Surrounding state recognition device, surrounding state recognition method and program

Abstract

To appropriately enhance the safety of an own vehicle when there is a nearby vehicle that can possibly fall a load.SOLUTION: A surrounding state recognition device 15 comprises: a load determination section 3B which determines whether a nearby vehicle positioned around an own vehicle 1 is carrying a load; a behavior calculation section 3C which calculates a parameter indicating a behavior of the nearby vehicle; and a surrounding state recognition section 3D which determines whether it is necessary to make an inter-vehicle distance between the own vehicle and the nearby vehicle equal to or greater than a predetermined value based on the parameter indicating the behavior of the nearby vehicle calculated by the behavior calculation section 3C when the load determination section 3B determines that the surrounding vehicle is carrying a load.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a surrounding situation recognition device, a surrounding situation recognition method, and a program. [Background technology]

[0002] Patent Document 1 describes a technology for determining whether an object is likely to fall from the bed of a surrounding vehicle traveling around a vehicle (host vehicle) or whether an object has fallen, based on the calculation results of one or more of the vibration frequency, amplitude, and size of the object. The technology described in Patent Document 1 requires the host vehicle to approach the surrounding vehicles in order to be able to calculate one or more of the vibration frequency, amplitude, and size of the object. In other words, the technology described in Patent Document 1 requires the host vehicle to approach the surrounding vehicles that may drop the object, which may put occupants of the host vehicle in danger. In order to improve the safety of passengers in one's own vehicle, it is considered necessary to have a technology that ensures a distance between one's own vehicle and surrounding vehicles (neighboring vehicles) that may drop objects, rather than a technology that moves one's own vehicle closer to surrounding vehicles that may drop objects, as in the technology described in Patent Document 1. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-170370 Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology described in Patent Document 1, different modes of driving assistance are performed depending on the determination result of whether there is a possibility that an object will fall from the loading platform of the surrounding vehicle or whether an object has already fallen. As described above, in the technology described in Patent Document 1, since the host vehicle needs to approach the surrounding vehicle, there is a risk that appropriate driving assistance that is beneficial to the occupants of the host vehicle may not be performed.

[0005] In view of the above, the present disclosure aims to provide a surrounding situation recognition device, a surrounding situation recognition method, and a program that can appropriately improve the safety of a vehicle when there is a nearby vehicle that may drop cargo. is. [Means for solving the problem]

[0006] (1) One aspect of the present disclosure is a surrounding situation recognition device that includes a cargo determination unit that determines whether a surrounding vehicle located around the host vehicle is carrying an object; a behavior calculation unit that calculates parameters that represent the behavior of the surrounding vehicle; and a surrounding situation recognition unit that, when the cargo determination unit determines that the surrounding vehicle is carrying the object, determines whether the distance between the surrounding vehicle and the host vehicle needs to be greater than or equal to a predetermined value based on the parameters that represent the behavior of the surrounding vehicle calculated by the behavior calculation unit.

[0007] (2) In the surrounding situation recognition device of (1), the parameters representing the behavior of the surrounding vehicle include the acceleration / deceleration of the surrounding vehicle and the horizontal acceleration of the surrounding vehicle in an image showing the measurement results of a surrounding situation sensor mounted on the host vehicle, and if the cargo determination unit determines that the surrounding vehicle is carrying the object and the acceleration / deceleration of the surrounding vehicle is equal to or greater than a first threshold, the surrounding situation recognition unit may determine that the distance between the surrounding vehicle and the host vehicle needs to be made equal to or greater than the predetermined value, and if the cargo determination unit determines that the surrounding vehicle is carrying the object and the horizontal acceleration of the surrounding vehicle is equal to or greater than a second threshold, the surrounding situation recognition unit may determine that the distance between the surrounding vehicle and the host vehicle needs to be made equal to or greater than the predetermined value.

[0008] (3) The surrounding situation recognition device of (1) or (2) includes a road surface condition estimation unit that estimates the road surface conditions of the road on which the surrounding vehicle and the host vehicle are traveling, and when the cargo determination unit determines that the surrounding vehicle is carrying the object, the surrounding situation recognition unit may determine whether or not the distance between the surrounding vehicle and the host vehicle needs to be greater than a predetermined value based on parameters representing the behavior of the surrounding vehicle calculated by the behavior calculation unit and the road surface conditions estimated by the road surface condition estimation unit.

