Mobile body control system, control method thereof, and program

Abstract

To achieve a cooperation behavior of a mobile body without requiring an agreement via communication.SOLUTION: A mobile body control system determines a behavior of a mobile body in order to pass a specified area on a movement route. The mobile body control system includes: acquisition means for acquiring a movement state of the mobile body and a movement state of a cooperation partner; calculation means for calculating a cooperation degree indicating the degree for enabling the mobile body to pass the specified area by cooperation with the cooperation partner based on the movement state of the mobile body and the movement state of the cooperation partner; and determination means for determining the behavior of the mobile body to the specified area so as to increase the cooperation degree. The cooperation degree is increased when a movement state is obtained, where one of the mobile body and the cooperation partner enters the specified area after the other one leaves the specified area.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to a mobile object control system, a control method therefor, and a program. [Background technology]

[0002] Conventionally, the intelligent driver model (IDM) has been known as a model for predicting the behavior of moving objects. Compared to rule-based models that assume uniform motion of moving objects, this model can handle nonlinear driving speeds and therefore can predict behavior that is closer to reality. However, IDM is intended for use when driving on expressways, and other moving objects in the model are assumed to follow a set target speed. In other words, while IDM can consider the relationship between a moving object and other moving objects if they are traveling in the same lane, it cannot consider the cooperative behavior of other moving objects moving in a different direction from the moving object.

[0003] A system that enables cooperative operation among multiple mobile objects has been proposed (Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] U.S. Patent No. 10,139,828 Summary of the Invention [Problem to be solved by the invention]

[0005] In the system disclosed in Patent Document 1, cooperative actions are realized by communication between mobile objects. It is true that complex cooperative actions can be realized by mutually agreeing on actions via communication. However, communication can take time, and there may be cases where cooperative actions need to be performed in an extremely short time. In other words, there is a need for technology that allows multiple mobile objects to proceed with cooperative actions without mutual agreement via communication.

[0006] The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to realize cooperative behavior of mobile entities without requiring agreement via communication. [Means for solving the problem]

[0007] In the present invention, A mobile object control system that determines the behavior of a mobile object to pass through a specific area on a movement path, acquisition means for acquiring a movement status of the moving body and a movement status of a cooperative partner; a calculation means for calculating a degree of cooperation that indicates a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on a movement status of the moving body and a movement status of the cooperative partner; a decision means for deciding an action of the moving object in the specific area so as to increase the degree of cooperation; The degree of cooperation increases as the movement situation changes such that one of the moving body and the cooperative partner exits the specific area and the other enters the specific area. [Effects of the Invention]

[0008] According to the present invention, cooperative behavior of mobile entities can be realized without the need for agreement via communication. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a vehicle as an example of a moving body according to an embodiment; [Figure 2] FIG. 1 is a block diagram illustrating an example of a functional configuration of a control device according to an embodiment. [Figure 3] FIG. 1 is a block diagram showing an example of the functional configuration of a cooperative action decision unit according to an embodiment; [Figure 4] FIG. 1 is a diagram illustrating an example of cooperative behavior according to an embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of calculating an agreement degree as an example of a cooperation degree according to an embodiment; [Figure 6] FIG. 10 is a diagram illustrating an example of calculating the cost of a first passing mode according to an embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of calculating the cost of a second passing mode according to an embodiment. [Figure 8] 1 is a flowchart showing a series of operations of a driving assistance process according to an embodiment; DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Furthermore, the same reference numerals are used for the same or similar components, and redundant explanations will be omitted.

[0011] <Vehicle configuration example> FIG. 1 is a block diagram of a vehicle 1 as an example of a mobile body according to the present invention. In FIG. 1, the vehicle 1 is generally shown in plan view and side view. The vehicle 1 is a four-wheeled passenger car as an example, but may also be a two-wheeled vehicle or other types of vehicle. The mobile body control system according to this embodiment may be a mobile body, a control device such as an ECU included in the mobile body, or an information processing server on the cloud for controlling the mobile body. That is, part or all of the driving assistance processing according to this embodiment, which will be described later, may be executed in the mobile body or in an information processing server on the cloud. The mobile body is not limited to a vehicle, but may include various mobile bodies such as robots capable of autonomous driving.

[0012] The vehicle 1 includes a vehicle control device (hereinafter simply referred to as the control device 2) that controls the vehicle 1. The control device 2 includes multiple ECUs (Electronic Control Units) 20 to 29 that are communicatively connected via an in-vehicle network. Each ECU includes a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), a memory such as a semiconductor memory, an interface with external devices, etc. The memory stores programs executed by the processor and data used by the processor for processing, etc. Each ECU may include multiple processors, memories, interfaces, etc. For example, the ECU 20 includes a processor 20a and a memory 20b. The processor 20a executes instructions included in a program stored in the memory 20b, thereby performing processing by the ECU 20. Alternatively, the ECU 20 may include a dedicated integrated circuit such as an ASIC (Application Specific Integrated Circuit) for performing processing by the ECU 20. The same applies to the other ECUs.

[0013] The functions and the like that are handled by each of the ECUs 20 to 29 will be described below. The number of ECUs and the functions that they are responsible for can be designed as appropriate, and they can be subdivided or integrated more than in this embodiment. For example, one ECU (e.g., ECU 22) may also have the functions of other ECUs.

[0014] The ECU 20 executes control related to manual driving and automatic driving of the vehicle 1. In automatic driving, at least one of steering and acceleration / deceleration of the vehicle 1 is automatically controlled. Note that the automatic driving by the ECU 20 may include automatic driving that does not require driving operation by the driver (also called automatic driving) and automatic driving that assists driving operation by the driver (also called driving assistance). The control of driving by the ECU 20 may include, for example, control to automatically stop or steer the vehicle to avoid a collision in place of driving by the driver.

