Electronic control device and object management method

Abstract

An electronic control device, comprising: an object recognition unit that recognizes surrounding objects on the basis of external information acquired by an external sensor; an obstacle-object-generating unit that generates an obstacle object relating to an object among the recognized objects that blocks observation by the external sensor and generates a blind spot region; and a blind spot object management unit that manages blind spot regions generated by obstacle objects as blind spot objects. The object recognition unit generates solid object information relating to objects among the recognized objects that can enter and exit the blind spot region. The blind spot object management unit associates a solid object that entered the blind spot region with the blind spot object of that blind spot region, and cancels the association with the blind spot object of the blind spot region for a solid object that exited the blind spot region.

Description

Incorporation by Reference

[0001] This application claims the priority of Japanese Patent Application No. 2021-211927, filed on December 27, 2021, and incorporates its content by reference into this application.

Technical Field

[0002] The present invention relates to an electronic control device, and particularly to a technique for managing an object outside the vehicle in an in-vehicle electronic control device.

Background Art

[0003] In autonomous driving and advanced driver assistance, an object outside the vehicle is detected by a sensor to control the vehicle or assist the driver.

[0004] As the background art in this technical field, there are the following patent documents. Patent Document 1 (Japanese Unexamined Patent Application Publication No. 2011-248870) describes a blind spot area detection device mounted on a vehicle that detects a blind spot area representing an area that becomes a blind spot around the host vehicle, the device including: an object information acquisition means for acquiring object information representing the shape including the height of a surrounding object representing an object existing around the host vehicle and the distance to the surrounding object; and a blind spot area detection means for detecting the size of a blind spot area that is an area made blind by the surrounding object based on the acquired object information.

[0005] In addition, Patent Document 2 (Japanese Unexamined Patent Application Publication No. 2020-135215) describes an action control method used in a vehicle equipped with an environment recognition unit that recognizes a driving environment and controls the behavior of the vehicle. The method includes steps of identifying a blind spot area that is a blind spot of the environment recognition unit with respect to a driving route of the vehicle set to include a right or left turn or a lane change in a process executed by at least one processor, determining the possibility of an object emerging from the blind spot area into the driving route, implementing a risk reduction action to transition the possibility to a low state when there is a possibility of emergence from the blind spot area, and implementing the driving behavior of the vehicle according to the driving route after the start of the risk reduction action.

Summary of the Invention

Problems to be Solved by the Invention

[0006] The blind spot area (sometimes referred to as occlusion) caused by an obstacle is on the back side of the obstacle, so the size of the obstacle and the object hidden by the obstacle cannot be detected. Furthermore, it is difficult to estimate the risk inherent in the blind spot area. For example, an object hidden in the shadow of an obstacle may suddenly emerge into the vehicle's path. In addition, it is difficult to accurately estimate the size and shape of a blind spot area that does not include an obstacle that obstructs the observation of an object.

[0007] An object of the present invention is to accurately estimate an object hidden in a blind spot area, further accurately predict the risk caused by the hidden object, and improve the driving safety of a vehicle.

Means for Solving the Problems

[0008] A typical example of the invention disclosed in the present application is as follows. That is, an electronic control device includes an object recognition unit that recognizes surrounding objects based on external information acquired by an external sensor, an obstacle object generation unit that generates an obstacle object related to an object that shields the observation by the external sensor and generates a blind spot area among the recognized objects, a blind spot object management unit that manages the blind spot area generated by the obstacle object as a blind spot object, and a risk calculation unit that calculates a potential risk indicating the driving risk degree of the vehicle using the information of the blind spot object. The object recognition unit generates solid object information related to an object that can enter and exit the blind spot area among the recognized objects. The blind spot object management unit associates a solid object that has entered the blind spot area with the blind spot object of the blind spot area, and releases the association between the solid object that has exited the blind spot area and the blind spot object of the blind spot area. The risk calculation unit The potential risk depends on the density of each type of solid object encapsulated in the blind spot object is characterized by calculating.

Effects of the Invention

[0009] According to one aspect of the present invention, an object hidden in a blind spot area can be accurately predicted. Problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0011] The electronic control device 10 of the embodiment of the present invention detects an obstacle that generates a dead angle area where the observation by the external sensor 32 is obstructed among the observed objects, and manages the solid objects entering and leaving the dead angle area in time series. That is, once an object is recognized, it is continuously managed even if it enters the dead angle area. In addition, the area or volume of the dead angle area is accurately grasped, and virtual solid objects such as pedestrians, motorcycles, and automobiles included in the dead angle area are set according to the shape and size of the dead angle area. Then, according to the number and content of the objects included in the dead angle area, the risk of obstructing the progress of the host vehicle is calculated.