[0009] (4) One aspect of the present disclosure is a surrounding situation recognition method including a cargo determination step in which a surrounding situation recognition device determines whether a surrounding vehicle located around the host vehicle is carrying an object; a behavior calculation step in which the surrounding situation recognition device calculates parameters representing the behavior of the surrounding vehicle; and a surrounding situation recognition step in which, when the surrounding situation recognition device determines in the cargo determination step that the surrounding vehicle is carrying the object, determines whether the distance between the surrounding vehicle and the host vehicle needs to be greater than a predetermined value based on the parameters representing the behavior of the surrounding vehicle calculated in the behavior calculation step.

[0010] (5) One aspect of the present disclosure is a program for causing a processor to execute a cargo determination step of determining whether a surrounding vehicle located around the host vehicle is carrying an object, a behavior calculation step of calculating parameters representing the behavior of the surrounding vehicle, and a surrounding situation recognition step of determining, if the cargo determination step determines that the surrounding vehicle is carrying the object, whether the distance between the surrounding vehicle and the host vehicle needs to be greater than a predetermined value based on the parameters representing the behavior of the surrounding vehicle calculated in the behavior calculation step. [Effects of the Invention]

[0011] According to the present disclosure, it is possible to appropriately improve the safety of a vehicle when there is a nearby vehicle that may drop a load. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a diagram showing an example of a host vehicle 1 to which a surrounding situation recognition device 15 according to a first embodiment is applied. [Figure 2] 5 is a flowchart illustrating an example of processing executed by a processor 153 of the surrounding situation recognition device 15 according to the first embodiment. [Figure 3] FIG. 10 is a diagram showing an example of a host vehicle 1 to which a surrounding situation recognition device 15 according to a fifth embodiment is applied. [Figure 4] 10 is a flowchart illustrating an example of processing executed by a processor 153 of a surrounding situation recognition device 15 according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of a surrounding situation recognition device, a surrounding situation recognition method, and a program according to the present disclosure will be described with reference to the drawings.

[0014] First Embodiment FIG. 1 is a diagram showing an example of a host vehicle 1 to which a surrounding situation recognition device 15 according to the first embodiment is applied. In the example shown in Figure 1, the vehicle 1 is equipped with a surrounding situation sensor 11, a vehicle state sensor 12, an HMI (Human Machine Interface) 13, a vehicle control device 14, a steering actuator 14A, a braking actuator 14B, a driving actuator 14C, and a surrounding situation recognition device 15. The surrounding situation sensor 11 measures the surrounding situation of the host vehicle 1 (for example, surrounding vehicles located around the host vehicle 1, objects carried on the surrounding vehicles, obstacles located around the host vehicle 1, etc.), and transmits the measurement results of the surrounding situation of the host vehicle 1 to the vehicle control device 14 and the surrounding situation recognition device 15. The surrounding situation sensor 11 includes, for example, a camera, LiDAR (Light Detection And Ranging), etc.

[0015] The vehicle state sensor 12 measures the state of the host vehicle 1 and transmits the measurement results of the state of the host vehicle 1 to the vehicle control device 14 and the surrounding situation recognition device 15. The vehicle state sensor 12 includes, for example, a vehicle speed sensor, an acceleration sensor, a yaw rate sensor, a gyro sensor, and the like. The HMI 13 has a function of accepting various operations by the driver of the vehicle 1, and transmits a signal indicating the operation by the driver of the vehicle 1 to the vehicle control device 14. The vehicle control device 14 controls the steering actuator 14A, the braking actuator 14B, and the drive actuator 14C based on information (data, signals) transmitted from the surroundings sensor 11, the vehicle state sensor 12, and the HMI 13, for example.

[0016] The surrounding situation recognition device 15 is configured by a microcomputer equipped with a communication interface (I / F) 151, a memory 152, and a processor 153. The communication interface 151 has an interface circuit for connecting the surrounding situation recognition device 15 to the surrounding situation sensors 11, the vehicle state sensors 12, the HMI 13, and the vehicle control device 14. The memory 152 stores programs and various data used in the processing executed by the processor 153.