[0015] The ECU 21 controls the electric power steering device 3. The electric power steering device 3 includes a mechanism for steering the front wheels in response to a driver's driving operation (steering operation) on the steering wheel 31. The electric power steering device 3 also includes a motor that generates driving force to assist the steering operation and automatically steer the front wheels, a sensor that detects the steering angle, etc. When the driving state of the vehicle 1 is autonomous driving, the ECU 21 automatically controls the electric power steering device 3 in response to instructions from the ECU 20, and controls the traveling direction of the vehicle 1.

[0016] The ECUs 22 and 23 control the detection units that detect the vehicle's surroundings and process information on the detection results. The vehicle 1 includes, for example, one standard camera 40 and four fisheye cameras 41 to 44 as detection units that detect the vehicle's surroundings. The standard camera 40 and the fisheye cameras 42 and 44 are connected to the ECU 22. The fisheye cameras 41 and 43 are connected to the ECU 23. By analyzing images captured by the standard camera 40 and the fisheye cameras 41 to 44, the ECUs 22 and 23 can recognize the status of targets, such as their type, position, and speed, as well as lane boundaries on the travel path, lane boundaries (white lines), and dividing lines (broken lines, etc.) between lanes. Note that the type, number, and mounting positions of the cameras in the vehicle 1 are not limited to the example in this embodiment and may be other configurations. Furthermore, the vehicle 1 may include a lidar (light detection and ranging) or millimeter-wave radar as a detection unit for detecting targets around the vehicle 1 and measuring the distance to the targets.

[0017] The standard camera 40 is attached to the center of the front of the vehicle 1 and captures the surroundings in front of the vehicle 1. The fisheye camera 41 is attached to the center of the front of the vehicle 1 and captures the surroundings in front of the vehicle 1. In FIG. 1, the standard camera 40 and the fisheye camera 41 are shown aligned horizontally. However, the arrangement of the standard camera 40 and the fisheye camera 41 is not limited to this; for example, they may be aligned vertically. Furthermore, at least one of the standard camera 40 and the fisheye camera 41 may be attached to the front of the roof of the vehicle 1 (for example, on the inside of the front windshield). The fisheye camera 42 is attached to the center of the right side of the vehicle 1 and captures the surroundings to the right of the vehicle 1. The fisheye camera 43 is attached to the center of the rear of the vehicle 1 and captures the surroundings behind the vehicle 1. The fisheye camera 44 is attached to the center of the left side of the vehicle 1 and captures the surroundings to the left of the vehicle 1.

[0018] The ECU 22 controls the standard camera 40 and the fisheye cameras 42 and 44 and processes information on the detection results. The ECU 23 controls the fisheye cameras 41 and 43 and processes information on the detection results. By dividing the detection unit that detects the vehicle's surroundings into two systems, the reliability of the detection results can be improved. In addition, the ECU 22 can detect the driver's head direction and line of sight using an image of the driver captured by a fisheye camera (not shown) installed inside the vehicle cabin.

[0019] The ECU 24 controls the gyro sensor 5, the GPS sensor 24b, and the communication device 24c, and processes information on the detection results or communication results. The gyro sensor 5 detects the rotational motion of the vehicle 1. The path and moving speed of the vehicle 1 can be determined based on the detection results of the gyro sensor 5, the wheel speed, etc. The GPS sensor 24b detects the current position of the vehicle 1. The communication device 24c wirelessly communicates with a server that provides map information and traffic information to acquire this information. The communication device 24c may also acquire position information and moving speed information of other moving objects from an external device. The ECU 24 can access a database 24a of map information stored in memory, and the ECU 24 performs tasks such as searching for a route from the current location to a destination. The ECU 24, the map database 24a, and the GPS sensor 24b constitute a so-called navigation device.

[0020] The ECU 25 includes a communication device 25a for vehicle-to-vehicle communication. The communication device 25a performs, for example, wireless communication with other vehicles in the vicinity, and exchanges information between the vehicles.

[0021] The ECU 26 controls the power plant 6. The power plant 6 is a mechanism that outputs driving force to rotate the drive wheels of the vehicle 1, and includes, for example, an engine and a transmission. The ECU 26 controls the output of the engine in response to a driving operation (accelerator operation or acceleration operation) by the driver detected by an operation detection sensor 7a provided on the accelerator pedal 7A, for example, and switches the gear position of the transmission based on information such as the vehicle speed detected by a vehicle speed sensor 7c.

[0022] The ECU 27 controls lighting devices (such as headlights, taillights, etc.) including the direction indicator 8 (flasher). In the example of FIG. 1, the direction indicator 8 is provided at the front, door mirrors, and rear of the vehicle 1.

[0023] The ECU 28 controls the input / output device 9. The input / output device 9 outputs information to the passengers (e.g., the driver) and receives the input of information from the driver. The voice output device 91 notifies the driver of information by voice including, for example, a predetermined sound or utterance. The notification content is output, for example, by the ECU 22 performing the driving support process described later, determining the execution of the notification, and transmitting it to the ECU 28. The driving support process will be described later. The display device 92 notifies the driver of information by displaying an image. The display device 92 is arranged, for example, on the surface of the driver's seat and constitutes an instrument panel or the like. Here, voice and display are exemplified, but information may also be notified by vibration or light. Further, information may be notified by combining a plurality of voice, display, vibration, or light. The input device 93 is arranged at a position where the driver can operate and is a group of switches for giving instructions to the vehicle 1, and may also include a voice input device.