[0012] FIG. 1 is a block diagram showing the logical configuration of the electronic control device 10 of the embodiment of the present invention.

[0013] The electronic control device 10 of this embodiment has an arithmetic device, a storage device, and a communication interface. The arithmetic device is a processor (for example, a CPU) that executes a program stored in the storage device. By executing a predetermined program, the arithmetic device operates as a functional unit that provides various functions. The storage device includes a non-volatile storage area and a volatile storage area. The non-volatile storage area includes a program area for storing programs executed by the arithmetic device and a data area for temporarily storing data used by the arithmetic device during program execution. The volatile storage area stores data used by the arithmetic device during program execution. The communication interface is connected to other electronic control devices via a network such as CAN or Ethernet.

[0014] The electronic control device 10 includes a vehicle position estimation unit 11, an external information acquisition unit 12, an object recognition unit 13, a vehicle information acquisition unit 14, a surrounding map generation unit 15, a map storage unit 16, a communication unit 17, a current surrounding map search unit 18, an obstacle object detection / judgment unit 19, a blind spot detection unit 20, a blind spot object management unit 21, a risk calculation unit 22, a driving behavior planning unit 23, an automatic driving management unit 24, an automatic driving control unit 25, an operation information acquisition unit 26, and a manual / automatic driving switching unit 27.

[0015] Position information 31, external information from an external sensor 32, and vehicle behavior information from a vehicle sensor 33 are input to the electronic control device 10. The position information 31 is position information (latitude / longitude and relative position information) output from a GNSS unit or an inertial navigation unit (not shown). The external sensor 32 is a sensor that observes the state outside the vehicle and outputs external information, and examples thereof include a camera, a radar, and a LiDAR. The vehicle sensor 33 is a sensor that measures the behavior of the vehicle (acceleration, speed, roll, pitch, yaw, etc.). Further, an operation angle from a steering device 34, an operation amount of an accelerator pedal 35, and an operation amount of a brake pedal 36 are input to the electronic control device 10.

[0016] The own vehicle position estimation unit 11 estimates the position of the vehicle from the position information 31 input to the electronic control device 10, the vehicle information output from the vehicle information acquisition unit 14, and the operation information output from the operation information acquisition unit 26. The external information acquisition unit 12 generates surrounding information from the observation results (such as photographed images, point cloud data, etc.) by the external sensor 32. The object recognition unit 13 recognizes the objects included in the surrounding information generated by the external information acquisition unit 12, and generates solid object information representing the recognized objects. The solid object information is a pedestrian, a two-wheeled vehicle, a motor vehicle, a wall, a guardrail, etc. recognized as a result of observation by the external sensor 32, and is a moving object and a fixed object that exist in reality with clear attributes such as volume or bottom area. The solid object information may maintain its attributes even when the solid object moves into the blind spot area or the blind spot area itself deforms due to the change in the relative position between the own vehicle and the obstacle and becomes unobservable. The vehicle information acquisition unit 14 generates vehicle information indicating the state of the vehicle from the vehicle behavior information from the vehicle sensor 33.

[0017] The surrounding map generation unit 15 generates a map of the surroundings of the vehicle from the vehicle position estimated by the own vehicle position estimation unit 11, the surrounding information generated by the external information acquisition unit 12, and the object information generated by the object recognition unit 13. The communication unit 17 communicates wirelessly with a map distribution server (not shown) to acquire map update information or update risk calculation parameters (calculation formulas). The map storage unit 16 stores the surrounding map generated by the surrounding map generation unit 15 and the map acquired from the server via the communication unit 17. The map stored in the map storage unit 16 should have a higher accuracy (for example, an accuracy of about several tens of centimeters) than the map used by the navigation device, and it should be possible to distinguish between the roadway and the sidewalk or distinguish between lanes. It may be a high-precision map for autonomous driving, a map generated from the observation results of the own vehicle, or a map obtained from the map distribution server updated with the surrounding map generated by the surrounding map generation unit 15. The current surrounding map search unit 18 acquires the current map around the position of the vehicle estimated by the own vehicle position estimation unit 11 from the map storage unit 16.

