Control system and control method

Abstract

This control system (10) comprises: an acquisition unit (11) that acquires sensing data output by a sensor that senses the outside of a moving body; a detection unit (12) that detects the position of an object outside the moving body on the basis of the sensing data; a movement prediction unit (13) that predicts the movement of the object on the basis of the sensing data; a cost map generation unit (14) that generates a first cost map based on the detected position of the object and generates a second cost map based on the predicted movement of the object; a route generation unit (15) that generates a route of the moving body on the basis of the first cost map; a determination generation unit (16) that generates movement determination for the moving body on the basis of the second cost map and the generated route; and a control unit (17) that controls the movement of the moving body according to the generated route and the movement determination.

Description

[Technical field]

[0001] The present disclosure relates to a control system and a control method for controlling the movement of a moving object. [Background technology]

[0002] 2. Description of the Related Art Conventionally, driving assistance devices have been disclosed that predict the movement of objects such as obstacles outside the vehicle and enable the vehicle to travel safely by avoiding collision with the objects outside the vehicle (for example, Patent Document 1).

[0003] It is also possible to use a cost map that represents objects outside the vehicle as costs to generate a vehicle route that avoids areas with high costs, and to allow the vehicle to travel safely along the generated route (for example, non-patent document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5617677 [Non-patent literature]

[0005] [Non-Patent Document 1] A novel navigation scheme in dynamic environment using layered costmap, https: / / ieeexplore.ieee.org / abstract / document / 7978468 Summary of the Invention [Problem to be solved by the invention]

[0006] However, a route generated using a cost map that takes into account the movement of objects may compromise the safety or comfort of travel of a moving body such as a vehicle.

[0007] Therefore, the present disclosure provides a control system etc. that can improve the safety or comfort of movement of a moving object using a cost map. [Means for solving the problem]

[0008] The control system of the present disclosure includes an acquisition unit that acquires sensing data output by a sensor that senses the outside of a moving body, a detection unit that detects the position of an object outside the moving body based on the sensing data, a movement prediction unit that predicts movement of the object based on the sensing data, a cost map generation unit that generates a first cost map based on the detected position of the object and generates a second cost map based on the predicted movement of the object, a path generation unit that generates a path of the moving body based on the first cost map, a judgment generation unit that generates a movement judgment for both the moving bodies based on the second cost map and the generated path, and a control unit that controls movement of the moving body in accordance with the generated path and the movement judgment.

[0009] Furthermore, these comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM, or may be realized by any combination of the system, the method, the integrated circuit, the computer program, and the recording medium. Effect of the Invention

[0010] According to a control system and the like according to an aspect of the present disclosure, it is possible to improve the safety or comfort of the movement of a moving object using a cost map. [Brief description of the drawings]

[0011] [Figure 1A] 11 is a diagram for explaining a problem that occurs when object movement prediction is reflected in a cost map. FIG. [Figure 1B] 11 is a diagram for explaining a problem that occurs when object movement prediction is reflected in a cost map. FIG. [Diagram 2]1 is a block diagram showing an example of a control system according to a first embodiment. [Diagram 3] 4 is a flowchart showing an example of the operation of the control system according to the first embodiment. [Figure 4] 4A and 4B are diagrams illustrating an example of a first cost map and a second cost map. [Diagram 5] FIG. 11 is a diagram showing an example of a route generated based on a first cost map. [Figure 6] FIG. 13 is a diagram showing an example of a movement determination generated based on a second cost map and a generated route. [Figure 7] FIG. 13 is a diagram showing an example of a route generated based in part on a second cost map. [Figure 8] FIG. 11 is a block diagram showing an example of a control system according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] (How one aspect of the present disclosure was achieved) First, the process by which one embodiment of the present disclosure was achieved will be described with reference to FIGS. 1A and 1B.

[0013] 1A and 1B are diagrams for explaining a problem that occurs when object movement prediction is reflected in a cost map.

[0014] As described above, a cost map often deals with a static environment, and when dealing with a dynamic environment, it is possible to generate a vehicle route by reflecting the motion prediction of an object such as an obstacle outside a moving body (e.g., a vehicle) in the cost map. For example, it is possible to increase the cost of the area to which the object will move based on the predicted object motion, and generate a vehicle route that avoids areas with high cost. However, when the motion prediction of an object is reflected in the cost map, problems such as those described in FIG. 1A and FIG. 1B arise.