[0024] The ECU 29 controls the brake device 10 and the parking brake (not shown). The brake device 10 is, for example, a disc brake device, which is provided on each wheel of the vehicle 1 and decelerates or stops the vehicle 1 by applying resistance to the rotation of the wheels. The ECU 29 controls the operation of the brake device 10 corresponding to the driving operation (brake operation) of the driver detected by the operation detection sensor 7b provided on the brake pedal 7B, for example. When the driving state of the vehicle 1 is in autonomous driving, the ECU 29 automatically controls the brake device 10 corresponding to the instruction from the ECU 20 and controls the deceleration and stop of the vehicle 1. The brake device 10 and the parking brake can also operate to maintain the stopped state of the vehicle 1. Further, when the transmission of the power plant 6 has a parking lock mechanism, this can also operate to maintain the stopped state of the vehicle 1.

[0025] <Example of functional configuration realized in ECU 22> Next, an example of a functional configuration implemented in the ECU 22 will be described with reference to FIG. 2. Note that some or all of the functions described below as being implemented in the ECU 22 may be implemented in another ECU (e.g., ECU 20). The example of the functional configuration shown in FIG. 2 illustrates an example of a functional configuration implemented by the ECU 22 executing a program stored in an internal memory. The example of the functional configuration shown in FIG. 2 focuses on a configuration related to a driving assistance process, which will be described later. Therefore, the functions implemented in the ECU 22 are not limited to those shown in FIG. 2 and may include other functions.

[0026] The target recognition unit 201 recognizes the state of targets in the external world of the vehicle 1 based on at least one of images obtained from the detection unit and sensor information from a lidar or the like. Targets include, for example, moving objects around the vehicle 1 (surrounding vehicles, bicycles), passersby such as pedestrians and cyclists, or fallen objects. Surrounding vehicles include other vehicles on the lane in which the vehicle 1 is traveling, other vehicles traveling in an oncoming lane to the lane in which the vehicle 1 is traveling, or other vehicles traveling in a lane intersecting the lane in which the vehicle 1 is traveling. The state of the target includes, for example, the type of the target, the position of the target, the moving speed of the target, the moving trajectory of the target, etc. The position of the target may be a relative position from the vehicle 1. The target recognition unit 201 can recognize the state of targets in the external world using, for example, one or more neural networks, but other learning models may also be used.

[0027] The movement status acquisition unit 202 acquires the movement status of the vehicle 1. The movement status acquisition unit 202 acquires the current position and movement speed as the movement status of the vehicle 1, for example, from the GPS sensor 24b or the like, for example, via the ECU 24. The movement status acquisition unit 202 also acquires the movement status of moving objects around the vehicle 1. The movement status acquisition unit 202 can acquire the current position and movement speed of the moving object as the movement status of the moving object around the vehicle 1 from at least one of the target recognition unit 201 and the communication unit 24c.

[0028] The cooperative behavior determination unit 203 determines the behavior of the vehicle 1 in order to perform cooperative behavior with other moving objects, which will be described later. As shown in FIG. 3, the cooperative behavior determination unit 203 includes an area identification unit 301, a degree calculation unit 302, and a behavior determination unit 303.

[0029] The area identification unit 301 identifies a common area 406, which will be described below, based on at least one of an image obtained from the detection unit and sensor information such as a LIDAR. For example, the area identification unit 301 can identify a passable common area 406 based on the recognized road shape and landmarks on the road. In this case, it is possible to grasp a common area without using a high-precision map and taking into account movable obstacles such as parked vehicles. The area identification unit 301 may identify the common area using information such as road shape and passable lanes included in pre-acquired map data, or by using such information in addition to sensor information. In this case, it is possible to identify the area using accurate data.

[0030] FIG. 4 shows an example in which vehicle 1 behaves cooperatively with other moving objects. In the example shown in FIG. 4, vehicle 401 (i.e., vehicle 1), which is the target of control, and vehicle 402 pass through a specific area (referred to as a common area 406) on road 403 through cooperative behavior. The width of common area 406 is limited by, for example, vehicles 404 and 405 parked on road 403. That is, vehicle 401 and its cooperative partner vehicle 402 can each pass through common area 406, but vehicle 401 and vehicle 402 cannot pass through common area 406 at the same time. For this reason, vehicle 401 and vehicle 402 must behave cooperatively, and one of vehicle 401 and vehicle 402, which entered first, must exit common area 406 before the other vehicle can enter common area 406.

[0031] In this embodiment, an example is described in which vehicle 401 realizes cooperative behavior in which vehicle 401 passes through a common area 406 in cooperation with vehicle 402 based on the movement status of vehicle 401 and the movement status of its cooperative partner vehicle 402, without communicating an agreement on behavior between vehicle 401 and vehicle 402.

[0032] The degree calculation unit 302 calculates a degree of agreement as an example of a degree of cooperation for determining cooperative behavior. The degree of cooperation increases, for example, as the movement situation progresses in which one of the vehicle 401 and the cooperative partner (vehicle 402) exits the common area 406 and the other enters the common area 406. The degree of agreement will be described later. The degree calculation unit 302 then calculates costs for two passing modes: one in which the vehicle 402 yields to the vehicle 401 to pass through the common area 406, and one in which the vehicle 402 does not yield to the vehicle 401 to pass through the common area 406. The vehicle 401 compares the costs for the two passing modes and selects the passing mode with the lowest cost. The vehicle 401 calculates a coefficient based on the degree of cooperation based on the above-mentioned degree of cooperation and multiplies the calculated cost by the coefficient. In this way, the degree of cooperation functions in cost calculation such that the lower the degree of cooperation, the higher the cost. In this way, by combining the degree of cooperation with the selection of the cost, the vehicle 401 can change the movement state of the vehicle 401 into the common area so that the degree of cooperation increases.