[0017] The processor 153 has a function as an acquisition unit 3A, a function as a loaded object determination unit 3B, a function as a behavior calculation unit 3C, a function as a surrounding situation recognition unit 3D, and a function as a processing unit 3E. The acquisition unit 3A acquires the measurement results of the surrounding situation sensor 11 from the surrounding situation sensor 11. The measurement results of the surrounding situation sensor 11 include, for example, an image including surrounding vehicles and objects carried on those surrounding vehicles captured by a camera serving as the surrounding situation sensor 11, and measurement results (e.g., three-dimensional images) of the surrounding vehicles and objects carried on those surrounding vehicles captured by a LiDAR serving as the surrounding situation sensor 11. The acquisition unit 3A also acquires the measurement results of the vehicle state sensor 12 from the vehicle state sensor 12.

[0018] The loaded object determination unit 3B determines whether or not the surrounding vehicle is carrying an object based on the measurement results of the surrounding condition sensor 11 acquired by the acquisition unit 3A. In detail, the loaded object determination unit 3B determines whether or not the surrounding vehicle is carrying an object based on the measurement results of the surrounding condition sensor 11 by using a model obtained by performing learning using teacher data, which is a data set of measurement results of the surrounding condition sensor mounted on the learning vehicle and labels indicating whether or not the surrounding vehicles (learning surrounding vehicles) located around the learning vehicle that are the measurement targets of the surrounding condition sensor are carrying an object (learning object).

[0019] The behavior calculation unit 3C calculates parameters representing the behavior of the surrounding vehicle based on the measurement results of the surrounding situation sensor 11 and the measurement results of the vehicle state sensor 12 acquired by the acquisition unit 3A. Specifically, the parameters representing the behavior of the surrounding vehicles include the acceleration and deceleration of the surrounding vehicles. The behavior calculation unit 3C calculates the acceleration and deceleration in the forward and backward directions (traveling directions) of the surrounding vehicles relative to the surface of the road on which the surrounding vehicles and the surrounding vehicle 1 are traveling, based on the acceleration and deceleration of the host vehicle 1 indicated by the measurement results of the vehicle state sensor 12 acquired by the acquisition unit 3A and the acceleration and deceleration in the forward and backward directions (traveling directions) of the surrounding vehicles in the image indicating the measurement results of the surrounding situation sensor 11 acquired by the acquisition unit 3A. Furthermore, the parameters representing the behavior of the surrounding vehicle include the acceleration of the surrounding vehicle in the horizontal direction (the direction intersecting the traveling direction), which indicates the steepness of the steering of the surrounding vehicle. Based on the image showing the measurement results of the surrounding situation sensor 11 acquired by the acquisition unit 3A, the behavior calculation unit 3C calculates the acceleration of the surrounding vehicle in the horizontal direction (the direction intersecting the traveling direction) in the image.

[0020] When the cargo determination unit 3B determines that a nearby vehicle is carrying an object, the surrounding situation recognition unit 3D determines whether or not the distance between the nearby vehicle and the vehicle 1 needs to be greater than a predetermined value based on parameters representing the behavior of the nearby vehicle calculated by the behavior calculation unit 3C. Specifically, when the load determination unit 3B determines that the nearby vehicle is carrying an object and the acceleration / deceleration of the nearby vehicle is equal to or greater than a first threshold, the surrounding situation recognition unit 3D determines that the distance between the nearby vehicle and the host vehicle 1 needs to be equal to or greater than a predetermined value. The "predetermined value" is, for example, a distance that can reduce the risk of a collision between the object and the host vehicle 1 even if the object falls from the nearby vehicle into the vicinity of the host vehicle 1. In addition, when the cargo determination unit 3B determines that the surrounding vehicle is carrying an object and the horizontal acceleration of the surrounding vehicle is equal to or greater than a second threshold, the surrounding situation recognition unit 3D determines that the distance between the surrounding vehicle and the vehicle 1 needs to be greater than a predetermined value. 1, the surrounding situation recognition unit 3D determines whether or not the distance between the surrounding vehicle and the host vehicle 1 needs to be equal to or greater than a predetermined value based not only on information indicating whether or not an object that may fall is loaded on the surrounding vehicle but also on the movement (behavior) of the surrounding vehicle carrying the object (i.e., determines whether or not the object is likely to fall from the surrounding vehicle). Therefore, the safety of the host vehicle 1 can be improved more appropriately than with a technique that requires the host vehicle 1 to approach a surrounding vehicle that may drop an object, such as the technique described in Patent Document 1, for example.

