control device

Abstract

To provide an automatic control technique that can reduce frequencies at which a use intervenes.SOLUTION: A control device relating to one aspect in the disclosure selects one or more control models out of a plurality of control models, using a selection model; derives a control command for a moving body, using the selected one or more control models; unless intervention operation is performed, controls motion of the moving body, in accordance with the derived control command and when the intervention operation is performed, discards the derived control command or overlaps with the derived control command, and controls motion of the moving body, in accordance with operation of intervention by a user. The selection model is configured to select one or more control models so as to avoid occurrence of intervention from a history of n intervention performed by the user.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a control device.

Background Art

[0002] In Patent Document 1, a system for autonomous vehicle control configured to determine vehicle commands from routes, GPS data, and sensor data using a trained neural network has been proposed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] One object of the present disclosure is to provide an automatic control technology capable of reducing the frequency of user intervention.

Means for Solving the Problems

[0005] A control device according to a first aspect of this disclosure comprises a storage unit for storing a plurality of control models and a selection model, and a control unit. Each control model is configured to derive a control command for automatically controlling the movement of a mobile object. The control unit is configured to perform the following actions based on the selection model: select one or more control models from the plurality of control models; derive a control command for the mobile object using the selected one or more control models; control the movement of the mobile object according to the derived control command if there is no user intervention; and, if there is a user intervention, discard the derived control command or overlap the derived control command to control the movement of the mobile object according to the user intervention. The selection model is configured to select one or more control models based on the user's intervention history to avoid user intervention. At least one of the plurality of control models and the selection model may be a trained machine learning model. A neural network may be used as the machine learning model. [Effects of the Invention]

[0006] According to this disclosure, a reduction in the frequency of user intervention can be expected. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 schematically illustrates an example of a scenario in which this disclosure applies. [Figure 2] Figure 2 schematically shows an example of the data structure of the intervention history in this disclosure. [Figure 3] Figure 3 schematically shows an example of the hardware configuration of the control device of this disclosure. [Figure 4] Figure 4 shows an example of a processing procedure related to control by the control device of this disclosure. [Modes for carrying out the invention]

[0008] Conventionally, rule-based autonomous driving systems are known. Furthermore, according to methods such as those described in Patent Document 1, an autonomous driving system can be constructed using a trained machine learning model. However, the control of autonomous driving by a control model (rule-based model or machine learning model) is not always suitable for the user. If the control of autonomous driving by a control model is not suitable for the user, user intervention will occur, and the autonomous driving will not be practical. If the system is not implemented, manual driving will be performed. If the automated driving model does not suit the user well, the automated driving system may hardly be used, and there is a risk that the user will frequently intervene. This problem can occur regardless of the type of vehicle. Moreover, this problem is not limited to situations where vehicles are controlled. The same applies to moving objects other than vehicles when it comes to controlling movement. Therefore, the same problem can occur when controlling any moving object other than a vehicle.

[0009] In contrast, the control device according to the first aspect of the present disclosure comprises a storage unit for storing a plurality of control models and selection models, and a control unit. Each control model is configured to derive control commands for automatically controlling the movement of a mobile object. The control unit is configured to perform the following actions based on the selection model: select one or more control models from the plurality of control models; derive control commands for the mobile object using the selected one or more control models; control the movement of the mobile object according to the derived control commands if there is no user intervention; and, if there is a user intervention, discard the derived control commands or overlap the derived control commands to control the movement of the mobile object according to the user intervention. The selection model is configured to select one or more control models from the user's intervention history to avoid the occurrence of user interventions.

[0010] In a first aspect of this disclosure, the selection model is constructed to select a control model to avoid user interventions based on an intervention history that shows a record of past user interventions. In a simple example, the selection model may be constructed to select a different control model in situations where an intervention occurred in the past, rather than using the same control model in a new situation. By adjusting the control model used for automatic control using a selection model constructed from the intervention history in this way, the derived control commands can be adapted to the user. As a result, according to this disclosure, a reduction in the frequency of user interventions can be expected.