[0033] A method for calculating the degree of agreement as an example of the degree of cooperation will be specifically described with reference to FIG. 5. The degree calculation unit 302 can calculate the predicted asymmetry for all traffic participants that may pass through the common area according to equations (1) to (5) described below. The degree calculation unit 302 may identify the traffic participant with the smallest predicted asymmetry as the cooperation partner. In this case, the traffic participant that is most likely to compete in the common area can be identified as the cooperation partner. In the following description, the traffic participant to be processed is also referred to as an agent. In the following description, the case where the traffic participant to be processed is a vehicle 402 will be described as an example. The degree calculation unit 302 calculates the degree of agreement for all traffic participants that may pass through the common area according to equations (1) to (5) described below. The degree calculation unit 302 calculates the predicted asymmetry for all traffic participants that may pass through the common area according to the TTE agent and TTL agent is calculated according to the following formulas (1) and (2) (501). TTE is the Time to Entry, and TTE agentindicates the time it takes for the vehicle 402 to arrive at the start position of the common area 406. TTL is the Time to Leave, and TTL agent indicates the time until the vehicle 402 exits the end position of the common area 406.

[0034]

number

[0035]

number

[0036] Next, the degree calculation unit 302 calculates the asymmetry agent is calculated according to formula (3) (502). ego indicates the time it takes for the vehicle 401 to arrive at the start position of the common area 406. agent represents the asymmetry of arrival times for the common area 406. This value can also be considered to represent the time difference (with a sign) between the arrival times of the vehicles 401 and 402 at the starting positions.

[0037]

number

[0038] The degree calculation unit 302 calculates the Required_Asymmetry agent is calculated according to equation (4) (503).

[0039]

number

[0040] Required_Asymmetry agentindicates the asymmetry required to prevent the two vehicles from meeting within the common area 406 when passing through the common area 406. This value can also be interpreted as representing the time required for a vehicle that arrives at the common area 406 first to pass through the common area 406. The upper part of equation (4) corresponds to the case where vehicle 401 arrives at the common area 406 first, and the lower part corresponds to the case where vehicle 402 arrives at the common area 406 first.

[0041] The degree calculation unit 302 calculates the Predicted_Asymmetry agent is calculated according to equation (5) (504).

[0042]

number

[0043] Predicted_Asymmetry agent represents the predicted asymmetry. ΔAsymmetry represents the change in asymmetry during one step (e.g., 100 ms) of the most recent processing. Therefore, using equation (5), it is possible to calculate the predicted asymmetry in the future development until the vehicle 401 or 402 arrives at the common area 406. Predicted_Asymmetry agent can also be considered to represent the predicted time difference (with a sign) until the vehicle 401 and the vehicle 402 arrive at their respective starting positions.

[0044] The degree calculation unit 302 calculates the degree of agreement. agent is calculated according to equation (6) (505).

[0045]

number

[0046] The agreement is expressed as the ratio of the asymmetry required to prevent the vehicles from meeting in the common area 406 to the predicted asymmetry. This allows the agreement between vehicle 401 and vehicle 402 to be quantified. The greater the predicted asymmetry is compared to the asymmetry required to prevent the vehicles from meeting in the common area, the higher the agreement. In other words, the greater the time difference between the arrival of vehicle 401 and vehicle 402 at the start position compared to the time required for the first-arriving vehicle to pass through the common area 406, the higher the agreement, making it easier to achieve the cooperative behavior of the vehicles shown in FIG. 4. For example, if one vehicle slows down before the common area 406 to allow the other vehicle to pass, the time difference between the arrival of vehicle 401 and vehicle 402 at the start position increases, resulting in a higher agreement. In other words, if the behavior of vehicle 401 is determined so that the absolute value of the agreement in Equation 6 is large, cooperative behavior in the common area can be achieved. For example, if the degree of cooperation in this embodiment is the absolute value of the degree of agreement, the greater the time difference between vehicle 401 and vehicle 402 arriving at the starting position compared to the time required for the vehicle that arrived earlier to pass through common area 406, the greater the degree of cooperation.

[0047] In this embodiment, an example using the agreement degree is described, but the present invention is not limited to this example. The degree of cooperation can be calculated based on the movement situation, and other calculation methods can be used as long as the degree of cooperation increases as the movement situation changes such that one of the vehicle 401 and the cooperation partner enters the common area after the other one leaves the common area.

[0048] The behavior decision unit 303 decides cooperative behavior using the predicted costs of when the cooperative partner (vehicle 402) does not yield and when it yields to pass through the common area 406. An example of a method for deciding behavior by the behavior decision unit 303 will be described with reference to FIGS. 6 and 7.

[0049] 6 shows a schematic example of cost calculation in the first passing manner (also referred to as the first passing mode) where another vehicle (vehicle 402) does not yield to pass through the common area 406. In the first passing mode, the cooperative vehicle 402 passes through the common area, and the controlled vehicle 401 decelerates just before the common area 406 to allow the cooperative vehicle 402 to pass first. The cost in the first passing mode can be calculated according to equation (7).

[0050]

number

[0051] Here, Cost C1 (602) indicates the cost of changing the current movement status (position, speed) of vehicle 402 to a movement status in which the vehicle passes through the common area (first) without yielding to the other vehicle. The cost can be calculated, for example, based on a comfort index when the vehicle behaves in such a way that the current movement status is changed to a new movement status. The comfort index for a change in movement status can be determined in advance through experiments, etc. Use of the comfort index enables behavior selection that takes into account the passenger comfort. For example, if, under the current movement status, vehicle 402 is scheduled to arrive at the common area 406 earlier than vehicle 401, vehicle 402 will pass through the common area 406 first, so the current movement status does not need to change significantly. In other words, the cost in this case is small. On the other hand, if, under the current movement status, vehicle 402 is scheduled to arrive at the common area 406 significantly later than vehicle 401, the cost will be large. This is because, in order for vehicle 402 to pass through the common area 406 first, it is necessary to significantly change the current movement state (for example, increase the speed by sudden acceleration, etc.). Furthermore, Cost C3 (601) indicates the cost for changing the current movement state (position, speed) of vehicle 401 to a movement state that allows vehicle 402 to pass through the common area. For example, if, in the current movement state, vehicle 401 is scheduled to arrive at the common area 406 earlier than vehicle 402 is scheduled to arrive at the common area 406, the cost becomes large. This is because, in order for vehicle 402 to pass through the common area 406 first, vehicle 401 is required to significantly change the current movement state, for example, by significantly decelerating. In this way, the behavior decision unit 303 adds Cost C3 and Cost C1 to calculate the cost in the first passing mode (Mode 1 Cost).