[0021] When the surrounding situation recognition unit 3D determines that the distance between the surrounding vehicles and the vehicle 1 needs to be greater than or equal to a predetermined value, the processing unit 3E executes a process to output a warning to the HMI 13 indicating that the distance between the surrounding vehicles and the vehicle 1 needs to be greater than or equal to a predetermined value.

[0022] FIG. 2 is a flowchart illustrating an example of processing executed by the processor 153 of the surrounding situation recognition device 15 according to the first embodiment. 2, in step S10, the acquisition unit 3A acquires the measurement result of the surrounding condition sensor 11 from the surrounding condition sensor 11. The acquisition unit 3A also acquires the measurement result of the vehicle condition sensor 12 from the vehicle condition sensor 12. In step S11, the cargo determination unit 3B determines whether or not the surrounding vehicle is carrying an object based on the measurement result of the surrounding situation sensor 11 acquired in step S10. If YES, the process proceeds to step S12, and if NO, the process shown in FIG. 2 ends. In step S12, the behavior calculation unit 3C calculates parameters representing the behavior of the surrounding vehicle (the longitudinal acceleration / deceleration of the surrounding vehicle relative to the road surface, and the horizontal acceleration of the surrounding vehicle in the image showing the measurement results of the surrounding condition sensor 11) based on the measurement results of the surrounding condition sensor 11 and the measurement results of the vehicle condition sensor 12 acquired in step S10. In step S13, the surrounding situation recognition unit 3D determines whether the acceleration / deceleration in the longitudinal direction of the nearby vehicle relative to the road surface calculated in step S12 is equal to or greater than a first threshold value. If YES, the process proceeds to step S15, and if NO, the process proceeds to step S14. In step S14, the surrounding situation recognition unit 3D determines whether the horizontal acceleration of the surrounding vehicle in the image showing the measurement result of the surrounding situation sensor 11 calculated in step S12 is equal to or greater than a second threshold value. If the determination is YES, the process proceeds to step S15, and if the determination is NO, the process proceeds to step S17. In step S15, the surrounding situation recognition unit 3D determines that the distance between the nearby vehicle and the host vehicle 1 needs to be set to a predetermined value or more. In other words, the surrounding situation recognition unit 3D determines that there is a possibility that an object carried on the nearby vehicle may fall from the nearby vehicle. In step S16, the processing unit 3E executes a process of causing the HMI 13 to output a warning indicating that the distance between the surrounding vehicles and the host vehicle 1 needs to be set to a predetermined value or more. In step S17, the surrounding situation recognition unit 3D determines that it is not necessary to make the distance between the surrounding vehicle and the host vehicle 1 equal to or greater than a predetermined value. In other words, the surrounding situation recognition unit 3D determines that there is no possibility that an object carried on the surrounding vehicle will fall from the surrounding vehicle.

[0023] Second Embodiment The host vehicle 1 to which the surrounding situation recognition device 15 of the second embodiment is applied is configured in the same manner as the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment described above is applied, except for the points described below.

[0024] In the example shown in Figure 1 (an example of a host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment is applied), the vehicle control device 14 does not have an automatic driving function that controls the steering actuator 14A, braking actuator 14B, and drive actuator 14C to cause the host vehicle 1 to travel autonomously without the need for operation by the driver of the host vehicle 1. On the other hand, in an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the second embodiment is applied, the vehicle control device 14 has an automatic driving function that controls the steering actuator 14A, the braking actuator 14B, and the drive actuator 14C to cause the host vehicle 1 to travel autonomously without the need for operation by the driver of the host vehicle 1. Specifically, the vehicle control device 14 generates a travel plan for the host vehicle 1 to reach a destination based on, for example, map information, position information of the host vehicle 1, information indicating the destination of the host vehicle 1, etc. Furthermore, the vehicle control device 14 causes the host vehicle 1 to travel autonomously in accordance with the travel plan. In detail, the vehicle control device 14 causes the host vehicle 1 to travel autonomously while modifying the travel plan based on, for example, measurement results of the surrounding situation sensor 11 so as to avoid collisions between the host vehicle 1 and surrounding vehicles, etc.