[0011] As another form of the control device according to the above embodiment, one aspect of this disclosure may be an information processing method, a program, or a machine-readable storage medium that stores such a program. Here, a machine-readable storage medium is a medium that stores information such as a program by electrical, magnetic, optical, mechanical, or chemical action.

[0012] [1. Application Examples] Figure 1 schematically shows an example of a scenario in which the present disclosure is applied. The control device 1 according to this embodiment is one or more computers configured to control the automatic movement of a target mobile body M. In this embodiment, the control device 1 is mounted on the mobile body M and holds a selection model 20 and a plurality of control models 30. Each control model 30 is configured to derive control commands in order to perform automatic control of the movement of the mobile body M.

[0013] In this embodiment, the control device 1 selects one or more control models 35 from a plurality of control models 30 using the selection model 20, and derives a control command 50 for the mobile body M using the selected one or more control models 35. If the derived control command 50 is appropriate, the user is more likely to accept the automatic control by that control command 50 and less likely to intervene with user operations 55. However, if the derived control command 50 is not appropriate, it is assumed that the user is more likely to intervene with user operations 55. For example, if the speed of the mobile body M in the automatic control by the control model 35 is suitable for the user, the possibility of acceleration or deceleration intervention is low, but if the speed of the mobile body M is slow or fast, the possibility of acceleration or deceleration intervention is expected to increase.

[0014] If there is no user intervention operation 55, the control device 1 controls the movement of the mobile body M according to the derived control command 50. On the other hand, if there is no user intervention operation 55 If such an event occurs, the derived control command 50 is discarded or overlapped with the derived control command 50 to control the movement of the mobile body M according to the user intervention operation 55. When an intervention operation 55 occurs, the control device 1 records information indicating that intervention as intervention history 60. The more user interventions occur, the more the intervention history 60 is accumulated. The selection model 20 is configured to select one or more control models 35 from the user intervention history 60 to avoid the occurrence of user interventions.

[0015] In situations identical or similar to those in which interventions have occurred in the past, repeatedly executing the same automated control as in those situations is likely to result in further user intervention. Therefore, in this embodiment, a selection model 20 is constructed to select a control model 35 that avoids user intervention based on a record of past user intervention operations (intervention history 60). In other words, in this embodiment, multiple control models 30 are deployed, and the intervention history 60 is used to optimize the control model 35 used for automated control (i.e., selected by the selection model 20) based on the trends of past user interventions. This allows the control device 1 to avoid using control models that are presumed to be unsuitable for the user in the target situation based on past intervention trends, and to actively use control models that are more likely to be suitable for the user. As a result, according to this embodiment, a reduction in the frequency of user interventions can be expected. In addition, by reducing the frequency of user operations, wear on the operating tools of the mobile body M (for example, if the mobile body M is a vehicle, the steering wheel, accelerator pedal, brake pedal, etc.) can be suppressed, and the lifespan of the operating tools can be expected to be extended.

[0016] (Mobile) The type of mobile body M can be appropriately selected depending on the embodiment, as long as it can move automatically by mechanical control. The mobile body M may be, for example, a mobile device such as a vehicle, an aircraft, a ship, or a robotic device. The aircraft may be at least one of an unmanned aircraft such as a drone or a manned aircraft. In one example, as shown in Figure 1, the mobile body M may be a vehicle. In this case, it can be expected that the frequency of user intervention will be reduced when the vehicle is driven automatically. When the mobile body M is a vehicle, the type of vehicle (number of wheels, power source, size, etc.) may be arbitrarily selected. As a typical example, the mobile body M may be an automobile with Level 2 or higher autonomous driving capability.