[0018] The obstacle object detection / judgment unit 19 selects an obstacle object that obstructs the observation from the vehicle itself from the surrounding information generated by the external world information acquisition unit 12 and the object information generated by the object recognition unit 13, and generates obstacle object information. The blind spot detection unit 20 calculates a blind spot area where the observation is obstructed from the current map acquired by the current surrounding map search unit 18 and the obstacle object information generated by the obstacle object detection / judgment unit 19, and generates blind spot information. In the first observation result from one direction, since the shape of the obstacle object and the objects in the blind spot area cannot be recognized, it is difficult to accurately estimate the net shape of the blind spot area. At this time, the blind spot detection unit 20 calculates the net blind spot area excluding the area occupied by the obstacle object using the map information of the current position. Also, the net shape of the blind spot area may be accurately estimated by reducing the shape of the obstacle object estimated using multiple observation results and the objects in the blind spot area.

[0019] The blind spot object management unit 21 generates blind spot object information representing the blind spot area from the blind spot information generated by the blind spot detection unit 20, the obstacle object information generated by the obstacle object detection / judgment unit 19, and the solid object information generated by the object recognition unit 13. Details of the blind spot object management unit 21 will be described with reference to FIGS. 2 and 7.

[0020] The blind spot object is an object for continuously managing in time series the blind spot area with an irregular shape caused by an obstacle object that obstructs the observation from the host vehicle. The blind spot object is composed of a polygon in a two-dimensional space and a polygonal prism or polygon in a three-dimensional space, and its configuration differs depending on whether the map used is a two-dimensional map or a three-dimensional map, and its shape changes over time. The blind spot object may be represented by the vertex coordinates of a plane or a solid so that the area can be calculated in a two-dimensional space and the volume can be calculated in a three-dimensional space. The blind spot object is associated with the obstacle object that causes the blind spot area by the corresponding obstacle object 2145 in the blind spot object database 214. The obstacle object that causes the blind spot area is an object (such as a non-moving building or a moving vehicle) observed by the external sensor 32 and recognized by the object recognition unit 13, or an object observed by the external sensor 32 but whose type cannot be recognized by the object recognition unit 13. Any object with a certain shape may be regarded as an obstacle object of unknown type.

[0021] The risk calculation unit 22 calculates the driving risk degree on the driving route from the blind spot object information generated by the blind spot object management unit 21 and generates potential risk information indicating the driving risk degree. That is, since the blind spot object information includes the association with the solid object information and the virtual solid object information included in the blind spot area, a risk value indicating the possibility that the driving of the vehicle may be hindered by these solid objects and virtual solid objects is calculated. For example, the possibility that a pedestrian (solid object) behind a parked vehicle jumps out into the roadway or the possibility that a vehicle (virtual solid object) that may be in the shade of a building comes out into the lane is calculated. For example, the risk value may be calculated according to the density of each type of object included in the blind spot object. Also, at high-risk locations such as entrances and exits and gaps between parked vehicles, the risk value may be increased by multiplying by a predetermined coefficient. Then, the calculated risk value is assigned to each divided area of the map to generate potential risk information.

[0022] The driving action planning unit 23 generates a driving action from the potential risk information generated by the risk calculation unit 22. For example, a low-risk driving action can be generated by selecting an area with a low risk around the vehicle's route. The automatic driving management unit 24 generates a control command for automatic driving and a manual / automatic driving switching signal from the driving action generated by the driving action planning unit 23. The automatic driving control unit 25 generates a steering control signal 37, an acceleration control signal 38, and a deceleration control signal 39 according to the control command generated by the automatic driving management unit 24. The operation information acquisition unit 26 acquires the operation angle from the steering device 34, the operation amount of the accelerator pedal 35, and the operation amount of the brake pedal 36, and generates operation information.

[0023] The manual / automatic driving switching unit 27 switches between manual driving and automatic driving according to the manual / automatic driving switching signal generated by the automatic driving management unit 24. For example, in the case of manual driving, the signal circuit is switched so that the operation information generated from the operation amounts of the steering device 34, the accelerator pedal 35, and the brake pedal 36 is output as the steering control signal 37, the acceleration control signal 38, and the deceleration control signal 39, respectively. On the other hand, in the case of automatic driving, the signal circuit is switched so that the steering control signal 37, the acceleration control signal 38, and the deceleration control signal 39 generated by the automatic driving control unit 25 are output.

[0024] FIG. 2 is a block diagram showing the configuration of the blind spot object management unit 21.

[0025] The blind spot object management unit 21 includes a blind spot object generation unit 211, an obstacle object database 212, a solid object database 213, a blind spot object database 214, and a virtual solid object database 215. Blind spot information is input to the blind spot object management unit 21 from the blind spot detection unit 20, obstacle object information is input from the obstacle object detection / judgment unit 19, and solid object information is input from the object recognition unit 13. Further, the blind spot object management unit 21 outputs blind spot object information.

