 collects, through the communication system 1b, the recognition information, plan information Ip, and control command information of the support destination mobile object 2 that has received the instruction information Io, as judgment information Ij made by the mobile object 2 after the instruction information Io has been received. That is, after planning for the instruction information Io, the information collection block 120 collects judgment information Ij including the plan information Ip from the support destination mobile object 2. At the same time, in S105, the information collection block 120 collects, through the communication system 1b, behavior information Ia of the support destination mobile object 2 that has received the instruction information Io.

[0055] Here, in S105, the collection of the judgment information Ij and the behavior information Ia continues for a period from the transmission of the instruction information Io in S104 until a set time including the judgment timing tj (see Figs. 7 to 9 described later) which is the transition timing of the DDT judged in the moving body 2 has elapsed. During such a collection continuation period, it is assumed that the driving control block 360 or the planning block 320 imposes a constraint on the support destination moving body 2 after planning the plan information Ip for the instruction information Io. Therefore, the information collection block 120 of this embodiment in particular is capable of collecting the plan information Ip representing the planned trajectory Tp planned as shown in Fig. 5 for the instruction information Io, and the behavior information Ia representing the actual trajectory Ta to which a constraint is imposed as shown in the same figure for the planned trajectory Tp.

[0056] 4, in S105, the judgment information Ij and behavior information Ia collected in this way are stored in the memory 10 in association with the support request Rd and the instruction information Io, and are accumulated. This ends one real-time support flow. During the execution of the real-time support flow, in preparation for another support request Rd, another real-time support flow may be started in parallel with the currently executed step S101 and thereafter.

[0057] Among the remote assistance methods for the moving object 2, the evaluation assistance method for assisting the evaluation of each operator 8 is executed according to the evaluation assistance flow shown in Fig. 6. Note that each "S" in the evaluation assistance flow also means a plurality of steps executed by a plurality of commands included in the remote assistance program.

[0058] 3 reads out data sets of the support request Rd, the instruction information Io, the judgment information Ij including the plan information Ip, and the behavior information Ia, which are stored in association with each other in the memory 10. The reading out at this time may be performed for each data set upon completion of one real-time support, or may be performed all at once for multiple data sets resulting from multiple completed real-time support sessions. Therefore, the following description of each step will representatively be a description of the processing for one data set.

[0059] 6, in the next S111, the gap acquisition block 130 in Fig. 3 acquires a time gap Δt between the instruction timing to represented by the instruction information Io and the judgment timing tj represented by the judgment information Ij corresponding to the instruction information Io, as the transition timing of the DDT by the moving object 2. At this time, the gap acquisition block 130 calculates the time difference from the instruction timing to to the judgment timing tj as the time gap Δt.

[0060] Specifically, in S111, as shown in Figs. 7 and 8, the gap acquisition block 130 may calculate the time gap Δt from the instruction timing to which the instruction information Io is directly represented by time. As shown in Fig. 7, the gap acquisition block 130 may calculate the time gap Δt from the judgment timing tj which the judgment information Ij is directly represented by time. As shown in Figs. 8 and 9, the gap acquisition block 130 may calculate the time gap Δt from the judgment timing tj which the judgment information Ij indirectly represents by the motion physical quantity such as the vehicle speed, steering angle, or acceleration / deceleration of the moving body 2. As shown in Fig. 9, when the instruction information Io is instructed by the operator 8 by remote operation of the moving body 2 as an input, the gap acquisition block 130 may calculate the time gap Δt from the instruction timing to which the instruction information Io indirectly represents by the operation amount of the remote operation. Furthermore, when instruction information Io is instructed by operator 8 by remote operation, prior judgment information Ij preceding the instruction information Io may be acquired by S105 and read out by S110, and the time difference from the prior judgment timing tj to the instruction timing to may be calculated as the time gap Δt.

[0061] As shown in Fig. 6, in the next S112, the evaluation output block 140 in Fig. 3 generates evaluation information Ie that evaluates the operator 8 corresponding to the instruction information Io based on the acquired time gap Δt. At this time, the evaluation output block 140 compares the time gap Δt acquired in S111 with a time reference threshold value that is clustered for each type of driving scene as shown in Fig. 10 for the time gap Δt previously stored in the memory 10 and set to, for example, an average value, a median value, or a mode value.