[0017] (Controlling actions) In one example, controlling the operation of the target moving body M may be configured by directly controlling the target moving body M. In another example, the moving body M may include a dedicated control device such as a controller. In this case, controlling the operation of the target moving body M by the control device 1 may be configured by indirectly controlling the target moving body M by providing a derivation result to the dedicated control device. Note that the control device 1 may be deployed at any location. In one example, as shown in FIG. 1, the control device 1 may be mounted on the moving body M. In another example, the control device 1 may be arranged away from the moving body M and remotely control the moving body M.

[0018] (Control model) Each control model 30 is constructed to derive a control command according to the environment of the moving body M. The environment is an event observed at at least one of the moving body M itself and its surroundings. In one example, at least a part of the environment may be observed by one or more sensors S arranged inside or outside the moving body M. The type of the sensor S need not be particularly limited as long as it can observe any environment in which the moving body M moves, and may be appropriately selected according to the embodiment. In one example, the one or more sensors S may include a camera (image sensor), radar, LiDAR (Light Detection And Ranging), sonar (ultrasonic sensor), infrared sensor, GNSS (Global Navigation Satellite System) / GPS (Global Positioning Satellite) module, and the like.

[0019] If it is possible to derive a control command from the environment of the moving body M, the input / output format of each control model 30 may be appropriately selected according to the embodiment. In one example, at least any one of the plurality of control models 30 may be configured to derive a control command from observation data of sensors at one or more time points. In another example, at least any one of the control models may be configured to derive a control command from the recognition result of the surrounding environment. In this case, the control device 1 may further include an analysis model that infers the recognition result of the surrounding environment from the observation data of the sensors. Alternatively, at least any one of the control models may include an analysis model. The analysis model may be arbitrarily configured. In one example, the analysis model may be configured by a machine learning model. Other information may be arbitrarily added to the input of at least any one of the control models. At least any one of the control models may be configured to further receive an input of arbitrary information such as, for example, a set speed, a limit speed, a position, map information, navigation information, etc.

[0020] Each control model 30 may be configured by at least any one of a trained machine learning model and a rule-based model. The rule-based model collates a given input (for example, information indicating an environment such as observation data, recognition result of the surrounding environment, etc.) with rules, and derives a control command according to the result of the collation (in accordance with the rules that match). The rules may be set manually or at least partially automatically. The machine learning model is configured to have one or more arithmetic parameters that can be adjusted by machine learning. The one or more arithmetic parameters are used for the arithmetic of the target inference (in this disclosure, the derivation of the control command). Machine learning is to adjust (optimize) the values of the arithmetic parameters using learning data. The machine learning model may be configured by, for example, a neural network, a support vector machine, a regression model, a decision tree model, etc. The method of machine learning may be appropriately selected according to the machine learning model adopted (for example, the error backpropagation method, etc.).

[0021] As an example, at least one of the control models may be constructed using a neural network. The structure of the neural network may be determined as appropriate depending on the embodiment, and may be specified, for example, by the number of layers from the input layer to the output layer, the type of each layer, the number of nodes (neurons) contained in each layer, the connectivity between nodes in each layer, etc. In one example, the neural network may have a recursive structure. Furthermore, the neural network may include any layers such as fully connected layers, convolutional layers, pooling layers, deconvolutional layers, unpooling layers, normalization layers, dropout layers, LSTM (Long Short-Term Memory), etc. The neural network may have any mechanisms such as an attention mechanism. The control model may include any model such as a GNN (Graph neural network), a diffusion model, or a generative model (e.g., Generative Adversarial Network, Transformer, etc.). When a neural network is used as the control model, the weights of the connections between each node in the control model and the thresholds of each node are examples of computational parameters. When a machine learning model is adopted, the control model may be structured as an end-to-end model.

[0022] Furthermore, at least one of the multiple control models 30 is configured to be able to derive different control commands from the other control models under the same environment or the same movement pattern. This ensures that if automatic control by one of the multiple control models 30 is not suitable for the user (intervention occurs), the feasibility of executing automatic control suitable for the user can be ensured by using another control model. In other words, the possibility of discovering a control model 35 suitable for the user can be ensured by selecting the selection model 20.