[0026] The dead angle object generation unit 211 generates dead angle object information using the input dead angle information, obstacle object information, and solid object information, and stores the generated dead angle object information in the dead angle object database 214. The details of the process executed by the dead angle object generation unit 211 will be described with reference to FIG. 7. The obstacle object database 212 is a database in which obstacle objects are registered, and its details will be described with reference to FIG. 3. The solid object database 213 is a database in which solid objects are registered, and its details will be described with reference to FIG. 4. The dead angle object database 214 is a database in which dead angle objects are registered, and its details will be described with reference to FIG. 5. The virtual solid object database 215 is a database in which virtual solid objects are registered, and its details will be described with reference to FIG. 6. A virtual solid object is a virtual moving object that may exist within a dead angle area. For virtual solid objects, the same types (pedestrians, bicycles, automobiles) and attributes as solid objects are defined, as well as the average shape and bottom area or volume for each type.

[0027] FIG. 3 is a diagram showing a configuration example of the obstacle object database 212.

[0028] The obstacle object database 212 is a database in which obstacle objects are registered, and includes data of ID 2121, type 2122, shape 2123, bottom shape 2124, bottom area 2125, volume 2126, state 2127, and TTL 2128.

[0029] ID2121 is identification information for uniquely identifying a failure object. Type 2122 is the type of the failure object, such as an automobile, a structure, etc. Shape 2123 is the shape of the failure object, such as a regular cube, an irregular cube, etc. Bottom surface shape 2124 is the shape of the bottom surface of the failure object. For example, in the case of a regular cube, it is represented by the length and width of the bottom surface, and in the case of an irregular cube, it is represented by the coordinates constituting the bottom surface. Bottom surface area 2125 is the bottom surface area of the failure object, represented in square meters. Volume 2126 is the volume of the failure object, represented in cubic meters. State 2127 is an attribute of the failure object, such as a dynamic object that moves or changes shape, a static object that does not move, etc. TTL (Time to Live) 2128 is a counter value used to organize failure objects detected in the past. When a failure object is detected, an upper limit value is set, and it is subtracted when the failure object is not detected.

[0030] Figure 4 is a diagram showing a configuration example of the solid object database 213.

[0031] The solid object database 213 is a database in which solid objects are registered, and includes data of ID2131, type 2132, bottom surface shape 2133, bottom surface area 2134, volume 2135, and TTL2136.

[0032] ID2131 is identification information for uniquely identifying a solid object. Type 2132 is the type of the solid object, such as a pedestrian, a bicycle, a car, etc. Bottom surface shape 2133 is the shape of the bottom surface of the solid object, and is represented by, for example, the vertical and horizontal sizes of the rectangle occupied by the solid object, or the coordinates constituting the bottom surface. Bottom surface area 2134 is the bottom surface area of the solid object, and is represented in square meters. Volume 2135 is the volume of the solid object, and is represented in cubic meters. TTL (Time to Live) 2136 is a counter value used to sort out solid objects detected in the past. When a solid object is detected, an upper limit value is set, and it is subtracted when the solid object is not detected.

[0033] Figure 5 is a diagram showing a configuration example of the blind spot object database 214.

[0034] The blind spot object database 214 is a database in which blind spot objects are registered, and includes data of ID2141, shape 2142, bottom surface area 2143, volume 2144, corresponding obstacle object 2145, included object 2146, and TTL2147.

[0035] ID2141 is identification information for uniquely identifying a blind spot object. Shape 2142 is the shape of the blind spot object, and is represented by, for example, the vertex coordinates of the solid occupied by the blind spot object. Bottom area 2143 is the bottom area (the size of the blind spot area) of the blind spot object, and is represented in square meters. Volume 2144 is the volume of the blind spot object, and is represented in cubic meters. Corresponding obstacle object 2145 is identification information of an obstacle object that generates a blind spot object, that is, an obstacle object that obstructs the observation of the blind spot area of the blind spot object from the host vehicle. Encapsulated object 2146 is identification information of a virtual solid object encapsulated in the blind spot object. TTL (Time to Live) 2147 is a counter value used to organize blind spot objects detected in the past. When a blind spot object is detected, an upper limit value is set, and when the blind spot object is not detected, it is subtracted.

[0036] Figure 6 is a diagram showing a configuration example of the virtual solid object database 215.

[0037] The virtual solid object database 215 is a database in which virtual solid objects are registered, and includes data of ID2151, type 2152, bottom shape 2153, bottom area 2154, and volume 2155.