[0015] FIG. 1A shows that time advances, for example, by 0.1 seconds in the order of the left diagram, the center diagram, and the right diagram. At the time of the left diagram in FIG. 1A, the vehicle 200 is predicted to move straight, the prediction result is reflected in the cost map, and a route is generated in which the vehicle 100 turns left in the traveling direction to avoid the vehicle 200 moving straight based on the cost map in which the prediction result is reflected. However, the movement prediction is not stable in reality, and for example, while the vehicle 200 is predicted to move straight at the time of the left diagram in FIG. 1A, the vehicle 200 is predicted to turn right in the traveling direction 0.1 seconds later at the time of the center diagram. Therefore, at the time of the center diagram in FIG. 1A, a route is generated in which the vehicle 100 turns right in the traveling direction to avoid the vehicle 200 turning right in the traveling direction based on the cost map in which the prediction result is reflected. Furthermore, for example, while at the time of the central diagram in Fig. 1A, it is predicted that the vehicle 200 will turn to the right in the traveling direction, at the time of the right diagram 0.1 seconds later, it is predicted that the vehicle 200 will turn to the left in the traveling direction. Therefore, at the time of the right diagram in Fig. 1A, a route is generated in which the vehicle 100 turns to the left in the traveling direction based on a cost map reflecting the prediction result, in order to avoid the vehicle 200 turning to the left in the traveling direction. As a result, a route is generated that fluctuates from moment to moment, and the vehicle 100 behaves in a meandering manner, which poses a problem in the safety or comfort of the traveling of the vehicle 100.

[0016] 1B also shows that vehicle 200 is predicted to travel straight, the prediction result is reflected in a cost map, and a route is generated in which vehicle 100 turns to the right in the traveling direction to avoid vehicle 200 traveling straight, based on the cost map reflecting the prediction result. In such a case, it would be safer for vehicle 100 to stop, but vehicle 100 will actively try to avoid vehicle 200, causing the two vehicles 100 to approach each other, creating a problem with the safety of vehicle 100's travel.

[0017] Therefore, a control system according to one embodiment of the present disclosure includes an acquisition unit that acquires sensing data output by a sensor that senses the outside of a moving body, a detection unit that detects the position of an object outside the moving body based on the sensing data, a movement prediction unit that predicts movement of the object based on the sensing data, a cost map generation unit that generates a first cost map based on the detected position of the object and generates a second cost map based on the predicted movement of the object, a path generation unit that generates a path of the moving body based on the first cost map, a judgment generation unit that generates a movement judgment of the moving body based on the second cost map and the generated path, and a control unit that controls the movement of the moving body in accordance with the generated path and the movement judgment.

[0018] According to this, a first cost map based on the position of the detected object and a second cost map based on the predicted movement of the object are generated, and each cost map is used for generating the path of the moving body and generating the movement judgment of the moving body. Specifically, the first cost map in which the object's movement prediction is not reflected is used for generating the path of the moving body, and the second cost map in which the object's movement prediction is reflected is used for generating the movement judgment of the moving body. By using the first cost map in which the movement prediction is not reflected for generating the path of the moving body, even if the movement prediction is not stable, a path that fluctuates from moment to moment is not easily generated, and the safety or comfort of the movement of the moving body can be improved. In addition, by using the second cost map in which the object's movement prediction is reflected and the generated path for generating the movement judgment of the moving body, it is possible to avoid stationary objects while avoiding moving objects, and to stop or slow down the moving body according to the movement prediction of the object without trying to avoid them by force, and the safety of the movement of the moving body can be improved. In this way, it is possible to generate a stable path on the premise that the movement prediction is not stable, and to stop or slow down when necessary. Therefore, according to this aspect, it is possible to improve the safety or comfort of the movement of the moving body using the cost map.

[0019] The movement determination may also include stopping or slowing down the moving body when an area in the second cost map that has been assigned a cost equal to or greater than a predetermined cost overlaps with the generated route.

[0020] When an area in the second cost map to which a cost equal to or greater than a predetermined cost is assigned overlaps with the generated route, there is a risk of collision with a moving object if the moving body moves along the generated route. Therefore, in this case, a movement decision is generated to stop or slow down the moving body, thereby improving the safety of the moving body's movement.

[0021] The route generating unit may generate the route of the moving object based also on a part of the second cost map.

[0022] For example, when the mobile body moves to avoid a moving object, the occupant may be wary of the moving object and may wish to move further away from the moving object than would be the case when avoiding a non-moving object. In this regard, by using a part of the second cost map reflecting the object's motion prediction in generating the path of the mobile body, the mobile body can move further away from the moving object than would be the case when avoiding a non-moving object.

[0023] For example, a portion of the second cost map may be determined according to an attribute of the object.

[0024] For example, the accuracy of motion prediction may be low depending on the attributes of the object. For example, since a person can suddenly change the direction of travel, when the object is a person, the accuracy of motion prediction of the person is likely to be low. For this reason, for example, when the attributes of the object are attributes that result in low accuracy of motion prediction, a part of the second cost map can be made small to reduce the influence of motion prediction on route generation.