[0023] For example, the structures of a trained machine learning model and a rule-based model may differ. Therefore, the automatic control characteristics of the trained machine learning model and the rule-based model may differ from each other. Thus, multiple control models 30 may include one or more trained machine learning models and one or more rule-based models. This ensures variations in the characteristics of automatic control and increases the probability that a control model 30 suitable for the user exists. As a result, a reduction in the frequency of user interventions can be expected.

[0024] In another example, the automatic control characteristics of a trained machine learning model may depend on the training conditions. Therefore, the characteristics of machine learning models trained under different training conditions (e.g., different training samples used for machine learning, changes in sampling probability, etc.) may differ. Also, if the structure of the machine learning model differs, the inference results of the machine learning model may also differ. Therefore, multiple control models 30 may include multiple trained machine learning models, each differing in at least one of the training conditions and / or structure. This allows for the same effects as described above. If multiple control models 30 include multiple rule-based models, the rules of each rule-based model may differ.

[0025] Furthermore, the control required may differ from scene to scene. Therefore, each control model 30 may be prepared for each scene. For example, if the moving object M is a vehicle, multiple control models 3 may be prepared for each scene, such as lane changes, lane keeping, and emergency stops (EDSS: Emergency Driving Stop System). A value of 0 may be provided. In this case, the multiple control models 30 may be configured to include at least two control models that can be used for automatic control in at least one identical or overlapping scene among the scenes for which automatic control is to be performed. That is, the control device 1 may maintain two or more control models for identical or overlapping scenes. For example, when the moving object M is a vehicle, the multiple control models 30 may include a first control model and a second control model that target the same lane change. In this case, the first control model and the second control model may be configured to derive different control commands so that the control contents such as the timing of the lane change, speed, and steering angle differ from each other, even in the same lane change scenario.

[0026] (Control command) The control command (control command 50) relates to the operation of the mobile body M. The configuration of the control command may be appropriately selected depending on the embodiment. In one example, the control command may consist of acceleration, deceleration, steering, or a combination thereof. Acceleration and deceleration may include gear changes. If at least one of acceleration, deceleration, and steering is included, the control command may be expressed as a path. Accordingly, each control model 30 may be expressed as a path planner. The control command may also further include commands relating to the operation of the mobile body M. For example, if the mobile body M is a vehicle, the control command may include vehicle operations such as turn signals, hazard lights, horn, and communication processing (e.g., sending data to a center, making an emergency call, etc.).

[0027] In one example, each control model 30 may be configured to directly output a control command. In another example, each control model 30 may be configured to indirectly output a control command, and the control command may be obtained by performing arbitrary information processing (interpretation processing) on ​​the output of each control model 30. The control command may be configured to directly indicate a control amount (control instruction value, control output amount) of the moving body M, such as an accelerator control amount, a brake control amount, or a steering angle. Alternatively, the control command may be configured to indirectly indicate a control amount of the moving body M, such as a path or a state after control. In this case, the control amount of the moving body M may be obtained from the control command by performing arbitrary information processing.

[0028] (Select one or more control models) The selection of one or more control models 35 may consist of selecting one control model 35 or selecting two or more control models 35. Accordingly, the deriving of the control command 50 for the mobile body M may consist of deriving the control command 50 from the selected control model 35, or deriving the control command 50 by integrating the control commands obtained from each of the two or more selected control models 35. The integration may be performed using any calculation such as sum, average, or weighted average. This allows for the appropriate acquisition of the control command 50.

[0029] (Discard or overlap) Discarding (ignoring) may be an immediate switch from automatic control to manual control, that is, an immediate switch from control by control commands 50 derived from one or more control models 35 to control according to user intervention operations 55. On the other hand, overlapping may be a gradual switch from automatic control to manual control (user control).