[0052] 7 shows a schematic example of a cost calculation in the second passing mode (also referred to as the second passing mode) in which another vehicle (vehicle 402) gives way to pass through the common area 406. In the second passing mode, the vehicle 401 to be controlled passes through the common area, and the vehicle 402 to be coordinated decelerates just before entering the common area 406. The cost in the first passing mode can be calculated according to equation (8).

[0053]

number

[0054] Here, Cost C2 (603) indicates the cost of changing the current movement status (position, speed) of the vehicle 402 to a movement status that allows the other vehicle to pass through the common area. As in the first passing mode, this cost can be calculated, for example, based on a comfort index when the vehicle behaves in such a way that the current movement status changes to a post-change movement status. Furthermore, Cost C4 (604) indicates the cost of changing the current movement status (position, speed) of the vehicle 402 to a movement status that allows the other vehicle to pass through the common area (first) without yielding. The behavior decision unit 303 adds Cost C2 and Cost C4 to calculate the cost in the second passing mode (Mode 2 Cost).

[0055] In the first processing step, the behavior decision unit 303 compares the cost of the first passing mode (Mode 1 Cost) with the cost of the second passing mode (Mode 2 Cost) to select the passing mode with the lower cost. The behavior decision unit 303 decides the behavior of the vehicle 401 so that the passing mode with the lower cost is selected, and the traveling control unit 204 controls the traveling of the vehicle so that the vehicle travels in accordance with the determined behavior.

[0056] Once the behavior of vehicle 401 has been controlled, subsequent processing steps include repeating calculation of the degree of agreement (degree of cooperation), calculation of the cost of each passing mode, selection of the passing mode, and control of driving to achieve the selected passing mode.

[0057] Here, we will explain the steps after the passing mode is selected and control is performed in the first processing step. At this time, the degree calculation unit 302 calculates the agreement degree (or cooperation degree) after control according to the above-mentioned equations (1) to (6).

[0058] The behavior decision unit 303 calculates the cost of each passing mode in the current movement situation according to equations (7) and (8). Furthermore, for the passing mode selected in the previous step, the behavior decision unit 303 calculates the cost of the passing mode taking into account the degree of agreement according to equation (9) or equation (10). For example, if the first passing mode was selected in the previous step, the behavior decision unit 303 calculates the cost of the first passing mode according to equation (9).

[0059] At this time, the behavior determination unit 303 multiplies the cost by a coefficient (Agreement_factor) based on the degree of agreement. As described above, the coefficient based on the degree of agreement functions in calculating the cost such that the cost increases as the degree of agreement (degree of cooperation) decreases. The coefficient can be calculated by various calculations based on the degree of agreement, as long as it functions such that the cost increases as the degree of agreement decreases. The coefficient may be, for example, the reciprocal of the degree of agreement. Alternatively, the coefficient may be calculated by inputting a value based on the degree of agreement into a sigmoid function whose characteristics are appropriately set to output a value within a predetermined binary range. As an example of the value based on the degree of agreement, a value obtained by multiplying the degree of agreement by -1 may be used. By using a differentiable function such as a sigmoid function, frequent switching between the first passing mode and the second passing mode can be suppressed under conditions where the degree of cooperation is low.

[0060]

number

[0061]

number

[0062] The behavior decision unit 303 compares the calculated costs of the passing modes and selects the passing mode with the lower cost. For example, the behavior decision unit 303 compares the cost of the second passing mode calculated using equation (8) with the cost of the first passing mode calculated using equation (9) and selects the passing mode with the lower cost (thereby determining the behavior of vehicle 1). In this way, the behavior decision unit 303 can change the movement status of vehicle 401 into the shared area so as to increase the degree of cooperation. Then, when the movement status of vehicle 401 changes (by control of the driving control unit 204), the degree calculation unit 302 again calculates a new degree of cooperation based on the changed movement status of vehicle 401. As a result, the behavior (passing mode) is determined based on the degree of cooperation again. By repeating such operations, vehicle 401 can control cooperative behavior with vehicle 402 while observing the behavior of the cooperative partner.

[0063] Referring again to FIG. 2 , the driving control unit 204 generates a driving trajectory for the vehicle 401 based on the behavior determined by the cooperative behavior determination unit 203. Then, the driving control unit 204 controls the driving of the vehicle 401 based on the generated driving trajectory. For example, when the vehicle 401 is driving in the second passing mode, the driving control unit 204 generates the driving trajectory for the vehicle 401 shown in FIG. 7. Alternatively, when the vehicle 401 is driving in the first passing mode, the driving control unit 204 may generate the driving trajectory shown in FIG. 6 and decelerate the vehicle 401. That is, the driving control unit 204 controls at least one of the speed and steering of the vehicle 401 so that the vehicle 401 performs autonomous driving in accordance with the determined behavior. In addition to the speed and steering, the driving control unit 204 can perform various controls necessary for autonomous driving along the determined driving trajectory. The autonomous driving may include autonomous driving of a vehicle that does not require driving operation by a driver, or autonomous driving that assists driving operation by a driver.

[0064] In the above example, the case where the traveling direction of the cooperative partner (vehicle 402) is opposite to the traveling direction of the host vehicle (vehicle 401) has been described as an example. However, this embodiment is not limited to this case and can also be applied to a case where the cooperative partner approaches the host vehicle from the side in the traveling direction.

[0065] Next, a series of operations of the driving assistance process in the vehicle will be described with reference to Fig. 8. This process is realized, for example, by the processor 20a of the ECU 22 of the control device 2 executing a program in the memory 20b.