[0025] In the example shown in Figure 1 (an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment is applied), as described above, when the surrounding situation recognition unit 3D determines that the distance between the surrounding vehicles and the host vehicle 1 needs to be greater than or equal to a predetermined value (when the surrounding situation recognition unit 3D determines that there is a possibility that an object carried on the surrounding vehicle may fall from the surrounding vehicle), the processing unit 3E executes processing to output a warning to the HMI 13 indicating that the distance between the surrounding vehicles and the host vehicle 1 needs to be greater than or equal to a predetermined value. On the other hand, in an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the second embodiment is applied, if the surrounding situation recognition unit 3D determines that the distance between the surrounding vehicles and the host vehicle 1 needs to be equal to or greater than a predetermined value (if the surrounding situation recognition unit 3D determines that there is a possibility that an object carried on the surrounding vehicle may fall from the surrounding vehicle), the processing unit 3E causes the vehicle control device 14 to modify the driving plan so that the host vehicle 1 can travel safely without a collision between the object and the host vehicle 1, even if the object falls from the surrounding vehicle into the vicinity of the host vehicle 1. The vehicle control device 14 modifies the driving plan in response to an instruction from the processing unit 3E, and causes the host vehicle 1 to travel autonomously according to the modified driving plan. Therefore, in an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the second embodiment is applied, even if the object falls from a nearby vehicle into the vicinity of the host vehicle 1, it is possible to reduce the risk of the object colliding with the host vehicle 1. In detail, it is possible to appropriately improve the safety of the host vehicle 1 based on the movement (behavior) of the nearby vehicle carrying the object, without the need to calculate the vibration frequency, amplitude, size, etc. of the object as in the technology described in Patent Document 1, for example.

[0026] Third Embodiment The host vehicle 1 to which the surrounding situation recognition device 15 of the third embodiment is applied is configured in the same manner as the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment described above is applied, except for the points described below.

[0027] In the example shown in Figure 1 (an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment is applied), the cargo determination unit 3B has a function to determine whether or not the surrounding vehicle is carrying an object, but does not have a function to determine whether or not the object loaded on the surrounding vehicle is in an overloaded state, does not have a function to determine whether or not the object loaded on the surrounding vehicle is in a state where it is protruding from the surrounding vehicle and is loaded on the surrounding vehicle, and does not have a function to determine whether or not the object loaded on the surrounding vehicle is in a state where it is loaded on the surrounding vehicle without being fixed to the surrounding vehicle. On the other hand, in an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the third embodiment is applied, the load determination unit 3B not only has a function of determining whether the surrounding vehicle is carrying an object, but also a function of determining whether the object carried on the surrounding vehicle is overloaded with respect to the surrounding vehicle, a function of determining whether the object carried on the surrounding vehicle is protruding from the surrounding vehicle and is loaded on the surrounding vehicle, and a function of determining whether the object carried on the surrounding vehicle is loaded on the surrounding vehicle without being fastened to the surrounding vehicle. The load determination unit 3B determines whether the object carried on the surrounding vehicle is overloaded with respect to the surrounding vehicle based on the measurement results of the surrounding situation sensor 11 by using a model obtained by learning using training data, which is a data set of measurement results of a surrounding situation sensor mounted on the learning vehicle and labels indicating whether objects (learning objects) carried on surrounding vehicles (learning surrounding vehicles) located around the learning vehicle that are the measurement target of the surrounding situation sensor are overloaded with respect to the learning surrounding vehicle. Furthermore, the loaded object determination unit 3B uses a model obtained by performing learning using teacher data, which is a data set of, for example, measurement results of a surrounding situation sensor mounted on the learning vehicle and a label indicating whether a training object loaded on the surrounding learning vehicle, which is the measurement target of the surrounding situation sensor, is in a state of being loaded on the surrounding learning vehicle protruding from the surrounding learning vehicle, based on the measurement results of the surrounding situation sensor 11. Furthermore, the loaded object determination unit 3B uses a model obtained by performing learning using teacher data, which is a data set of, for example, measurement results of a surrounding situation sensor mounted on the learning vehicle and a label indicating whether a training object loaded on the surrounding learning vehicle, which is the measurement target of the surrounding situation sensor, is in a state of being loaded on the surrounding learning vehicle without being fixed to the surrounding learning vehicle, based on the measurement results of the surrounding situation sensor 11.