[0030] (Selected model) The selection model 20 is configured to select a control model 35 that is inferred from the intervention history 60 to have a low probability of intervention occurring or that no intervention will occur. In one example, the selection rule for the selection model 20 may be adjusted so that the control model used in the past is not used as is in environments that are the same as or close to the environment in which an intervention occurred in the past (i.e., within the range of environments in which an intervention occurred in the past). Whether or not the conditions are the same or close to the past may be inferred from environmental information such as observational data obtained by the sensor S.

[0031] For example, the strategy for defining the selection rule may be to select a suitable control model while avoiding the selection model in which the intervention occurred (e.g., random, specified in a predetermined order, etc.). Simply put, the selection model 20 may be configured to select a control model other than the one used at the time, within the range of environments in which an intervention occurred in the past. Preferably, the selection model 20 may be configured to select a control model that can derive a control command identical to or near the control command for the intervention operation given by the user at that time.

[0032] Another example is that the strategy for defining the selection rule may involve arbitrarily selecting two or more control models and deriving the integration ratio of the two or more selected control models. The selected model 20 may be configured to select two or more control models within the range of environments in which interventions have occurred in the past. The two or more control models may consist of the control model used at that time and one or more other control models, or two or more other control models other than the control model used at that time. The integration ratio of the two or more control models may be calculated as appropriate to match the control command resulting from the user intervention at that time.

[0033] If the intervention history 60 can be reflected in the selection of the control model 35, the configuration of the selection model 20 may be appropriately determined according to the embodiment. In one example, the selection model 20 may consist of at least one of a rule-based model and a trained machine learning model. When a rule-based model is adopted, the information from the intervention history 60 may be directly reflected in the selection rules of the selection model 20. In one example, the selection model 20 may consist of the information from the intervention history 60 and criteria for setting the selection rules from the intervention history 60. The selection rules may be set manually or at least partially automatically. When a machine learning model is adopted, the information indicating the environment in which interventions occurred in the past, as shown by the intervention history 60, may be used as training samples (input data), and the control model (and integration ratio) selected according to the above selection rules may be used as labels (teacher signals, ground truth data) to train the selection model 20. This makes it possible to generate a trained machine learning model (selection model 20) that reflects the selection rules according to the above policy.

[0034] The multiple control models 30 may include trained machine learning models and rule-based models. Accordingly, selecting one or more control models 35 may include selecting a rule-based model under the conditions indicated by the record if the intervention history 60 contains a record (information) indicating that a user intervention occurred while the automatic control of the mobile object M was being performed using a trained machine learning model. The conditions indicated by the record may be the same as or near the environment in which the intervention occurred. The range of the vicinity may be arbitrarily defined. This allows for the use of a control model in an environment where the trained machine learning model is not suitable for the user. You can switch your model from a pre-trained machine learning model to a rule-based model.

[0035] (Intervention history) The intervention history 60 consists of information on user interventions (records of past interventions) that occurred while the automatic control of the mobile body M was being performed using at least one of the multiple control models 30 in the past. The data format of the intervention history 60 may be determined as appropriate depending on the embodiment. The intervention history 60 may be stored in any database format.

[0036] The items of information to be stored as the intervention history 60 are not particularly limited, as long as they allow for the formation of the selection model 20, and may be appropriately selected depending on the embodiment. For example, the intervention history 60 may include the environmental conditions in which the intervention occurred (location, route, etc.) and information for identifying the control model used in that environment (e.g., identifier, etc.).

[0037] Furthermore, the intervention history 60 may include information that can be used to improve the control model 30, in addition to the information used to form the selection model 20 (information for formulating rules or information for generating a dataset to be used for machine learning). For example, the intervention history 60 may further include the user's intervention operation or the control command resulting from that operation. If the control model 30 is composed of a machine learning model, machine learning (retraining, additional training, etc.) for updating the control model 30 may be performed using the information indicating the environmental conditions in which the intervention occurred, included in the intervention history 60, as training samples, and the user's intervention operation or the control command resulting from that operation as labels. The machine learning for updating may be performed on the control device 1 or on a computer other than the control device 1 (e.g., an external server).