[0025] For example, a portion of the second cost map may be determined according to attributes of a section included in a road on the route of the mobile object. For example, the attributes of the section may include a width of the road. For example, the attributes of the section may include a width of a sidewalk associated with the road, if the road is a road for mobile objects. For example, the attributes of the section may include an intersection on the route of the mobile object. For example, the attributes of the section may include a type of the road.

[0026] For example, when the width of a path of a moving body such as a vehicle (for example, the width of a driving lane) is narrow, the moving body may be less likely to move away from a moving object than to avoid a non-moving object. For this reason, for example, when the width of a path of a moving body is narrow, a part of the second cost map can be made small to reduce the influence of motion prediction on the generation of the path, and the moving body can be prevented from significantly going outside the driving lane when avoiding a moving object. Also, for example, at an intersection on the path of the moving body, the movements of objects around the moving body become complicated, and the accuracy of the object motion prediction is likely to be low. For this reason, for example, when the moving body is at an intersection, a part of the second cost map can be made small to reduce the influence of motion prediction on the generation of the path.

[0027] The cost map generating unit may further generate a third cost map based on attributes of the detected object, and the judgment generating unit may generate a movement judgment of the moving body based on the third cost map as well. For example, the judgment generating unit may generate a stop judgment of the moving body as the movement judgment based on the generated path and the third cost map.

[0028] It is desirable that the movement judgment is determined according to the attributes of an object outside the moving body. For example, depending on the attributes of an object outside the moving body, it may be better to stop the moving body. For example, there is a case where a person is standing still near a crosswalk and is about to cross the crosswalk. In this case, the movement judgment generated based on the second cost map may not stop the moving body because the person is not moving. Therefore, a third cost map is generated based on the attributes of the object (for example, whether the attribute of the object is a person or not), and a stop judgment of the moving body is made based on the third cost map, so that the moving body can be stopped depending on the attributes of the object, and the safety of the movement of the moving body can be further improved.

[0029] The system may further include a lane prediction unit that predicts a lane along which the moving object is scheduled to move, the cost map generation unit may further generate a fourth cost map based on the predicted lane, and the judgment generation unit may generate a movement judgment for the moving object based also on the fourth cost map. For example, the judgment generation unit may generate a deceleration judgment for the moving object as the movement judgment based on the generated path and the fourth cost map.

[0030] It is desirable that the movement judgment is determined according to the lane in which the moving body is scheduled to move. For example, depending on the lane in which the moving body is scheduled to move, it may be better to decelerate the moving body. For example, when a moving body such as a vehicle is about to move to an adjacent lane, there may be a rear vehicle behind in the lane in which the moving body is scheduled to move. In this case, in the movement judgment generated based on the second cost map, for example, even if a rear vehicle is present far enough behind that the moving body can move in the lane with ease, the moving body may stop. Therefore, a fourth cost map is generated based on the predicted lane, and a deceleration judgment is made based on the fourth cost map, so that the moving body can decelerate and move in the lane smoothly, and the safety or comfort of the moving body can be further improved.

[0031] A control method according to one embodiment of the present disclosure is a control method executed by a computer, which acquires sensing data output by a sensor that senses the outside of a moving body, detects the position of an object outside the moving body based on the sensing data, predicts movement of the detected object, generates a first cost map based on the position of the detected object, generates a second cost map based on the predicted movement of the object, generates a path for the moving body based on the first cost map, generates a movement judgment for the moving body based on the second cost map and the generated path, and controls the movement of the moving body in accordance with the generated path and the movement judgment.

[0032] This makes it possible to provide a control method that can improve the safety or comfort of the movement of a moving object using a cost map.

[0033] Hereinafter, the embodiment will be specifically described with reference to the drawings.

[0034] The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, the arrangement and connection of the components, steps, and the order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure.

[0035] (Embodiment 1) The first embodiment will be described with reference to FIG. 2 to FIG.

[0036] FIG. 2 is a block diagram showing an example of the control system 10 according to the first embodiment.

[0037] The control system 10 is a computer for controlling the movement of a moving body. The control system 10 is, for example, an in-vehicle device mounted on a moving body (for example, a vehicle 100, etc.). The control system 10 is a computer including a processor, a memory, a communication interface, etc. The memory is a ROM (Read Only Memory) and a RAM (Random Access Memory), etc., and can store a program executed by the processor. The control system 10 includes an acquisition unit 11, a detection unit 12, a movement prediction unit 13, a cost map generation unit 14, a path generation unit 15, a judgment generation unit 16, and a control unit 17. The acquisition unit 11, the detection unit 12, the movement prediction unit 13, the cost map generation unit 14, the path generation unit 15, the judgment generation unit 16, and the control unit 17 are realized by a processor or the like that executes a program stored in the memory. Here, the moving body is described as a vehicle, and the control system 10 is described as a computer for controlling the running of the vehicle. In addition to a vehicle, the moving body may be an air vehicle such as a drone, a mobile robot, or a ship.