[0038] ID2151 is identification information for uniquely identifying a virtual solid object. Type 2152 is the type of the virtual solid object, and is, for example, a pedestrian, a two-wheeled vehicle, an automobile, or the like. Bottom shape 2153 is the shape of the bottom surface of the virtual solid object, and is represented by, for example, the vertical and horizontal sizes of a rectangle occupied by the virtual solid object, or the coordinates constituting the bottom surface. Bottom area 2154 is the bottom area of the virtual solid object, and is represented in square meters. Volume 2155 is the volume of the virtual solid object, and is represented in cubic meters.

[0039] Figure 7 is a flowchart of the blind spot object management process executed by the blind spot object management unit 21, that is, the blind spot object generation unit 211.

[0040] The electronic control device 10 is activated when the vehicle's ignition is on. The blind spot object management unit 21 is activated, and the processes of steps S2 to S6 are repeatedly executed every predetermined time. First, the blind spot object generation unit 211 initializes the obstacle object database 212, the solid object database 213, and the blind spot object database 214 (step S1). For example, all the data recorded in each database is erased.

[0041] Next, the blind spot object generation unit 211 executes preprocessing (step S2). This preprocessing is executed as a pre-stage of the processes after step S3, and may be executed in synchronization with the processes after step S3 or repeatedly executed at independent timings. Specifically, the blind spot object generation unit 211 searches for the surrounding map of the current position and acquires the surrounding map of the current position. Then, the blind spot object generation unit 211 determines an object larger than a predetermined size as an obstacle object from the information of the surrounding objects described in the acquired surrounding map and the object information recognized by the external sensor 32. Also, the blind spot object generation unit 211 determines a solid object from the object recognition result (solid object information) by the object recognition unit 13. Further, the blind spot object generation unit 211 calculates the blind spot area from the current position (observation point) based on the obstacle object information from the obstacle object detection / judgment unit 19 and the blind spot information detected by the blind spot detection unit 20 from the current map.

[0042] Next, the blind spot object generation unit 211 updates the obstacle object database 212 (step S3). Specifically, the blind spot object generation unit 211 records the newly detected obstacle object in the obstacle object database 212 (step S3). If the detected obstacle object is recorded in the obstacle object database 212, the blind spot object generation unit 211 sets the TTL2128 of the corresponding record to the upper limit value.

[0043] Next, the blind spot object generation unit 211 updates the blind spot object database 214 (step S4). Specifically, the blind spot object generation unit 211 searches the obstacle object database 212, extracts obstacle objects that are detected by the blind spot detection unit 20 and generate a blind spot area larger than a predetermined size, and newly registers a record of the blind spot area generated by the obstacle object in the blind spot object database 214.

[0044] Then, as an initial setting of the newly registered blind spot area record, a virtual solid object included in the blind spot object is determined according to the size of the blind spot object. The virtual solid object included in the blind spot object may be determined according to the type and area of the blind spot object. Specifically, the number of virtual solid objects included in a blind spot object per unit area is determined for each type of blind spot object (such as sidewalk, roadway, etc.) and each type of virtual solid object, and the virtual solid objects included can be determined according to the type and area of the registered blind spot object. Also, the virtual solid objects included may be determined according to the number (density) per unit area of the solid objects around the blind spot object. This is because it is presumed that solid objects exist inside the blind spot object at a density similar to that of the surroundings. Furthermore, the virtual solid objects included may be determined according to the shape of the blind spot object. For example, a blind spot object with a width so narrow that a vehicle cannot exist may be determined to include virtual solid objects of pedestrians instead of virtual solid objects of vehicles. Then, the determined virtual solid objects are set in the virtual solid object database 215, and link information associating the blind spot objects and the virtual solid objects is recorded. The density of the virtual solid objects may be changed according to the position of the blind spot objects. For example, by arranging more virtual solid objects in the blind spot objects near high-risk locations such as entrances and exits, gaps between parked vehicles, etc., the risk value of the high-risk locations calculated by the risk calculation unit 22 can be increased.

[0045] In addition, the solid object observed near the blind spot object may enter the blind spot object. Based on the observation results of the external sensor 32, the entry and exit of the blind spot object by the solid object are grasped, and the solid object included in the blind spot area is managed.

[0046] An upper limit may be set for the number of solid objects and virtual solid objects that can be included in the blind spot object to prevent a large number of solid objects from remaining in the blind spot object. When the bottom area or volume of the blind spot object decreases and the total area or total volume of the virtual solid object and the solid object included therein exceeds the bottom area or volume of the blind spot object, the virtual solid object is reduced. By reducing the virtual solid object as the blind spot object becomes smaller, the accuracy of risk prediction can be improved.