[0062] As a result of comparing the time gap Δt with the time reference threshold value, in S112 shown in Fig. 6, if the time gap Δt is equal to or exceeds the time reference threshold value, the evaluation output block 140 in Fig. 3 determines that the command judgment by the operator 8 was an abnormal judgment. In this case, the evaluation output block 140 generates an abnormality flag indicating the judgment result of the abnormal judgment as evaluation information Ie, and accumulates the evaluation information Ie by storing it in the memory 10 associated with the operator 8 to be evaluated.

[0063] As shown in Fig. 6, in the next S113, the gap acquisition block 130 in Fig. 3 acquires a trajectory gap ΔT between a planned trajectory Tp represented by the plan information Ip planned for the instruction information Io as a travel trajectory of the moving body 2 and an actual trajectory Ta represented by the behavior information Ia that appears after the plan. At this time, as shown in Fig. 11, the gap acquisition block 130 may extract a representative value such as an average value or a median value of the aggregated distance by tallying up the distance between the trajectories Tp and Ta at the same time or a distance calculated by DTW (Dynamic Time Warping) as the trajectory gap ΔT. The gap acquisition block 130 may extract a representative value such as an average value or a median value of the aggregated deviation by tallying up the attitude angle deviation between the trajectories Tp and Ta at the same time as the trajectory gap ΔT.

[0064] As shown in Fig. 6, in the next S114, the evaluation output block 140 in Fig. 3 also generates evaluation information Ie based on the acquired trajectory gap ΔT. At this time, the evaluation output block 140 compares the trajectory gap ΔT acquired in S113 with a trajectory reference threshold value that is clustered for each type of driving scene regarding the trajectory gap ΔT previously stored in the memory 10 and set to, for example, an average value, a median value, or a mode value. Here, the comparison of the trajectory gap ΔT with the trajectory reference threshold value is performed regardless of the presence or absence of a constraint on the actual trajectory Ta represented by the behavior information Ia, or only when the constraint is applied to the actual trajectory Ta.

[0065] As a result of comparing the trajectory gap ΔT with the trajectory threshold value, in S114 shown in Fig. 6, if the trajectory gap ΔT is equal to or exceeds the trajectory reference threshold value, the evaluation output block 140 in Fig. 3 determines that the command judgment by the operator 8 was an abnormal judgment. In this case, the evaluation output block 140 generates an abnormality flag representing the judgment result of the abnormal judgment as evaluation information Ie, and accumulates the evaluation information Ie by storing it in the memory 10 associated with the operator 8 to be evaluated.

[0066] 6, in the next S115, the gap acquisition block 130 in Fig. 3 acquires a behavior gap ΔB between the actual behavior Ba of the moving object 2 represented by the behavior information Ia that emerged after planning for the instruction information Io and the statistical behavior Bs represented by the statistical information Is regarding the actual behavior Ba previously accumulated in the memory 10. Here, the statistical information Is includes information on the statistical behavior Bs that is clustered for each type of traveling scene and set to, for example, an average value, a median value, or a mode value regarding the actual behavior Ba previously accumulated in the memory 10.

[0067] Therefore, the gap acquisition block 130 in S115 may extract, as the behavior gap ΔB, a difference between the value represented by the statistical behavior Bs and the amount of change over time of a physical quantity of motion, such as vertical acceleration, which represents the actual behavior Ba in a driving scene of sudden braking that occurred in the moving body 2 after planning for the instruction information Io. The gap acquisition block 130 may extract, as the behavior gap ΔB, a difference between the value represented by the statistical behavior Bs and the amount of change over time of a physical quantity of motion, such as vertical acceleration, lateral acceleration, attitude angle, TTC (Time To Collision), or TTV (Time To Vehicle), which represents the actual behavior Ba in a driving scene of risk avoidance that occurred in the moving body 2 after planning for the instruction information Io.

[0068] As shown in Fig. 6, in the next S116, the evaluation output block 140 in Fig. 3 also generates evaluation information Ie based on the acquired behavior gap ΔB. At this time, the evaluation output block 140 compares the behavior gap ΔB acquired in S115 with a behavior reference threshold value that determines the boundary between normal judgment and abnormal judgment.

[0069] As a result of comparing the behavior gap ΔB with the behavior reference threshold, in S116 shown in Fig. 6, if the behavior gap ΔB is equal to or exceeds the behavior reference threshold, the evaluation output block 140 in Fig. 3 determines that the command judgment by the operator 8 was an abnormal judgment. In this case, the evaluation output block 140 generates an abnormality flag indicating the judgment result of the abnormal judgment as evaluation information Ie, and accumulates the evaluation information Ie by storing it in the memory 10 associated with the operator 8 to be evaluated. Note that the abnormality judgment in S116 may be performed by, for example, variance analysis or k-nearest neighbor analysis on the current and past behavior gaps ΔB for each operator 8.