[0038] The control system 10 does not have to be mounted on a vehicle, and may be a server connected to the vehicle so as to be capable of wireless communication. Also, the components constituting the control system 10 may be distributed and arranged in a plurality of servers.

[0039] The acquisition unit 11 acquires sensing data output by a sensor that senses the outside of the vehicle. For example, the acquisition unit 11 acquires sensing data output by a sensor mounted on a vehicle to be controlled by the control system 10, a vehicle surrounding the vehicle, or a roadside unit or the like surrounding the vehicle. The sensor is, for example, a camera or a LiDAR (Light Detection and Ranging) sensor.

[0040] The detection unit 12 detects the position of an object outside the vehicle based on the sensing data acquired by the acquisition unit 11. For example, the detection unit 12 detects the position of the object by analyzing the sensing data using a learning model or the like.

[0041] The movement prediction unit 13 predicts the movement of an object outside the vehicle based on the sensing data acquired by the acquisition unit 11. For example, the movement prediction unit 13 predicts the movement of the object (specifically, the moving direction, speed, etc. of the object) based on a change in the position of the object detected by the sensing data acquired moment by moment.

[0042] The cost map generating unit 14 generates a first cost map based on the position of the detected object, and generates a second cost map based on the predicted movement of the object. The cost map generating unit 14 will be described in detail later with reference to Figs. 3 and 4.

[0043] The route generating unit 15 generates a route for the vehicle based on the first cost map. The route generating unit 15 will be described in detail later with reference to Figs.

[0044] The decision generating unit 16 generates a movement decision for the vehicle based on the second cost map and the generated route. The details of the decision generating unit 16 will be described later with reference to Figs. 3 and 6.

[0045] The control unit 17 controls the movement of the vehicle according to the generated route and the movement judgment. For example, the control unit 17 stops or decelerates the vehicle according to the movement judgment while moving the vehicle along the generated route.

[0046] FIG. 3 is a flowchart showing an example of the operation of the control system 10 according to the first embodiment.

[0047] As described above, the acquisition unit 11 acquires sensing data output by a sensor that senses the outside of the vehicle (step S11), the detection unit 12 detects the position of an object outside the vehicle based on the sensing data (step S12), and the movement prediction unit 13 predicts the movement of the object outside the vehicle based on the sensing data (step S13).

[0048] Next, the cost map generating unit 14 generates a first cost map based on the position of the detected object (step S14), and generates a second cost map based on the predicted movement of the object (step S15). The cost map is a grid map that expresses objects such as obstacles as costs in order to generate an optimal path. For example, a high cost is assigned to an area where an object exists, and a path that avoids the area can be generated. The cost map typically has values ​​in a range determined by an upper limit value and a lower limit value in each grid, but is not limited to this, and the value in each grid may be two values. The cost map is also called a potential map. Here, the first cost map and the second cost map generated by the cost map generating unit 14 will be described with reference to FIG. 4.

[0049] 4 is a diagram showing an example of the first cost map and the second cost map, and in the following figures as well, a vehicle 200 is shown as an example of an object external to the vehicle.

[0050] The first cost map is a cost map generated based on the position of a detected object (for example, the vehicle 200). Fig. 4 shows that the first cost map is generated so that the cost is high around the vehicle 200.

[0051] The second cost map is a cost map generated based on the predicted movement of an object (e.g., vehicle 200). For example, vehicle 200 is predicted to turn left in the traveling direction, and Fig. 4 shows that the second cost map is generated so that the cost is high in the predicted moving direction of vehicle 200 (e.g., the direction of the arrow emanating from vehicle 200). In addition, the higher the predicted speed of vehicle 200, the further the area with high cost extends from vehicle 200 in the moving direction.

[0052] The cost map generating unit 14 generates a first cost map and a second cost map as shown in Fig. 4. Note that in Fig. 4, the cost map is shown as a schematic circle with the cost inside the circle being constant, but in reality the cost in the cost map is not constant and the cost decreases from the center of the circle to the outside.

[0053] Returning to the explanation in Fig. 3, the route generating unit 15 generates a route for the vehicle based on the first cost map (step S16). Here, the route generated based on the first cost map will be explained with reference to Fig. 5.

[0054] 5 is a diagram showing an example of a route generated based on the first cost map. In the drawings including the following drawings, a vehicle 100 is shown as an example of a vehicle controlled by the control system 10.