[0066] In S801, the movement status acquisition unit 202 acquires the movement status of the subject vehicle and surrounding traffic participants. As described above, the movement status acquisition unit 202 can acquire the movement status (current position and movement speed) of the subject vehicle and surrounding traffic participants from at least one of the GPS sensor 24b, the target recognition unit 201, and the communication unit 24c.

[0067] In S802, the area identifying unit 301 identifies the common area (based on at least one of the image obtained from the detection unit and the sensor information such as LIDAR) as described above.

[0068] In S803, the degree calculation unit 302 identifies a cooperation partner from among the surrounding traffic participants. As described above, the degree calculation unit 302 calculates the predicted asymmetry according to equations (1) to (5), and identifies a cooperation partner from the calculated asymmetry.

[0069] In S804, the behavior decision unit 303 calculates the cost of the first passing mode and the cost of the second passing mode, selects the passing mode with the smallest cost, and decides the behavior of the host vehicle. In S804, the behavior decision unit 303 calculates the cost according to equations (7) and (8).

[0070] In S805, the traveling control unit 204 controls the traveling of the host vehicle in accordance with the determined action (corresponding to any of the passing modes) as described above.

[0071] In S806, the degree calculation unit 302 calculates the degree of cooperation (degree of agreement) between the vehicle 1 and the other vehicle after the vehicle 1 has traveled in S805. For example, the degree calculation unit 302 calculates the degree of agreement according to equations (1) to (6).

[0072] In S807, the behavior determining unit 303 calculates the cost of each passing mode as described above. Specifically, the behavior determining unit 303 calculates the cost of each passing mode according to equations (7) and (8).

[0073] In S808, the behavior decision unit 303 multiplies the cost of the passing mode selected in S804 by a coefficient (Agreement_factor) based on the degree of cooperation (degree of agreement) according to equation (9) or equation (10). For example, if the first passing mode is selected in S804, the behavior decision unit 303 multiplies the cost of the first passing mode by Agreement_factor according to equation (9).

[0074] In S809, the behavior decision unit 303 selects the passing mode with the smallest cost using the cost of one of the passing modes calculated in S807 and the cost of the other passing mode calculated in S808. Then, the behavior decision unit 303 decides on an action corresponding to the selected passing mode.

[0075] In S810, the traveling control unit 204 generates a traveling trajectory of the vehicle 401 based on the action determined in S809, and controls the traveling of the vehicle 401 based on the generated traveling trajectory. As described above, for example, when the vehicle 401 travels in the second passing mode, the traveling control unit 204 passes through the common area 406 while avoiding the vehicle 404.

[0076] In S811, the cooperative behavior decision unit 203 determines whether to end the cooperative behavior. If the cooperative behavior decision unit 203 determines to end the cooperative behavior, it ends this series of operations. If not, it returns to S806 to repeat the process.

[0077] In this way, in the above-described embodiment, it is possible to determine the behavior of a moving object for passing through a specific area on a movement path. The above-described vehicle 401 acquires the movement status of vehicle 401 and the movement status of its partner vehicle 402, and calculates a degree of cooperation (e.g., a degree of agreement) based on the movement status of vehicle 401 and the movement status of vehicle 402. Then, vehicle 401 determines the behavior of vehicle 401 in a common area so as to increase the degree of cooperation. In this case, the degree of cooperation increases as the movement status is such that one of vehicle 401 and its partner vehicle 402 exits the common area and the other enters the common area. In this way, when passing through a common area, it becomes possible for multiple moving objects to proceed with cooperative operations without reaching an agreement with each other via communication.

[0078] In the above description, it is assumed that vehicle 401 and vehicle 402 travel straight along the lane. That is, the description is based on the assumption that the movement status of each vehicle can be obtained with high accuracy. However, vehicles do not always travel in the center of the lane, and may move left and right. Furthermore, when using recognition technology such as image recognition, the recognized traveling direction of the vehicle may not match the direction of the lane (e.g., the center of the lane). For this reason, when the predicted traveling direction of the vehicle differs from the direction of the center of the lane, the predicted traveling status of the vehicle (e.g., the traveling speed) is corrected based on the predicted traveling direction. This makes it possible to improve the prediction accuracy of cooperative behavior such as asymmetry.

[0079] Furthermore, if a vehicle's direction of travel is tilted more than a predetermined threshold relative to the lane direction, it can be assumed that the vehicle is entering a store adjacent to the lane or changing course at an unrelated intersection. Therefore, when identifying a cooperation partner, the degree calculation unit 302 may exclude vehicles that are tilted more than a predetermined threshold relative to the lane direction from the candidates for cooperation. This can avoid calculating the agreement degree for unnecessary vehicles, thereby speeding up the process for identifying a cooperation partner.

[0080] <Summary of the embodiment> (Item 1) A mobile object control system that determines the behavior of a mobile object (e.g., 1, 401) to pass through a specific area (e.g., 406) on a moving path, Acquisition means (e.g., 202) for acquiring the movement status of the moving object and the movement status of a cooperative partner (e.g., 402); a calculation means (e.g., 302) for calculating a degree of cooperation indicating a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on the movement status of the moving body and the movement status of the cooperative partner; a decision means (e.g., 303) for deciding the behavior of the moving object in the specific area so that the degree of cooperation increases; A mobile object control system characterized in that the degree of cooperation increases as the movement situation becomes such that one of the mobile object and the cooperative partner exits the specific area and the other enters the specific area.

[0081] According to this embodiment, cooperative behavior of mobile entities can be realized without the need for agreement via communication.

[0082] (Item 2) 2. The mobile object control system according to claim 1, wherein the calculation means calculates the degree of cooperation by calculating a ratio between the time required for one of the mobile object and the cooperative object, which arrives first, to pass through the specific area and the predicted arrival time difference between the mobile object and the cooperative object at the specific area.