[0047] Also, when newly registering a blind spot object, set the TTL 2147 of the blind spot object to the upper limit value. Also, a blind spot object that greatly deviates from the observation range by exceeding a predetermined threshold is unlikely to reappear in the observation range, so it may be deleted. However, if a blind spot object that has deviated from the observation range is maintained for the time until the TTL 2147 becomes zero, even if an obstacle object that generates a blind spot area reappears in the observation range and is re-observed, there is no need to re-register it in the blind spot object database 214. In this case, it is necessary to determine the identity of the blind spot object that has deviated from the observation range and the blind spot object that is re-recognized within the observation range. For this purpose, record the feature amount of the obstacle object associated with the blind spot object in the obstacle object database 212, and compare it with the feature amount of the observed obstacle object to determine whether the observed obstacle object is a newly observed obstacle object or a re-observed obstacle object. Also, a blind spot object that greatly deviates from the range that can be moved within a predetermined time in the traveling direction of the host vehicle (for example, moving backward from the host vehicle) is unlikely to reappear in the observation range, so it may be deleted. Set a lifetime of a predetermined time (for example, 10 seconds) for the blind spot object within the observation range, and delete the blind spot object from the blind spot object database 214 after the lifetime has elapsed since it was first observed. If the observed blind spot object is not recorded in the blind spot object database 214, it may be registered in the blind spot object database 214. In this case, since the blind spot object is refreshed every lifetime, the life and death management by TTL becomes unnecessary.

[0048] Next, the blind spot object generation unit 211 updates the solid object database 213 (step S5). Specifically, when a detected solid object enters a blind spot area that is managed as a blind spot object in the blind spot object database as time elapses, the blind spot object generation unit 211 records link information associating the blind spot object and the virtual solid object in the blind spot object database 214. When a solid object associated with a blind spot object exits the blind spot object, the association (link) between the solid object and the blind spot object is deleted.

[0049] Next, the blind spot object generation unit 211 deletes the obstacle object, the blind spot object, and the solid object (step S6). Specifically, the blind spot object generation unit 211 determines whether an obstacle object is observed. If an obstacle object is observed, it sets the TTL 2128 to the upper limit value. If no obstacle object is observed, it decrements the TTL 2128 by a predetermined value (for example, 1). Further, the blind spot object generation unit 211 deletes an obstacle object whose TTL 2128 has become zero or less from the obstacle object database 212. Then, it deletes the blind spot object associated with the deleted obstacle object from the blind spot object database 214, and deletes the virtual solid object associated with the deleted blind spot object from the virtual solid object database 215. Additionally, the blind spot object generation unit 211 determines whether a solid object is observed. If a solid object is observed, it sets the TTL 2136 to the upper limit value. If no solid object is observed, it decrements the TTL 2136 by a predetermined value (for example, 1). Then, it deletes a solid object whose TTL 2136 has become zero or less from the solid object database 213. Note that since a solid object is not observed while it is included in a blind spot object, the solid object is not deleted even if the TTL reaches the lower limit value.

[0050] In addition, the blind spot object generation unit 211 determines whether an obstacle object that generates a blind spot object is observed. If an obstacle object is observed, the TTL 2147 in the blind spot object database 214 is set to the upper limit value. If no obstacle object is observed, the TTL 2147 is decreased by a predetermined value (for example, 1). Further, the blind spot object generation unit 211 deletes a blind spot object for which the TTL 2147 has become zero or less from the blind spot object database 214. Then, the virtual solid object associated with the deleted blind spot object is deleted from the virtual solid object database 215.

[0051] Note that since the blind spot object generated by the obstacle object disappears due to the disappearance of the obstacle object, it is sufficient to provide a TTL for either the obstacle object or the blind spot object.

[0052] FIG. 8 is a diagram showing an example of an object processed by the electronic control device 10 of the present embodiment.

[0053] When viewed from the host vehicle 81, a blind spot area 83 is generated on the back side of the parked vehicles 82a and 82b. The blind spot area 83 is defined as a range excluding the parked vehicles 82a and 82b that are obstacle objects and the obstacles behind. Also, a solid object (pedestrian) 84a that is about to enter the blind spot area 83 is observed from the host vehicle 81. When the solid object (pedestrian) 84a enters the blind spot area 83, it becomes an included object 84b inside the blind spot object 83, and the association information between the blind spot object 83 and the solid object 84a is recorded in the included object 2146 of the blind spot object database 214. After that, when the included object (pedestrian) 84b exits the blind spot object 83 between the parked vehicles 82a and 82b, the record of the included object 2146, which is the association information between the blind spot object 83 and the included object 84b, is deleted. Since there is a risk of contact with the host vehicle 81 when the included object (pedestrian) 84b exits the blind spot object 83 between the parked vehicles 82a and 82b, an area 85 adjacent to the blind spot object 83 between the parked vehicles 82a and 82b is calculated as a high-risk area.