[0055] 5, in the first cost map, the cost is high around the position of the vehicle 200, and the route generating unit 15 generates a route that avoids areas with high cost in the first cost map. When the vehicle 100 moves along the route, there is a risk of collision between the vehicle 100 and the vehicle 200 depending on the movement of the vehicle 200. However, in this case, the movement prediction of the vehicle 200 is not taken into consideration, and the route of the vehicle 100 is generated based on the first cost map that is generated based on the position of the vehicle 200 at a certain moment.

[0056] Returning to the explanation in Fig. 3, the judgment generating unit 16 generates a vehicle movement judgment based on the second cost map and the generated route (step S17). Here, the route generated based on the second cost map and the generated route will be explained with reference to Fig. 6.

[0057] FIG. 6 is a diagram illustrating an example of a movement determination generated based on the second cost map and a generated route.

[0058] As shown in FIG. 6, an area in the second cost map to which a cost equal to or greater than a predetermined cost is assigned overlaps with the generated route. The predetermined cost is a cost indicating that the probability of an object's existence is high or will become high. In other words, if the vehicle 100 moves along the generated route, there is a risk of the vehicle 100 colliding with the vehicle 200. Therefore, the movement judgment generated by the judgment generating unit 16 includes stopping or decelerating the vehicle 100 when an area in the second cost map to which a cost equal to or greater than a predetermined cost is assigned overlaps with the generated route. This makes it possible to prevent a collision between the vehicle 100 and the vehicle 200, thereby improving the safety of the vehicle's travel.

[0059] The judgment generating unit 16 may generate a movement judgment based on the first cost map in addition to the second cost map and the generated route. Alternatively, the cost map generating unit 14 may generate a second cost map based on the position of a detected object in addition to the predicted object movement, and the judgment generating unit 16 may generate a movement judgment based on the second cost map and the generated route. In other words, the vehicle movement judgment may be generated taking into account the position of the object.

[0060] 3, the control unit 17 controls the movement of the vehicle according to the generated route and the movement judgment (step S18). For example, the control unit 17 calculates a tire angle or a pedal depression amount, etc. according to the generated route and the movement judgment, and notifies the vehicle of the calculation result via a CAN (Controller Area Network), etc., thereby controlling the movement of the vehicle.

[0061] The route generating unit 15 may generate a route for the vehicle based on a part of the second cost map as well. This will be described with reference to FIG.

[0062] FIG. 7 is a diagram showing an example of a route generated based on a part of the second cost map.

[0063] The part of the second cost map is, for example, a part of the region where the cost is high in the second cost map shown in Fig. 6 etc. Note that the part of the second cost map may be a reduced part of the second cost map where the cost is high, or may be a part of the second cost map where only the object side part is cut out from the part where the cost is high.

[0064] For example, when the vehicle 100 is driving to avoid a moving vehicle 200, the occupant of the vehicle 100 may be wary of the moving vehicle 200 and may wish to drive at a greater distance than the distance required to avoid a non-moving object. In this regard, a part of the second cost map reflecting the motion prediction of the vehicle 200 is used to generate the route of the vehicle 100, so that the vehicle 100 can drive at a greater distance when avoiding the moving vehicle 200 than when avoiding a non-moving object. For example, in the situation of FIG. 7, a route is generated that avoids areas with high costs in a part of the second cost map in addition to the first cost map, so that the vehicle 100 can drive as far to the right as possible from the vehicle 200.

[0065] A method for determining a portion of the second cost map will be described below.

[0066] For example, a part of the second cost map is determined according to the attribute of an object outside the vehicle. For example, the control system 10 may have a function such as an attribute detection unit 18 described later, and the attribute of an object outside the vehicle can be detected by, for example, sensing data by a sensor such as a camera. For example, the accuracy of motion prediction may be low depending on the attribute of the object. For example, since a person can suddenly change the direction of travel, when the object is a person, the accuracy of motion prediction of the person is likely to be low. For this reason, for example, when the attribute of the object is such that the accuracy of motion prediction is low, a part of the second cost map can be made small (i.e., the area of ​​the high-cost area can be made small) to reduce the influence of motion prediction on the generation of the route. In this case, the avoidance operation of the vehicle against the object is suppressed. Also, for example, when the attribute of the object is such that the accuracy of motion prediction is high, a part of the second cost map can be made large (i.e., the area of ​​the high-cost area can be made large) to increase the influence of motion prediction on the generation of the route. In this case, the avoidance operation of the vehicle against the object is recommended.