[0083] According to this embodiment, cooperative behavior can be determined using the quantitatively calculated degree of cooperation (degree of agreement) with a cooperative partner.

[0084] (Item 3) the determining means changes a movement state of the moving object into the specific area so as to increase the degree of cooperation; 2. The mobile object control system according to item 1, wherein the calculation means calculates a new degree of cooperation based on a changed movement state of the mobile object.

[0085] According to this embodiment, cooperative behavior can be controlled while observing the behavior of the cooperative partner.

[0086] (Item 4) 4. The mobile object control system according to claim 3, wherein the determining means determines the behavior of the mobile object by changing the movement status of the mobile object into the specific area so that the first mode is that the mobile object enters the specific area after the cooperative partner exits the specific area, or the second mode is that the mobile object passes through the specific area before the cooperative partner enters the specific area.

[0087] According to this embodiment, it is possible to pass through by taking the most appropriate action among a plurality of passing modes.

[0088] (Item 5) 5. The mobile object control system according to claim 4, wherein the determining means determines the behavior of the mobile object based on a comparison between a first cost for the mobile object to become the first state as a result of its behavior and a second cost for the mobile object to become the second state as a result of its behavior. According to this embodiment, it is possible to determine an action that places less strain on the vehicle based on the strain on the vehicle for achieving each passing mode.

[0089] (Item 6) The mobile object control system described in item 5, characterized in that the determination means calculates the first cost and the second cost based on an index of comfort when the mobile object acts so that the current movement status of the mobile object becomes the movement status of the mobile object corresponding to each cost.

[0090] According to this embodiment, by using the comfort index, it becomes possible to select an action that takes into consideration the riding comfort of the occupants.

[0091] (Item 7) 7. The mobile object control system according to item 6, wherein the determining means multiplies the cost calculated based on the comfort level by a coefficient whose value increases as the degree of cooperation decreases, to determine the first cost or the second cost.

[0092] According to this embodiment, it is possible to select a passing mode that has a high degree of cooperation (degree of agreement).

[0093] (Item 8) 8. The mobile object control system according to item 7, wherein the coefficient is based on a value obtained by applying a sigmoid function to the degree of cooperation.

[0094] According to this embodiment, frequent switching of the passing mode can be suppressed.

[0095] (Item 9) 2. The mobile object control system according to claim 1, further comprising an identification means for identifying the collaboration partner based on a predicted arrival time difference between the mobile object and each of a plurality of traffic participants in the specific area.

[0096] According to this embodiment, it is possible to identify the most likely competitor in a specific area (common area) as a cooperative partner.

[0097] (Item 10) 2. The mobile object control system according to item 1, further comprising an area specifying means for specifying the specific area based on data from a sensor provided on the mobile object.

[0098] According to this embodiment, it is possible to grasp a specific area (common area) without using a high-precision map and taking into consideration movable obstacles such as parked vehicles.

[0099] (Item 11) Item 11. The mobile object control system according to item 10, wherein the area specifying means specifies the specific area based on image data captured by the mobile object.

[0100] According to this embodiment, the area can be identified inexpensively using an image sensor, without using an expensive sensor.

[0101] (Item 12) 11. The mobile object control system according to item 10, wherein the area specifying means specifies the specific area based on map data.

[0102] This embodiment allows for accurate data to be used to identify the region.

[0103] (Item 13) 2. The mobile object control system according to claim 1, wherein the specific area includes an area through which the mobile object and the cooperative partner can each pass, but through which the mobile object and the cooperative partner cannot pass simultaneously.

[0104] According to this embodiment, it becomes possible for moving bodies to move through a path that can only be passed by one moving body at a time through cooperative behavior.

[0105] (Item 14) Item 14. The mobile object control system according to item 13, wherein the mobile object and the cooperative partner, which has a different traveling direction from the mobile object, each pass through the specific area.

[0106] According to this embodiment, areas that can be entered from several directions, such as an intersection, can be traversed by coordinated actions.

[0107] (Item 15) Item 15. The mobile object control system according to item 14, wherein the mobile object and the cooperative partner traveling in the opposite direction to the mobile object each pass through the specific area.

[0108] This embodiment allows for coordinated movement through areas entering from opposite directions.

[0109] (Item 16) The mobile body control system described in item 1 further comprises a control means for controlling the travel of the mobile body to the specific area based on the determined behavior of the mobile body, as an automatic travel of the mobile body that does not require driving operation by the driver, or an automatic travel to assist driving operation by the driver.

[0110] According to this embodiment, cooperative behavior can be realized when the driver is not performing driving operations or when driving assistance is being provided.

[0111] (Item 17) The mobile body control system described in item 16, characterized in that the control means controls at least one of the speed and steering of the mobile body when the mobile body is driven automatically without requiring driving operation by a driver.

[0112] According to this embodiment, it is possible to realize driving control for cooperative behavior.

[0113] (Item 18) A control method for a mobile object control system that determines the behavior of a mobile object (e.g., 1, 401) to pass through a specific area (e.g., 406) on a moving path, comprising: An acquisition step (e.g., S801) of acquiring the movement status of the moving object and the movement status of a cooperative partner (e.g., 402); a calculation step (e.g., S806) of calculating a degree of cooperation indicating a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on the movement status of the moving body and the movement status of the cooperative partner; a determination step (e.g., S807-S809) of determining an action of the moving object toward the specific area so that the degree of cooperation increases; A control method for a mobile object control system, characterized in that the degree of cooperation increases as the movement situation becomes such that one of the mobile object and the cooperative partner exits the specific area and the other enters the specific area.

[0114] According to this embodiment, cooperative behavior of mobile entities can be realized without the need for agreement via communication.