[0038] Figure 2 schematically shows an example of the data structure of the intervention history 60 according to this embodiment. In the example in Figure 2, the records of the intervention history 60 include a timestamp, identification information of the control model used (used model), the environmental conditions in which the intervention occurred, and information indicating the operation of the intervention. The timestamp indicates the date and time the intervention occurred. The date and time indicated by the timestamp may be used for deleting old records, identifying records to be reflected in the selection model 20 (when reflecting intervention history within a certain period in the selection model), etc. Note that records of the intervention history 60 may be generated for each intervention operation. The unit of intervention operation indicated by the record may be arbitrarily determined. In one example, one record (sample of intervention history) may be generated for each intervention operation. In another example, one record may be generated for multiple interventions.

[0039] (User) The term "user" may refer to a specific user or an unspecified user. In one example, while the target user is using the control device 1, only the intervention history 60 of the target user may be reflected in the selection rules of the control model 35. In another example, the intervention history 60 of any user, including users other than the target user, may be reflected in the selection rules of the control model 35. If the mobile object M is a vehicle, typically the user is the driver.

[0040] [2 Example Configurations] Figure 3 schematically shows an example of the hardware configuration of the control device 1 according to this embodiment. The control device 1 according to this embodiment is a computer in which a control unit 11, a storage unit 12, an external interface 13, an input device 14, an output device 15, and a drive 16 are electrically connected.

[0041] The control unit 11 includes a CPU (Central Processing Unit) and RAM (Random Access Memory). The memory unit 12 includes, for example, a hard disk drive, a solid-state drive, etc., and is configured to perform arbitrary information processing based on the program and various data. The control unit 11 (CPU) is an example of a processor resource. The memory unit 12 may be composed of, for example, a hard disk drive, a solid-state drive, etc. The memory unit 12 (and RAM, ROM) is a memory resource. This is one example. In this embodiment, the storage unit 12 stores various information such as the control program 81, control model data 300, selected model data 200, and intervention history data 600.

[0042] The control program 81 is a program that causes the control device 1 to perform information processing related to the control of the mobile body M (Figure 4, described later). The control program 81 includes a series of instructions for said information processing. The control model data 300 is configured to show information related to the control model 30. The selection model data 200 is configured to show information related to the selection model 20. In one example, at least one of the control model data 300 and the selection model data 200 may include information showing the values ​​of calculation parameters adjusted by machine learning. At least one of the control model data 300 and the selection model data 200 may further include information showing the configuration of the machine learning model (e.g., the structure of a neural network). In another example, at least one of the control model data 300 and the selection model data 200 may include information showing a rule-based model (rules). The intervention history data 600 may be configured as appropriate to include information showing the intervention history 60.

[0043] The external interface 13 may be, for example, a USB (Universal Serial Bus) port, a dedicated port, a wireless communication port, etc., and is configured to connect to an external device by wire or wireless connection. In this embodiment, the control device 1 may be connected to the sensor S via the external interface 13. The input device 14 is, for example, a device for input such as a mouse or keyboard. The output device 15 is, for example, a device for output such as a display or speaker. The input device 14 and the output device 15 may be integrally configured by, for example, a touch panel display.

[0044] Drive 16 is a device for reading various information, such as programs, stored in the storage medium 91. At least one of the control program 81, control model data 300, selection model data 200, and intervention history data 600 may be stored in the storage medium 91 in place of or together with the storage unit 12. The storage medium 91 is configured to store various information (stored programs, etc.) by electrical, magnetic, optical, mechanical, or chemical means so that a machine such as a computer can read the information. The control device 1 may acquire at least one of the control program 81, control model data 300, selection model data 200, and intervention history data 600 from the storage medium 91. The storage medium 91 may be a disk-type storage medium such as a CD or DVD, or a non-disk-type storage medium such as semiconductor memory (e.g., flash memory). The type of drive 16 may be appropriately selected according to the type of storage medium 91.