[0067] Also, for example, a part of the second cost map is determined according to attributes of a section included in a road on the vehicle's route. For example, the attributes of the section may include the width of the road on the vehicle's route, the width of the sidewalk accompanying the road, an intersection on the vehicle's route, or the type of road. An intersection is a place where two or more roads intersect, and is typically a crossroad, but is not limited to this, and may be a three-way intersection or a roundabout. Also, a sidewalk may be a sidewalk parallel to a road or a crosswalk crossing a road. The attributes of the section can be determined, for example, by sensing data by a sensor such as a camera or map information. Also, the type of the road may be a prescribed type of road such as a roadway or a sidewalk, or may be a road similar to the prescribed type. Specifically, a road similar to the prescribed type may be determined based on the type of object around the vehicle determined based on the sensing data or the distance between the object and the vehicle. For example, if the density of people around the vehicle is equal to or greater than a threshold, the type of the road may be determined to be a sidewalk (or a pseudo sidewalk). Examples of pseudo-sidewalks include a shopping street and a roadway in a pedestrian zone.

[0068] For example, when the width of the road on the vehicle's route (e.g., the width of the driving lane) is narrow, the vehicle may be less likely to drive away from a moving object than when avoiding a non-moving object. For this reason, for example, when the width of the road on the vehicle's route is narrow, a portion of the second cost map can be made smaller to reduce the effect of the motion prediction on the generation of the route. In this case, the vehicle's avoidance operation for the object is suppressed, and the vehicle can be prevented from going too far out of the driving lane when avoiding a moving object.

[0069] Also, for example, when the sidewalk accompanying the road on the vehicle's route is wide, the vehicle may run onto the sidewalk or get too close to the sidewalk when avoiding a moving object. For this reason, for example, when the sidewalk on the vehicle's route is wide, a part of the second cost map can be made small to reduce the influence of the motion prediction on the generation of the route. In this case, the vehicle's avoidance operation against the object is suppressed, and it is possible to suppress the vehicle from running onto the sidewalk or getting too close when avoiding a moving object.

[0070] Also, for example, at an intersection on the vehicle's route, the movements of objects around the vehicle become complicated, and the accuracy of object movement prediction tends to be low. For this reason, for example, when the vehicle is at an intersection, a portion of the second cost map can be made smaller to reduce the influence of the movement prediction on the generation of the route. In this case, the vehicle's avoidance operation against the object is suppressed.

[0071] Also, for example, when the type of road on the vehicle's route is a sidewalk, the density of objects (e.g., pedestrians) around the vehicle is high (in other words, the vehicle and objects are close to each other), so the vehicle may stop frequently. On the other hand, the vehicle's moving speed is reduced on the sidewalk, so the risk of collision is lower than on the road. For this reason, for example, when the type of road is a sidewalk, a portion of the second cost map is made larger than when the type of road is a roadway, to increase the influence of the motion prediction on the generation of the route. This prevents the vehicle from stopping, and allows the vehicle to continue moving while avoiding objects.

[0072] Note that a portion of the second cost map may be determined according to both the attributes of objects outside the vehicle and the attributes of sections included in the roads on the route of the vehicle.

[0073] As described above, according to the control system 10, a first cost map based on the position of the detected object and a second cost map based on the predicted movement of the object are generated, and each cost map is used for generating the vehicle's route and generating the vehicle's movement judgment. Specifically, the first cost map that does not reflect the object's movement prediction is used for generating the vehicle's route, and the second cost map that reflects the object's movement prediction is used for generating the vehicle's movement judgment. By using the first cost map that does not reflect the movement prediction for generating the vehicle's route, even if the movement prediction is unstable, a route that fluctuates from moment to moment is unlikely to be generated, and the safety or comfort of the vehicle's travel can be improved. In addition, by using the second cost map that reflects the object's movement prediction and the generated route for generating the vehicle's movement judgment, it is possible to avoid stationary objects while avoiding moving objects, and to stop or slow down the vehicle, for example, according to the movement prediction of the object without trying to avoid them by force, thereby improving the safety of the vehicle's travel. In this way, on the premise that the movement prediction is unstable, a stable route can be generated, and the vehicle can stop or slow down when necessary. Therefore, according to this aspect, it is possible to improve the safety and comfort of vehicle travel using a cost map.

[0074] (Embodiment 2) Next, a second embodiment will be described with reference to FIG.

[0075] 8 is a block diagram showing an example of a control system 10a according to the second embodiment. The control system 10a according to the second embodiment differs from the control system 10 according to the first embodiment in that it further includes an attribute detection unit 18 and a lane prediction unit 19, and includes a cost map generation unit 14a and a judgment generation unit 16a instead of the cost map generation unit 14 and the judgment generation unit 16. The other points are the same as those in the first embodiment, and therefore the description will be omitted. The cost map generation unit 14a, the judgment generation unit 16a, the attribute detection unit 18, and the lane prediction unit 19 are realized by a processor or the like that executes a program stored in a memory.