[0054] Also, a blind spot region 87 is generated in front of the preceding vehicle 86 as viewed from the host vehicle 81. There is a further preceding vehicle 88a in the blind spot region 87, but the preceding vehicle 88a cannot be observed from the host vehicle 81. Therefore, a virtual solid object (preceding vehicle) 88a that may exist within the blind spot object (blind spot region) 87 is generated, and the association information between the blind spot object 87 and the virtual solid object 88a is recorded in the contained object 2146 of the blind spot object database 214. After that, when the virtual solid object 88b changes lanes, it exits from the blind spot region 87 in front of the preceding vehicle 86, and the record of the contained object 2146, which is the association information between the blind spot object 87 and the virtual solid object 88a, is deleted. When the contained object (preceding vehicle) 88b exits the blind spot region 87 caused by the preceding vehicle 86, there is a possibility that a course change of the host vehicle 81 is required, so the adjacent lane region 89 in front of the preceding vehicle 86 is calculated as a high-risk region.

[0055] FIG. 9 is a diagram showing an example of another object processed by the electronic control device 10 of the present embodiment.

[0056] Similar to that described above with reference to FIG. 8, a blind spot region 91 is generated in front of the preceding vehicle 90 as viewed from the host vehicle 81. The blind spot region 91 is defined as a range excluding the obstacle 93 that is an obstacle object. Since the inside of the blind spot object (blind spot region) 91 cannot be observed, a virtual solid object (preceding vehicle) that may exist within the blind spot region 91 is generated, and the association information between the blind spot object 91 and the virtual solid object is recorded in the contained object 2146 of the blind spot object database 214. After that, when the virtual solid object changes lanes, it exits from the blind spot region 91 in front of the preceding vehicle 90, and the record of the contained object 2146, which is the association information between the blind spot object 87 and the virtual solid object 88a, is deleted. When the contained object (preceding vehicle) exits the blind spot region 91 caused by the preceding vehicle 90, there is a possibility that a course change of the host vehicle 81 is required, so the adjacent lane region 92 in front of the preceding vehicle 90 is calculated as a high-risk region.

[0057] Furthermore, buildings on the side of the road become obstacles 93, preventing observation of a side road that intersects from the side at the intersection, resulting in a blind spot area 94. Since the inside of the blind spot object (blind spot area) 94 cannot be observed, a virtual solid object (pedestrian, motorcycle, automobile, etc.) that may exist in the blind spot area 94 is generated, and association information between the blind spot object 94 and the virtual solid object is recorded in the included object 2146 of the blind spot object database 214. After that, when the virtual solid object leaves the blind spot area 94 from the side road, there is a risk of contact with the host vehicle 81, so an area 95 adjacent to the blind spot object 94 is calculated as a high risk area.

[0058] As shown in Figures 8 and 9, a net blind spot area excluding obstacles is defined. In addition, objects entering and exiting the blind spot area are managed as contained objects even if they cannot be observed in the blind spot area, and potential risks are calculated by predicting that the objects will come out of the blind spot objects. In addition, objects that may exist in the blind spot area are managed as virtual solid objects, and potential risks are calculated by predicting that the virtual solid objects will come out of the blind spot objects.

[0059] As described above, the electronic control device 10 of this embodiment includes an object recognition unit 13 that recognizes surrounding objects based on external environment information acquired by an external sensor, an obstacle object generation unit (obstacle object detection / determination unit 19) that generates obstacle objects related to objects that, among the recognized objects, block observation by the external sensor 32 and generate a blind spot area, and a blind spot object management unit 21 that manages the blind spot area generated by the obstacle object as a blind spot object. The object recognition unit 13 generates solid object information related to objects that, among the recognized objects, can enter and exit the blind spot area, and the blind spot object management unit 21 associates a solid object that enters a blind spot area with the blind spot object of the blind spot area and cancels the association of a solid object that leaves the blind spot area with the blind spot object of the blind spot area, so that solid objects that enter and exit the blind spot area can be managed over time.

[0060] In addition, the blind spot object management unit registers the shape of the blind spot area, the size of the blind spot area, the obstacle object that generates the blind spot area, and the solid object that enters and exits the blind spot area in the database to generate a blind spot object, so that the blind spot area can be accurately grasped.