[0028] That is, in an example of a host vehicle 1 to which the surrounding situation recognition device 15 of the third embodiment is applied, when the load determination unit 3B determines that a surrounding vehicle is carrying an object, the following cases are included: when the object is overloaded on the surrounding vehicle (determined by the load determination unit 3B) (first case); when the object is protruding from the surrounding vehicle and loaded on the surrounding vehicle (determined by the load determination unit 3B) (second case); when the object is loaded on the surrounding vehicle without being secured to the surrounding vehicle (third case); and when none of the first to third cases apply (fourth case) (when the load determination unit 3B determines that the surrounding vehicle is carrying an object, but determines that the object loaded on the surrounding vehicle is not overloaded on the surrounding vehicle, determines that the object loaded on the surrounding vehicle is not protruding from the surrounding vehicle and loaded on the surrounding vehicle, and determines that the object loaded on the surrounding vehicle is not secured to the surrounding vehicle). In an example of a host vehicle 1 to which the surrounding situation recognition device 15 of the third embodiment is applied, even when the fourth case described above applies, in consideration of the fact that an object loaded on a nearby vehicle may fall depending on the behavior of the nearby vehicle, when an object loaded on a nearby vehicle may fall, a warning is output indicating that the distance between the nearby vehicle and the host vehicle 1 needs to be greater than a predetermined value.

[0029] <Fourth embodiment> The host vehicle 1 to which the surrounding situation recognition device 15 of the fourth embodiment is applied is configured in the same manner as the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment described above is applied, except for the points described below.

[0030] In the example shown in Figure 1 (an example of the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment is applied), as described above, the cargo determination unit 3B determines whether the surrounding vehicle is carrying an object based on the measurement results of the surrounding situation sensor 11 by using a model obtained by learning using training data, which is a data set of measurement results of a surrounding situation sensor mounted on the training vehicle, for example, and labels indicating whether the surrounding vehicles (learning surrounding vehicles) located around the training vehicle that are the measurement target of the surrounding situation sensor are carrying an object (learning object).

[0031] Meanwhile, in one example of the host vehicle 1 to which the surrounding situation recognition device 15 of the fourth embodiment is applied, the load determination unit 3B determines whether or not a surrounding vehicle exists in an image obtained as a measurement result of the surrounding situation sensor 11. The load determination unit 3B determines whether or not a surrounding vehicle exists in an image based on the image obtained as a measurement result of the surrounding situation sensor 11 by using a model obtained by performing learning using teacher data, which is a data set of images (learning images) obtained as a measurement result of the surrounding situation sensor mounted on a learning vehicle and labels indicating whether or not a surrounding vehicle (learning surrounding vehicle) exists in the image. Furthermore, the load determination unit 3B determines whether or not an object different from the surrounding vehicle exists in the vehicle area of ​​the surrounding vehicle in the image obtained as a measurement result of the surrounding condition sensor 11. The load determination unit 3B determines whether or not an object different from the surrounding vehicle exists in the vehicle area of ​​the surrounding vehicle in the image based on the image obtained as a measurement result of the surrounding condition sensor 11 by using a model obtained by performing learning using training data, which is a data set of, for example, an image (learning image) obtained as a measurement result of the surrounding condition sensor mounted on the learning vehicle and a label indicating whether or not an object (learning object) different from the surrounding vehicle (learning surrounding vehicle) exists in the vehicle area of ​​the surrounding vehicle (learning surrounding vehicle) in the image. Furthermore, the load determination unit 3B determines whether or not the relative positional relationship between the surrounding vehicles and the object (an object different from the surrounding vehicles) in the image obtained as a measurement result of the surrounding condition sensor 11 is constant. The load determination unit 3B determines whether or not the relative positional relationship between the surrounding vehicles and the object (an object different from the surrounding vehicles) in the image is constant, based on the image obtained as a measurement result of the surrounding condition sensor 11, by using a model obtained by performing learning using teacher data, which is a data set of, for example, images (learning images) obtained as a measurement result of the surrounding condition sensor mounted on the learning vehicle and labels indicating whether or not the relative positional relationship between the surrounding vehicles (learning surrounding vehicles) and the learning object (learning object different from the learning surrounding vehicles) in the image is constant. In addition, the cargo determination unit 3B determines that a surrounding vehicle is carrying an object when a surrounding vehicle is present in the image as a measurement result of the surrounding condition sensor 11 and an object other than the surrounding vehicle is present in the vehicle area of ​​the surrounding vehicle in the image, and the relative positional relationship between the surrounding vehicle and the object is constant.

[0032] Fifth Embodiment The host vehicle 1 to which the surrounding situation recognition device 15 of the fifth embodiment is applied is configured in the same manner as the host vehicle 1 to which the surrounding situation recognition device 15 of the first embodiment described above is applied, except for the points described below.