[0076] The attribute detection unit 18 detects attributes of an object outside the vehicle based on sensing data obtained by a sensor such as a camera acquired by the acquisition unit 11. For example, the attribute detection unit 18 detects the attributes of the object by analyzing the sensing data using a learning model or the like. For example, the attribute detection unit 18 detects whether the object is a person, a roadside unit, a car, a bicycle, or the like.

[0077] The lane prediction unit 19 predicts the lane in which the vehicle is scheduled to travel. For example, the lane prediction unit 19 may obtain information indicating the vehicle's planned travel schedule from a car navigation system, and predict the lane in which the vehicle is scheduled to travel based on the information. Also, for example, the lane prediction unit 19 may obtain operation information on a turn signal, and predict the lane in which the vehicle is scheduled to travel based on the information.

[0078] The cost map generating unit 14a generates a third cost map based on the attributes of the detected object. For example, if the object is a stationary object such as a roadside unit, a third cost map is generated in which the cost of the area around the object is small. Also, for example, if the object is a person, a third cost map is generated in which the cost of the area around the object is large.

[0079] Furthermore, the cost map generating unit 14a generates a fourth cost map based on the predicted lanes. For example, the fourth cost map is generated such that the cost of an area corresponding to the lane in which the vehicle is scheduled to travel is large.

[0080] The judgment generating unit 16a generates a movement judgment of the vehicle based on the third cost map as well. For example, the judgment generating unit 16a generates a stop judgment of the vehicle as a movement judgment based on the generated route and the third cost map. For example, the movement judgment includes stopping the vehicle when an area to which a cost equal to or higher than a predetermined cost is assigned in the third cost map overlaps with the generated route. For example, depending on the attributes of an object outside the vehicle, it may be better to stop the vehicle. For example, there is a case where a person is standing still beside a pedestrian crossing and is about to cross the pedestrian crossing. In this case, in the movement judgment generated based on the second cost map, the person is not moving, so there is a possibility that the vehicle will not be stopped. Therefore, the third cost map is generated based on the attributes of the object (for example, whether the attribute of the object is a person or not), and the stop judgment of the vehicle is made based on the third cost map, so that the vehicle can be stopped depending on the attributes of the object, and the safety of the vehicle's travel can be further improved.

[0081] The judgment generating unit 16a also generates a movement judgment of the vehicle based on the fourth cost map. For example, the judgment generating unit 16a generates a deceleration judgment of the vehicle as a movement judgment based on the generated route and the fourth cost map. For example, the movement judgment includes decelerating the vehicle when an area in which a cost equal to or higher than a predetermined cost is assigned in the fourth cost map overlaps with the generated route. For example, depending on the lane in which the vehicle is scheduled to travel, it may be better to decelerate the vehicle. For example, when the vehicle is about to move to the adjacent lane, there may be a rear vehicle behind the vehicle in the lane in which the vehicle is scheduled to travel. In this case, in the movement judgment generated based on the second cost map, the vehicle may stop even if, for example, a rear vehicle is present far enough behind that the lane movement can be made with ease. Therefore, the fourth cost map is generated based on the predicted lane, and the deceleration judgment is made based on the fourth cost map, so that the vehicle can be decelerated to move smoothly through the lane, and the safety or comfort of the vehicle's travel can be further improved.

[0082] As described above, in addition to the first cost map based on the position of the object and the second cost map based on the movement of the object, a third cost map based on the attributes of the object and a fourth cost map based on the lane in which the vehicle is planned to travel are generated, and a vehicle movement judgment is generated based on the first cost map, the second cost map, the third cost map and the fourth cost map, thereby further improving the safety and comfort of the vehicle's travel.

[0083] (Other embodiments) Although the control system according to one or more aspects of the present disclosure has been described based on the embodiments, the present disclosure is not limited to these embodiments. As long as it does not deviate from the spirit of the present disclosure, various modifications conceived by a person skilled in the art to each embodiment and forms constructed by combining components in different embodiments may also be included within the scope of one or more aspects of the present disclosure.

[0084] For example, in the above-mentioned second embodiment, the cost map generating unit 14a generates both the third cost map and the fourth cost map, but the fourth cost map may not be generated. In this case, the control system 10a may not include the lane prediction unit 19, and the judgment generating unit 16a may not generate the vehicle movement judgment based on the fourth cost map either. Alternatively, the cost map generating unit 14a may not generate the third cost map. In this case, the control system 10a may not include the attribute detection unit 18, and the judgment generating unit 16a may not generate the vehicle movement judgment based on the third cost map either.

[0085] The present disclosure can be realized not only as a control system, but also as a control method including steps (processing) performed by each component of the control system.