[0061] In addition, since the electronic control device of this embodiment includes a risk calculation unit that calculates a potential risk indicating the driving risk of the vehicle using the blind spot object information, the risk caused by an object hidden in the blind spot area can be accurately predicted, and the driving safety of the vehicle can be improved.

[0062] In addition, since the electronic control device of this embodiment includes a blind spot detection unit that calculates a blind spot area excluding the area occupied by the obstacle object using at least one of the information of the buildings included in the map and the shape of the object recognized by the object recognition unit, the size and shape of the blind spot area that does not include the structure that generates the blind spot area can be accurately grasped, the virtual solid object included in the blind spot area can be estimated, and unnecessary potential risks can be accurately predicted.

[0063] In addition, the blind spot object management unit 21 estimates a virtual solid object included in the blind spot area based on the size and shape of the blind spot area, and manages the estimated virtual solid object in association with the blind spot object of the blind spot area. Therefore, the solid object included in the blind spot area can be estimated, and the potential risk caused by the blind spot area can be predicted. For this reason, the prediction with a low risk of jumping out can be reduced and suppressed within a reasonable range, and the oversensitive judgment and excessive control due to a low-probability prediction or a wrong prediction can be suppressed.

[0064] Note that the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Further, the configuration of another embodiment may be added to the configuration of one embodiment. Also, for a part of the configuration of each embodiment, addition, deletion, or replacement with other configurations may be made.

[0065] In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware, for example, by designing a part or all of them with an integrated circuit, or may be realized in software by a processor interpreting and executing a program that realizes each function.

[0066] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

[0067] Also, the control lines and information lines show those considered necessary for explanation, and do not necessarily show all the control lines and information lines necessary for implementation. In practice, it may be considered that almost all configurations are interconnected.

Claims

1. An electronic control device, comprising: an object recognition unit configured to recognize surrounding objects based on external information acquired by an external sensor; an obstacle object generation unit configured to generate an obstacle object related to an object that shields observations by the external sensor among the recognized objects and generates a dead angle area; a dead angle object management unit configured to manage the dead angle area generated by the obstacle object as a dead angle object; a risk calculation unit configured to calculate a potential risk indicating a driving risk degree of a vehicle using information of the dead angle object, wherein the object recognition unit generates solid object information related to an object that can enter and exit the dead angle area among the recognized objects; the dead angle object management unit associates a solid object that has entered the dead angle area with the dead angle object of the dead angle area, and releases the association between the solid object that has exited the dead angle area and the dead angle object of the dead angle area; the risk calculation unit calculates the potential risk based on the density of each type of solid object included in the dead angle object,

2. The electronic control device according to claim 1, wherein the dead angle object management unit registers the shape of the dead angle area, the size of the dead angle area, the obstacle object that generates the dead angle area, and a solid object that enters and exits the dead angle area in a database, and generates the dead angle object.

3. The electronic control device according to claim 1, further comprising a dead angle detection unit configured to calculate a dead angle area excluding an area occupied by the obstacle object using at least one of information on a building included in a map and the shape of an object recognized by the object recognition unit.

4. The electronic control device according to claim 3, wherein the dead angle object management unit estimates a virtual solid object included in the dead angle area based on the size and shape of the dead angle area, and manages the estimated virtual solid object in association with the dead angle object of the dead angle area.

5. A method for managing an object observed by an electronic control device, wherein the electronic control device includes an arithmetic device that executes a program and a storage device accessible by the arithmetic device, and the method for managing the object includes An object recognition procedure in which the arithmetic unit recognizes surrounding objects based on external information acquired by an external sensor; An obstacle object generation procedure in which the arithmetic unit generates an obstacle object related to an object that blocks observation by the external sensor among the recognized objects to generate a dead angle area; A dead angle object management procedure in which the arithmetic unit manages the dead angle area generated by the obstacle object as a dead angle object; A risk calculation procedure in which the arithmetic unit calculates a potential risk indicating the driving risk of the vehicle using the information of the dead angle object; An object management method including a solid object generation procedure in which the arithmetic unit generates solid object information related to an object that can enter and exit the dead angle area among the recognized objects; In the dead angle object management procedure, the arithmetic unit associates a solid object that has entered the dead angle area with the dead angle object of the dead angle area, and releases the association between the solid object that has exited the dead angle area and the dead angle object of the dead angle area; In the risk calculation procedure, the arithmetic unit calculates the potential risk based on the density of each type of solid object included in the dead angle object.

Images