[0070] As shown in FIG. 6, in the next S117, the evaluation output block 140 of FIG. 3 displays and outputs the evaluation information Ie for each operator 8 stored in the memory 10. At this time, before displaying and outputting, the evaluation output block 140 extracts the ratio of the instruction information Io for which an abnormal flag is set based on at least one of the gaps Δt, ΔT, and ΔB, and indexes the reciprocal of the extracted ratio as the evaluation information Ie for evaluating the safety of the instruction by each operator 8. Therefore, as shown in FIG. 12, the evaluation output block 140 may compare and display the indexed evaluation information Ie of the safety for each operator 8. As shown in FIG. 13, the evaluation output block 140 may compare and display representative values, such as the average value, median value, or mode value, of the response time tr stored in the memory 10 for each operator 8. As shown in FIG. 14, the evaluation output block 140 may further analyze the instruction characteristics of each operator 8 as the evaluation information Ie based on the indexed evaluation information Ie of the safety and the response time tr, and display a scatter diagram of the analysis results for those operators 8.

[0071] As shown in Fig. 15, the evaluation output block 140 may display, as evaluation information Ie, a time change in the abnormality rate, which is the extraction rate of instruction information Io for which an abnormality flag is set, for each operator 8. As shown in Fig. 16, the evaluation output block 140 may normalize the indexed safety evaluation information Ie between operators 8 in a set number of people unit, and display the corresponding point and ranking in the normalized distribution for each operator 8. As shown in Fig. 17, the evaluation output block 140 may display a correlation distribution between the indexed safety evaluation information Ie and response time tr, and the corresponding point for each operator 8 in the correlation distribution.

[0072] In this way, one evaluation support flow ends as shown in Fig. 6. The evaluation information Ie displayed and output as described above is stored in the memory 10 and accumulated, and is used for, for example, allocation of the operator 8 in the real-time support flow.

[0073] (Action and effect) The effects of the present embodiment described above will be described below.

[0074] In this embodiment, from the moving body 2 to which the instruction information Io of the operator 8 in response to the support request Rd is generated and transmitted, judgment information Ij judged in response to the instruction information Io is collected. According to this embodiment, evaluation information Ie evaluating the operator 8 based on the time gap Δt between the instruction timing to represented by the instruction information Io and the judgment timing tj represented by the judgment information Ij as the transition timing of the DDT by the moving body 2 is output. According to this, the instruction timing to reflecting the judgment ability of the operator 8 can be appropriately evaluated based on the time gap Δt as a comparison result with the judgment timing tj, which is the direct judgment information Ij of the moving body 2. Therefore, it is possible to provide reliability to the ability evaluation of the operator 8 to remotely support the automatic driving of the moving body 2.

[0075] In this embodiment, from the moving body 2 to which the instruction information Io of the operator 8 in response to the support request Rd is generated and transmitted, plan information Ip planned for the instruction information Io and behavior information Ia after the plan for the instruction information Io are collected. According to this embodiment, evaluation information Ie that evaluates the operator 8 based on the trajectory gap ΔT between the planned trajectory Tp represented by the plan information Ip and the actual trajectory Ta represented by the behavior information Ia as the travel trajectory of the moving body 2 is output. According to this, the contents of the instruction that reflect the judgment ability of the operator 8 can be properly evaluated based on the trajectory gap ΔT as a comparison result between the planned trajectory Tp according to the instruction contents and the actual trajectory Ta, which is the direct behavior information Ia of the moving body 2. Therefore, it is possible to provide reliability to the evaluation of the ability of the operator 8 to remotely support the automatic driving of the moving body 2.

[0076] According to this embodiment, behavior information Ia is collected that represents an actual trajectory Ta with constraints imposed by the moving body 2 on the plan information Ip. This allows the contents of instructions that reflect the judgment ability of the operator 8 to be properly evaluated based on the trajectory gap ΔT, which is a comparison result between the planned trajectory Tp according to the contents of the instructions and the actual trajectory Ta with constraints imposed as the direct behavior information Ia of the moving body 2. Therefore, it is possible to increase the reliability of the evaluation of the ability of the operator 8 to remotely support the automatic driving of the moving body 2.