[0086] Specifically, the control method is a control method executed by a computer, and includes the following processes as shown in Fig. 3: acquiring sensing data output by a sensor that senses the outside of the moving body (step S11), detecting the position of an object outside the moving body based on the sensing data (step S12), predicting the movement of the detected object (step S13), generating a first cost map based on the position of the detected object (step S14), generating a second cost map based on the predicted movement of the object (step S15), generating a path of the moving body based on the first cost map (step S16), generating a movement decision of the moving body based on the second cost map and the generated path (step S17), and controlling the movement of the moving body in accordance with the generated path and movement decision (step S18). Note that in Fig. 3, the moving body is a vehicle.

[0087] For example, the present disclosure may be realized as a program for causing a processor to execute steps included in the control method. Furthermore, the present disclosure may be realized as a non-transitory computer-readable recording medium, such as a CD-ROM, on which the program is recorded.

[0088] For example, when the present disclosure is realized by a program (software), each step is executed by executing the program using hardware resources such as a computer's CPU, memory, input / output circuitry, etc. In other words, each step is executed by the CPU acquiring data from memory or input / output circuitry, etc., performing calculations, and outputting the results of calculations to memory or input / output circuitry, etc.

[0089] In the above embodiment, each component included in the control system may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

[0090] Some or all of the functions of the control system according to the above-mentioned embodiment are typically realized as an LSI, which is an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip that includes some or all of the functions. Furthermore, the integrated circuit is not limited to an LSI, and may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after the LSI is manufactured, or a reconfigurable processor that can reconfigure the connections and settings of circuit cells inside the LSI may be used.

[0091] Furthermore, as long as the changes do not deviate from the spirit of the present disclosure, various modifications made to the embodiments of the present disclosure within the scope conceivable by a person skilled in the art are also included in the present disclosure. [Industrial Applicability]

[0092] The present disclosure can be applied to a system for controlling the movement of a moving body such as a vehicle. [Explanation of symbols]

[0093] 10, 10a Control system 11 Acquisition Department 12 Detection section 13 Movement prediction section 14, 14a Cost map generation section 15 Route Generation Unit 16, 16a Judgment generator 17 Control Unit 18 Attribute detection section 19 Lane Prediction Section 100, 200 vehicles

Claims

1. An acquisition unit that acquires sensing data output by a sensor that senses the outside of the moving object; a detection unit that detects a position of an object outside the moving body based on the sensing data; a movement prediction unit that predicts a movement of the object based on the sensing data; generating a first cost map based on the detected positions of the objects; a cost map generator that generates a second cost map based on the predicted movement of the object; a route generation unit that generates a route of the moving object based on the first cost map; a determination generating unit that generates a movement determination of the moving object based on the second cost map and the generated route; a control unit that controls the movement of the moving object according to the generated route and the movement determination. Control system.

2. The movement determination includes stopping or slowing down the moving body when an area to which a cost equal to or greater than a predetermined cost is assigned in the second cost map overlaps with the generated route. The control system of claim 1 .

3. The route generation unit generates a route for the moving object based on the second cost map as well.

3. A control system according to claim 1 or 2.

4. The area of ​​the second cost map used to generate a path for the moving body is determined according to an attribute of the object. The control system of claim 3.

5. The area of ​​the second cost map used to generate the route of the moving body is determined according to attributes of a section included in a road on the route of the moving body. A control system according to claim 3 or 4.

6. The attributes of the section include the width of the road. The control system of claim 5.

7. The attributes of the section include, in the case where the road is a road for moving bodies, the width of a sidewalk accompanying the road. A control system according to claim 5 or 6.

8. The attribute of the section includes an intersection on the route of the moving object. A control system according to any one of claims 5 to 7.

9. The attributes of the section include the type of the road. A control system according to any one of claims 5 to 8.

10. The cost map generator further generates a third cost map based on attributes of the detected object; The judgment generating unit generates a movement judgment of the moving body based on the third cost map as well. A control system according to any one of claims 1 to 9.

11. The determination generating unit generates a stop determination of the moving body as the movement determination based on the generated path and the third cost map. The control system of claim 10.

12. Further, a lane prediction unit is provided for predicting a lane along which the moving object is to move, The cost map generator further generates a fourth cost map based on the predicted lanes; The judgment generating unit generates a movement judgment of the moving body based on the fourth cost map as well. A control system according to any one of claims 1 to 11.

13. The determination generating unit generates a deceleration determination of the moving body as the movement determination based on the generated path and the fourth cost map.

13. The control system of claim 12.

14. A control method executed by a computer, comprising: Acquire sensing data output by a sensor that senses the outside of the moving object; Detecting a position of an object outside the moving body based on the sensing data; predicting the movement of the detected object; generating a first cost map based on the detected positions of the objects; generating a second cost map based on the predicted movement of the object; generating a route for the moving object based on the first cost map; generating a movement judgment of the moving object based on the second cost map and the generated route; Controlling the movement of the moving object according to the generated route and the movement decision. Control methods.

Images