[0115] (Item 19) A program for causing a computer to function as each means of a mobile object control system, the mobile object control system being a mobile object control system that determines the behavior of a mobile object (e.g., 1, 401) to pass through a specific area (e.g., 406) on a movement path, Acquisition means (e.g., 202) for acquiring the movement status of the moving object and the movement status of a cooperative partner (e.g., 402); a calculation means (e.g., 302) for calculating a degree of cooperation indicating a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on the movement status of the moving body and the movement status of the cooperative partner; a decision means (e.g., 303) for deciding the behavior of the moving object in the specific area so that the degree of cooperation increases; The degree of cooperation increases as the movement situation becomes such that one of the moving body and the cooperative partner exits the specific area and the other enters the specific area.

[0116] According to this embodiment, cooperative behavior of mobile entities can be realized without the need for agreement via communication.

[0117] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0118] 1...vehicle, 2...control device, 21-29...ECU

Claims

1. A mobile object control system that determines the behavior of a mobile object to pass through a specific area on a movement path, acquisition means for acquiring a movement status of the moving body and a movement status of a cooperative partner; a calculation means for calculating a degree of cooperation that indicates a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on a movement status of the moving body and a movement status of the cooperative partner; a decision means for deciding an action of the moving object in the specific area so as to increase the degree of cooperation; A mobile object control system characterized in that the degree of cooperation increases as the movement situation becomes such that one of the mobile object and the cooperative partner exits the specific area and the other enters the specific area.

2. 2. The mobile body control system according to claim 1, wherein the calculation means calculates the degree of cooperation by calculating the ratio between the time required for one of the mobile body and the cooperative partner, which arrives first, to pass through the specific area and the predicted arrival time difference between the mobile body and the cooperative partner at the specific area.

3. the determining means changes a movement state of the moving object into the specific area so as to increase the degree of cooperation; 2. The mobile object control system according to claim 1, wherein said calculation means calculates a new degree of cooperation based on a changed movement state of said mobile object.

4. The mobile object control system according to claim 3, characterized in that the determination means determines the behavior of the mobile object by changing the movement status of the mobile object into the specific area so that the first mode is that the mobile object enters the specific area after the cooperative partner exits the specific area, or the second mode is that the mobile object passes through the specific area before the cooperative partner enters the specific area.

5. 5. The mobile object control system according to claim 4, wherein the determination means determines the behavior of the mobile object based on a comparison between a first cost for the mobile object to become the first state as a result of its behavior and a second cost for the mobile object to become the second state as a result of its behavior.

6. The mobile body control system described in claim 5, characterized in that the determination means calculates the first cost and the second cost based on an index of comfort when the mobile body acts so that the current movement status of the mobile body becomes the movement status of the mobile body corresponding to each cost from the current movement status of the mobile body.

7. 7. The mobile object control system according to claim 6, wherein the determining means multiplies the first cost or the second cost by a coefficient whose value increases as the degree of cooperation decreases, by the cost calculated based on the comfort level.

8. 8. The mobile object control system according to claim 7, wherein the coefficient is based on a value obtained by applying a sigmoid function to the degree of cooperation.

9. 2. The mobile object control system according to claim 1, further comprising an identification means for identifying the cooperation partner for each of a plurality of traffic participants based on a predicted arrival time difference between the mobile object and the specific area.

10. 2. The mobile body control system according to claim 1, further comprising area specifying means for specifying the specific area based on data from a sensor provided in the mobile body.

11. 11. The mobile object control system according to claim 10, wherein the area specifying means specifies the specific area based on image data captured by the mobile object.

12. 11. The mobile object control system according to claim 10, wherein the area specifying means specifies the specific area based on map data.

13. 2. The mobile object control system according to claim 1, wherein the specific area includes an area through which the mobile object and the cooperative object can each pass, but through which the mobile object and the cooperative object cannot pass simultaneously.

14. The mobile object control system according to claim 13, wherein the mobile object and the cooperative partner traveling in a direction different from that of the mobile object each pass through the specific area.

15. 15. The mobile object control system according to claim 14, wherein the mobile object and the cooperative partner traveling in an opposite direction to the mobile object each pass through the specific area.

16. The mobile body control system according to claim 1, further comprising a control means for controlling the travel of the mobile body into the specific area based on the determined behavior of the mobile body, as an automatic travel of the mobile body that does not require driving operation by the driver, or as an automatic travel to assist driving operation by the driver.

17. 17. The mobile body control system according to claim 16, wherein the control means controls at least one of the speed and steering of the mobile body when the mobile body is driven automatically without requiring a driver to operate the mobile body.

18. A control method for a mobile object control system that determines the behavior of a mobile object to pass through a specific area on a movement path, comprising: an acquisition step of acquiring a movement status of the moving body and a movement status of a cooperative partner; a calculation step of calculating a degree of cooperation indicating a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on a movement status of the moving body and a movement status of the cooperative partner; a determination step of determining an action of the moving object in the specific area so that the degree of cooperation increases; A control method for a mobile object control system, characterized in that the degree of cooperation increases as the movement situation becomes such that one of the mobile object and the cooperative partner exits the specific area and the other enters the specific area.

19. A program for causing a computer to function as each means of a mobile object control system, the mobile object control system being a mobile object control system that determines the behavior of a mobile object for passing through a specific area on a movement path, acquisition means for acquiring a movement status of the moving body and a movement status of a cooperative partner; a calculation means for calculating a degree of cooperation that indicates a degree to which the moving body passes through the specific area in cooperation with the cooperative partner based on a movement status of the moving body and a movement status of the cooperative partner; a decision means for deciding an action of the moving object in the specific area so as to increase the degree of cooperation; The degree of cooperation increases as the movement situation becomes such that one of the moving body and the cooperative partner exits the specific area and the other enters the specific area.

20. A program for causing a computer to function as each of the means of the mobile object control system according to any one of claims 2 to 14.

Images