[0033] FIG. 3 is a diagram showing an example of a host vehicle 1 to which a surrounding situation recognition device 15 according to the fifth embodiment is applied. In the example shown in Figure 3, the processor 153 has a function as an acquisition unit 3A, a function as a cargo determination unit 3B, a function as a behavior calculation unit 3C, a function as a surrounding situation recognition unit 3D, a function as a processing unit 3E, and a function as a road surface condition estimation unit 3F. The road surface condition estimation unit 3F estimates the road surface conditions of the road on which the surrounding vehicles and the vehicle 1 are traveling based on the measurement results of the surrounding condition sensor 11 acquired by the acquisition unit 3A, and outputs estimated results such as poor road surface conditions (e.g., unpaved roads, roads that have deteriorated over time or have become rough due to disasters, etc.), good road surface conditions, etc. When the cargo determination unit 3B determines that a nearby vehicle is carrying an object, the surrounding situation recognition unit 3D determines whether or not the distance between the nearby vehicle and the vehicle 1 needs to be greater than a predetermined value based on the parameters representing the behavior of the nearby vehicle calculated by the behavior calculation unit 3C and the road surface conditions estimated by the road surface condition estimation unit 3F.

[0034] FIG. 4 is a flowchart illustrating an example of processing executed by the processor 153 of the surrounding situation recognition device 15 according to the fifth embodiment. 4, in step S20, the acquisition unit 3A acquires the measurement result of the surrounding condition sensor 11 from the surrounding condition sensor 11. The acquisition unit 3A also acquires the measurement result of the vehicle condition sensor 12 from the vehicle condition sensor 12. In step S21, the cargo determination unit 3B determines whether or not the surrounding vehicle is carrying an object based on the measurement result of the surrounding situation sensor 11 acquired in step S10. If YES, the process proceeds to step S22, and if NO, the process shown in FIG. 4 is terminated. In step S22, the behavior calculation unit 3C calculates parameters representing the behavior of the surrounding vehicle (the longitudinal acceleration / deceleration of the surrounding vehicle relative to the road surface, and the horizontal acceleration of the surrounding vehicle in the image showing the measurement results of the surrounding condition sensor 11) based on the measurement results of the surrounding condition sensor 11 and the measurement results of the vehicle condition sensor 12 acquired in step S20. In step S23, the road surface condition estimation unit 3F estimates the road surface conditions of the surrounding vehicles and the road on which the host vehicle 1 is traveling, based on the measurement results of the surrounding condition sensor 11 acquired in step S20.

[0035] In step S24, the surrounding situation recognition unit 3D determines whether the acceleration / deceleration in the longitudinal direction of the nearby vehicle relative to the road surface calculated in step S22 is equal to or greater than a first threshold value. If YES, the process proceeds to step S27, and if NO, the process proceeds to step S25. In step S25, the surrounding situation recognition unit 3D determines whether the horizontal acceleration of the surrounding vehicle in the image showing the measurement result of the surrounding situation sensor 11 calculated in step S22 is equal to or greater than a second threshold value. If the determination is YES, the process proceeds to step S27, and if the determination is NO, the process proceeds to step S26. In step S26, the surrounding situation recognition unit 3D determines, based on the estimation result in step S23, whether the road surface conditions of the road on which the surrounding vehicles and the host vehicle 1 are traveling are poor. If YES, the process proceeds to step S27, and if NO, the process proceeds to step S29.

[0036] In step S27, the surrounding situation recognition unit 3D determines that the distance between the surrounding vehicle and the host vehicle 1 needs to be set to a predetermined value or more. In other words, the surrounding situation recognition unit 3D determines that there is a possibility that an object carried on the surrounding vehicle may fall from the surrounding vehicle. In step S28, the processing unit 3E executes a process of causing the HMI 13 to output a warning indicating that the distance between the surrounding vehicle and the host vehicle 1 needs to be set to a predetermined value or more. In step S29, the surrounding situation recognition unit 3D determines that it is not necessary to make the distance between the surrounding vehicle and the host vehicle 1 equal to or greater than a predetermined value. In other words, the surrounding situation recognition unit 3D determines that there is no possibility that an object carried on the surrounding vehicle will fall from the surrounding vehicle.