[0077] According to this embodiment, evaluation information Ie is output based on a behavior gap ΔB between the actual behavior Ba of the moving object 2 represented by the behavior information Ia and the statistical behavior Bs represented by the statistical information Is accumulated regarding the actual behavior Ba. According to this, the content of the instruction reflecting the judgment ability of the operator 8 can be properly evaluated based on the behavior gap ΔB as a comparison result between the direct actual behavior Ba of the moving object 2 with respect to the plan information Ip according to the instruction content and the statistical behavior Bs, which is the statistical information Is of the past actual behavior Ba. Therefore, it is possible to increase the reliability of the ability evaluation of the operator 8 who remotely supports the automatic driving of the moving object 2.

[0078] According to this embodiment, the instruction information Io instructed by the operator 8 by remote operation of the moving body 2 may be generated. In this case, the instruction timing to reflecting the remote operation ability including the judgment ability of the operator 8 can be properly evaluated based on the time gap Δt as a comparison result with the judgment timing tj which is the direct judgment information Ij of the moving body 2. In addition, the content of the instruction reflecting the remote operation ability including the judgment ability of the operator 8 can be properly evaluated based on the trajectory gap ΔT as a comparison result between the planned trajectory Tp according to the instruction content and the actual trajectory Ta which is the direct behavior information Ia of the moving body 2. Furthermore, the content of the instruction reflecting the remote operation ability including the judgment ability of the operator 8 can be properly evaluated based on the behavior gap ΔB as a comparison result between the direct actual behavior Ba of the moving body 2 with respect to the planned information Ip according to the instruction content and the statistical behavior Bs which is the statistical information Is of the past actual behavior Ba. From these points, it is possible to provide reliability to the ability evaluation of the operator 8 who remotely supports the automatic driving of the moving body 2 by remote operation.

[0079] (Other embodiments) Although one embodiment has been described above, the present disclosure should not be construed as being limited to the embodiment described above, and can be applied to various embodiments within the scope not departing from the gist of the present disclosure.

[0080] In a modified example, the dedicated computer constituting the support device 1a and / or the control system 3 of the support system 1 may have at least one of a digital circuit and an analog circuit as a processor. Here, the digital circuit is at least one of ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), CPLD (Complex Programmable Logic Device), etc. Furthermore, such a digital circuit may have a memory that stores a program.

[0081] In a modified example, the constraint by the monitoring block 340 may not be applied to at least the actual trajectory Ta. In a modified example, at least one of the pair of S113, S114 and the pair of S115, S116 may not be executed. In a modified example, at least one of the pair of S111, S112 and the pair of S115, S116 may not be executed. [Explanation of symbols]

[0082] 1: Support system, 2: Mobile object, 8: Operator, 10: Memory, 12: Processor, Ba: Actual behavior, Bs: Statistical behavior, Ia: Behavior information, Ie: Evaluation information, Ij: Judgment information, Io: Instruction information, Ip: Planned information, Is: Statistical information, Rd: Support request, Ta: Actual trajectory, Tp: Planned trajectory, tj: Judgment timing, to: Instruction timing, ΔB: Behavior gap, ΔT: Trajectory gap, Δt: Time gap

Claims

1. A remote assistance system having a processor (12) for remotely assisting an autonomous driving of a moving object (2), comprising: The processor, Obtaining a request for assistance (Rd) from the mobile unit; generating instruction information (Io) instructed by an operator (8) in response to the assistance request so as to be transmitted to the mobile unit; Collecting judgment information from the mobile body capable of communication, the judgment information including plan information (Ip) planned by the control system based on recognition information of a driving scene, so as to realize a transition of a dynamic driving task represented by the instruction information when a positive judgment is made by a control system of the mobile body as judgment information (Ij) judged by the mobile body in response to the instruction information, and to realize a transition of a dynamic driving task represented by the instruction information when the control system rejects the instruction information and makes a self-judgment; and outputting evaluation information (Ie) that evaluates the operator based on the time gap (Δt) between the instruction timing (to) represented by the instruction information and the judgment timing (tj) represented by the judgment information as the transition timing of the dynamic driving task by the moving body.

2. The processor, Collecting plan information (Ip) planned by the moving object in response to the instruction information; and collecting behavior information (Ia) that appears in the moving object after planning for the instruction information. Outputting the evaluation information includes: The remote assistance system according to claim 1, further comprising: outputting the evaluation information based on a trajectory gap (ΔT) between a planned trajectory (Tp) represented by the planning information and an actual trajectory (Ta) represented by the behavior information as the traveling trajectory of the moving body.