[0045] Regarding the specific hardware configuration of the control device 1, components can be omitted, replaced, and added as appropriate depending on the embodiment. For example, the control unit 11 may include multiple hardware processors. Hardware processors include microprocessors, FPGAs (field-programmable gate arrays), DSPs (digital signal processors), and ECUs. It consists of components such as an Electronic Control Unit (ECC) and a Graphics Processing Unit (GPU). At least one of the external interface 13, input device 14, output device 15, and drive 16 may be omitted. The control device 1 may be a computer designed specifically for the services provided, a general-purpose computer, a terminal device, etc.

[0046] [3 Examples of operation] Figure 4 shows an example of a processing procedure for controlling the mobile body M by the control device 1 according to this embodiment. The following processing procedure is an example of a control method executed by a computer. However, the following processing procedure is merely an example, and each step may be modified as much as possible. Furthermore, depending on the embodiment, steps in the following processing procedure can be omitted, replaced, and added as appropriate.

[0047] In step S101, the control unit 11 operates as an acquisition unit 111 and acquires observation data 125 from the sensor S. The control unit 11 may acquire the observation data 125 directly or indirectly from the sensor S. In step S102, the control unit 11 operates as a selection unit 112 and selects one or more control models 35 from a plurality of control models 30 using a selection model 20. In one example, if the selection model 20 includes a rule-based model, the control unit 11 may derive the selection result of the control model 35 from the environment indicated by at least a portion of the observation data 125 according to the rules. In another example, if the selection model 20 includes a trained machine learning model, the control unit 11 may input at least a portion of the observation data 125 into the trained machine learning model and obtain the selection result of the control model 35 by executing the calculations of the trained machine learning model. In step S103, the control unit 11 acts as a derivation unit 113 and derives control commands 50 for the mobile body M from at least a portion of the acquired observation data 125 using one or more selected control models 35. Similar to the selected model 20, in one example, if the control model 35 includes a rule-based model, the control unit 11 may derive the control commands 50 according to the rules. In another example, if the control model 35 includes a trained machine learning model, the control unit 11 may derive the control commands 50 by performing calculations on the trained machine learning model.

[0048] In step S102, the control unit 11 may select one control model 35 or two or more control models 35. Accordingly, in step S103, the control unit 11 may derive a control command 50 from the selected control model 35. Alternatively, the control unit 11 may derive a control command 50 by integrating the control commands obtained from each of the two or more selected control models 35. Furthermore, the order of steps S102 and S103 is not limited to this example. In another example, step S103 may be executed before step S102. In this case, the control unit 11 may derive control commands from all control models 30 that may be selected, regardless of whether they are selected or not. The control unit 11 may then extract the control command of the control model 35 selected in step S102 from the derived control commands.

[0049] In step S104, the control unit 11 operates as an intervention reception unit 114 and determines whether or not there is an intervention operation 55 by the user. The control unit 11 may accept an intervention operation 55 by the user at any time while controlling the movement of the mobile body M. If an intervention operation 55 is accepted (i.e., there is an intervention operation 55), the control unit 11 proceeds to step S106. On the other hand, if no intervention operation 55 is accepted (there is no intervention operation 55), the control unit 11 proceeds to step S105.

[0050] In step S105, the control unit 11 operates as an motion control unit 116 and controls the movement of the mobile body M according to the derived control command 50. Once the motion control is complete, the control unit 11 proceeds to the next step S108.

[0051] In step S106, the control unit 11 operates as an operation control unit 116 and controls the movement of the mobile body M according to the user's intervention operation 55, either by discarding the derived control command 50 or by overlapping the derived control command 50. In step S107, the control unit 11 operates as a history generation unit 115 and generates information indicating the user's intervention operation 55, and saves the generated information as intervention history 60 in a predetermined storage area. The predetermined storage area (storage location) may be arbitrarily selected. In one example, the predetermined storage area may be RAM, storage unit 12, storage medium 91, etc. If the control device 1 is configured to communicate, the predetermined storage area may be an external computer. Note that the processing timing of step S107 is not limited to this example and may be changed as appropriate. Once the recording of the intervention history 60 (updating of intervention history data 600) is completed, the control unit 11 proceeds to the next step S108.