[0037] As described above, embodiments of the surrounding situation recognition device, the surrounding situation recognition method, and the program of the present disclosure have been described with reference to the drawings. However, the surrounding situation recognition device, the surrounding situation recognition method, and the program of the present disclosure are not limited to the above-described embodiments, and appropriate modifications may be made without departing from the spirit of the present disclosure. The configurations of the above-described embodiments may be combined as appropriate. In the above-described embodiments, the processing performed by the surrounding situation recognition device 15 has been described as software processing performed by executing a program. However, the processing performed by the surrounding situation recognition device 15 may be processing performed by hardware. Alternatively, the processing performed by the surrounding situation recognition device 15 may be processing that combines both software and hardware. Furthermore, the program stored in the memory 152 of the surrounding situation recognition device 15 (a program that realizes the functions of the processor 153 of the surrounding situation recognition device 15) may be recorded on a computer-readable storage medium such as a semiconductor memory, a magnetic recording medium, an optical recording medium, etc., and provided, distributed, etc. [Explanation of symbols]

[0038] 1... host vehicle, 11... surrounding condition sensor, 12... vehicle state sensor, 13... HMI, 14... vehicle control device, 14A... steering actuator, 14B... braking actuator, 14C... driving actuator, 15... surrounding condition recognition device, 151... communication interface, 152... memory, 153... processor, 3A... acquisition unit, 3B... load determination unit, 3C... behavior calculation unit, 3D... surrounding condition recognition unit, 3E... processing unit, 3F... road surface condition estimation unit

Claims

1. a loaded object determination unit that determines whether a nearby vehicle located around the host vehicle is loaded with an object; a behavior calculation unit that calculates parameters representing the behavior of the surrounding vehicle; a surrounding situation recognition unit that, when the cargo determination unit determines that the surrounding vehicle is carrying the object, determines whether or not the distance between the surrounding vehicle and the host vehicle needs to be made greater than a predetermined value based on parameters representing the behavior of the surrounding vehicle calculated by the behavior calculation unit.

2. the parameters representing the behavior of the surrounding vehicle include an acceleration / deceleration of the surrounding vehicle and a horizontal acceleration of the surrounding vehicle in an image showing a measurement result of a surrounding condition sensor mounted on the host vehicle; when the load determination unit determines that the nearby vehicle is carrying the object and when the acceleration / deceleration of the nearby vehicle is equal to or greater than a first threshold, the surrounding situation recognition unit determines that the distance between the nearby vehicle and the host vehicle needs to be set to the predetermined value or greater; 2. The surrounding situation recognition device according to claim 1, wherein when the cargo determination unit determines that the surrounding vehicle is carrying the object and the horizontal acceleration of the surrounding vehicle is equal to or greater than a second threshold, the surrounding situation recognition unit determines that the distance between the surrounding vehicle and the host vehicle needs to be equal to or greater than the predetermined value.

3. a road surface condition estimation unit that estimates road surface conditions of a road on which the surrounding vehicles and the host vehicle are traveling, 2. The surrounding situation recognition device according to claim 1, wherein, when the cargo determination unit determines that the surrounding vehicle is carrying the object, the surrounding situation recognition unit determines whether or not it is necessary to make the distance between the surrounding vehicle and the host vehicle greater than or equal to a predetermined value, based on parameters representing the behavior of the surrounding vehicle calculated by the behavior calculation unit and the road surface conditions estimated by the road surface condition estimation unit.

4. a load determination step in which the surrounding situation recognition device determines whether a nearby vehicle located around the host vehicle is carrying an object; a behavior calculation step in which the surrounding situation recognition device calculates parameters representing the behavior of the surrounding vehicle; a surrounding situation recognition step in which, when the surrounding situation recognition device determines in the load determination step that the surrounding vehicle is carrying the object, it determines whether or not the distance between the surrounding vehicle and the vehicle itself needs to be greater than a predetermined value based on parameters representing the behavior of the surrounding vehicle calculated in the behavior calculation step.

5. The processor a loaded object determination step of determining whether or not a nearby vehicle located around the host vehicle is loaded with an object; a behavior calculation step of calculating parameters representing the behavior of the surrounding vehicle; A program for executing a surrounding situation recognition step that, when it is determined in the cargo determination step that the surrounding vehicle is carrying the object, determines whether or not the distance between the surrounding vehicle and the vehicle itself needs to be greater than a predetermined value based on parameters representing the behavior of the surrounding vehicle calculated in the behavior calculation step.

Images