3. A remote assistance system having a processor (12) for remotely assisting an autonomous driving of a moving object (2), comprising: The processor, Obtaining a request for assistance (Rd) from the mobile unit; generating instruction information (Io) instructed by an operator (8) in response to the assistance request so as to be transmitted to the mobile unit; Collecting plan information (Ip) planned by the moving object in response to the instruction information; Collecting behavior information (Ia) exhibited by the moving object after planning for the instruction information; and outputting evaluation information (Ie) that evaluates the operator based on a trajectory gap (ΔT) between a planned trajectory (Tp) represented by the planning information and an actual trajectory (Ta) represented by the behavior information as the traveling trajectory of the moving body.

4. Collecting the behavioral information includes: The remote assistance system according to claim 2 or 3, further comprising: collecting the behavior information representing the actual trajectory constrained by the moving object with respect to the plan information.

5. Outputting the evaluation information includes: A remote assistance system as described in any one of claims 2 to 4, which outputs the evaluation information based on a behavior gap (ΔB) between the actual behavior (Ba) of the moving body represented by the behavior information and the statistical behavior (Bs) represented by statistical information (Is) accumulated regarding the actual behavior.

6. generating the indication information 6. The remote assistance system according to claim 1, further comprising generating the instruction information instructed by the operator through remote control of the mobile object.

7. A remote assistance method executed by a processor (12) for remotely assisting autonomous driving of a moving object (2), comprising: Obtaining a request for assistance (Rd) from the mobile unit; generating instruction information (Io) instructed by an operator (8) in response to the assistance request so as to be transmitted to the mobile unit; Collecting judgment information from the mobile body capable of communication, the judgment information including plan information (Ip) planned by the control system based on recognition information of a driving scene, so as to realize a transition of a dynamic driving task represented by the instruction information when a positive judgment is made by a control system of the mobile body as judgment information (Ij) judged by the mobile body in response to the instruction information, and to realize a transition of a dynamic driving task represented by the instruction information when the control system rejects the instruction information and makes a self-judgment; and outputting evaluation information (Ie) that evaluates the operator based on a time gap (Δt) between an instruction timing (to) represented by the instruction information and a judgment timing (tj) represented by the judgment information as a transition timing of a dynamic driving task by the moving body.

8. A remote assistance method executed by a processor (12) for remotely assisting autonomous driving of a moving object (2), comprising: Obtaining a request for assistance (Rd) from the mobile unit; generating instruction information (Io) instructed by an operator (8) in response to the assistance request so as to be transmitted to the mobile unit; Collecting plan information (Ip) planned by the moving object in response to the instruction information; Collecting behavior information (Ia) exhibited by the moving object after planning for the instruction information; and outputting evaluation information (Ie) that evaluates the operator based on a trajectory gap (ΔT) between a planned trajectory (Tp) represented by the planning information and an actual trajectory (Ta) represented by the behavior information as the traveling trajectory of the moving body.

9. A remote assistance program for remotely assisting automatic driving of a moving object (2), the remote assistance program being stored in a storage medium (10) and including instructions to be executed by a processor (12), The instruction: Acquiring a request for assistance (Rd) from the mobile unit; generating instruction information (Io) instructed by an operator (8) in response to the assistance request so as to be transmitted to the mobile unit; Collecting judgment information from the mobile body capable of communication, the judgment information including plan information (Ip) planned by the control system based on recognition information of a driving scene, so as to realize a transition of a dynamic driving task represented by the instruction information when a positive judgment is made by a control system of the mobile body as judgment information (Ij) judged by the mobile body in response to the instruction information, and to realize a transition of a dynamic driving task when the control system rejects the instruction information and makes a self-judgment; and outputting evaluation information (Ie) that evaluates the operator based on a time gap (Δt) between an instruction timing (to) represented by the instruction information and a judgment timing (tj) represented by the judgment information as a transition timing of a dynamic driving task by the moving body.

10. A remote assistance program for remotely assisting automatic driving of a moving object (2), the remote assistance program being stored in a storage medium (10) and including instructions to be executed by a processor (12), The instruction: Acquiring a request for assistance (Rd) from the mobile unit; generating instruction information (Io) instructed by an operator (8) in response to the assistance request so as to be transmitted to the mobile unit; Collecting plan information (Ip) planned by the moving object in response to the instruction information; Collecting behavior information (Ia) exhibited by the moving object after planning for the instruction information; and outputting evaluation information (Ie) that evaluates the operator based on a trajectory gap (ΔT) between a planned trajectory (Tp) represented by the planning information and an actual trajectory (Ta) represented by the behavior information as the traveling trajectory of the moving body.

Images