[0052] In step S108, the control unit 11 determines whether or not to terminate control of the mobile body M. The criteria for this determination can be set arbitrarily. For example, while the mobile body M is running, the control unit 11 may determine not to terminate control of the mobile body M, whereas it may determine to terminate control of the mobile body M in response to an arbitrary termination instruction (for example, a termination operation by the user via the input device 14). If it determines not to terminate control, the control unit 11 returns to step S101 and executes the process again from step S101. On the other hand, if it determines to terminate control, the control unit 11 proceeds to step S109.

[0053] In step S109, the control unit 11 operates as a model update unit 117 and updates the selected model 20 with the generated intervention history 60. In one example, the control unit 11 may update the selected model 20 according to the above-described strategy. As a result, the selected model 20 is configured to select one or more control models 35 from the user's intervention history 60 to avoid the occurrence of user interventions. In the example shown in Figure 4, step S109 is executed each time control ends and the selected model 20 is updated. However, the processing timing of step S109 is not limited to this example and may be determined as appropriate depending on the embodiment. In another example, the control unit 11 may update the selected model 20 by executing step S109 at regular intervals (for example, every month). Once the update of the selected model 20 is complete, the control unit 11 terminates the processing procedure of the control device 1 according to this example of operation.

[0054] [Features] In this embodiment, through the processing in steps S107 and S109, the selected model 20 is configured to select a control model 35 that avoids user interventions based on records of past user interventions. By using this selected model 20 in step S102, the control device 1 can be instructed to avoid using control models from among the multiple control models 30 that are presumed to be unsuitable for the user in the target situation based on past intervention trends, and to actively use control models that are more likely to be suitable for the user. As a result, according to this embodiment, a reduction in the frequency of user interventions can be expected.

[0055] [4. Variant] While embodiments of this disclosure have been described in detail above, the above description is merely illustrative in all respects of this disclosure. Needless to say, various improvements or modifications can be made without departing from the scope of this disclosure. The processes and means described in this disclosure can be freely combined and implemented as long as no technical inconsistencies arise. [Explanation of symbols]

[0056] 1...Control device, 11...Control unit, 12...Storage unit, 20...Selection model, 30-35...Control model, 50...Control command, 55...Operation, 60...Intervention history M...Mobile object, S...Sensor

Claims

1. A storage unit for storing multiple control models and selection models, and Control unit, A control device comprising, Each of the aforementioned control models is configured to derive control commands in order to automatically control the movement of a moving object. The control unit, The selection model involves selecting one or more control models from the plurality of control models. Using one or more selected control models, derive control commands for the moving body. In the absence of user intervention, the operation of the mobile body is controlled according to the derived control commands, and If the user intervenes, the derived control command is discarded or overlapped with the derived control command to control the movement of the mobile body in accordance with the user's intervention. It is configured to perform, The selection model is configured to select one or more control models from the user's intervention history to avoid the occurrence of interventions by the user. The aforementioned multiple control models include trained machine learning models and rule-based models, The selection of one or more control models includes, if the intervention history includes a record indicating that user intervention occurred while the automated control of the mobile object was being performed using the trained machine learning model, selecting the rule-based model under the conditions indicated by the record. Control device.

2. Selecting one or more control models means Selecting one control model, or Selecting two or more control models, It is composed of and To derive the control command for the aforementioned moving body, Obtaining the control command from the aforementioned one control model, or The control commands are derived by integrating the control commands obtained from each of the two or more control models. Composed of, The control device according to claim 1.

3. The aforementioned moving object is a vehicle. The control device according to claim 1 or 2.

Images