Traction state determination device vehicle

Abstract

To provide a traction state determination device for a vehicle, which can determine whether an own vehicle is being towed without receiving information from the outside.SOLUTION: A processor 162 of an ECU 160 comprises: a preceding vehicle recognition unit 162b that recognizes a preceding vehicle from an image obtained by imaging the surroundings of an oven vehicle; a distance estimation unit 162c that estimates a relative distance between the preceding vehicle and the own vehicle; and a traction state determination unit 162d that determines a state where the own vehicle is being towed by the preceding vehicle when a state where the relative distance is equal to or smaller than a prescribed distance continues for a prescribed time or more.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a towing state determination device for a vehicle. [Background technology]

[0002] It is conventionally known to determine whether a vehicle is being towed by receiving and evaluating driving state information from a preceding vehicle (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2018 / 179345 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in the above patent documents requires a wired or wireless information transmission means to receive driving status information from the preceding vehicle, and there is a problem that the towed vehicle alone cannot determine whether or not its own vehicle is being towed. Also, if the towed vehicle is unable to receive driving status information from the preceding vehicle due to communication failure, an accident, or other factors, it will be unable to determine whether or not its own vehicle is being towed.

[0005] In view of the above problems, an object of the present disclosure is to provide a vehicle towing state determination device that can determine whether or not the host vehicle is being towed without receiving information from an external source. [Means for solving the problem]

[0006] The gist of the present disclosure is as follows.

[0007] (1) a preceding vehicle recognition unit that recognizes a preceding vehicle from an image captured around the host vehicle; a distance estimation unit that estimates a relative distance between the preceding vehicle and the host vehicle; a towing state determination unit that determines that the host vehicle is being towed by the preceding vehicle when the state in which the relative distance is equal to or shorter than a predetermined distance continues for a predetermined time or more; A vehicle towing state determination device comprising: Effect of the Invention

[0008] According to the present disclosure, a vehicle towing state determination device is provided that is capable of determining whether or not the vehicle is being towed without receiving information from an external source. [Brief description of the drawings]

[0009] [Figure 1] 1 is a schematic diagram illustrating a vehicle according to an embodiment of the present disclosure being towed by a towing vehicle. FIG. [Diagram 2] 1 is a schematic diagram showing a configuration of a vehicle control system mounted on a vehicle. [Diagram 3] FIG. 2 is a schematic diagram showing functional blocks of a processor of an ECU provided in a vehicle. [Figure 4] 5 is a schematic diagram for explaining a determination process performed by a towing state determination unit; FIG. [Diagram 5] 4 is a flowchart showing a process performed by a processor of the ECU. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, some embodiments of the present invention will be described with reference to the drawings. However, these descriptions are intended to merely exemplify preferred embodiments of the present invention, and are not intended to limit the present invention to such specific embodiments. In the following description, similar components are given the same reference numerals.

[0011] 1 is a schematic diagram showing a state in which a vehicle 10 according to an embodiment of the present disclosure is towed by a towing vehicle 20. Among several methods for towing the vehicle 10, in a method in which the vehicle is towed with all four wheels on the ground (flat towing), the vehicle is towed with the shift position in neutral to prevent damage to the transmission of the vehicle 10. In this case, depending on the specifications of the vehicle 10, for example, in the case of a steer-by-wire vehicle in which the steering is electronically controlled, the vehicle power needs to be turned on during towing to unlock the steering.

[0012] On the other hand, if the power of the vehicle 10 is turned on during towing, normal vehicle control may be erroneously performed even while the vehicle is being towed. For example, the control of a driving assistance system that recognizes the situation around the vehicle and avoids collisions is unnecessary during towing, and it is desirable not to perform this control during towing.

[0013] In this embodiment, the vehicle 10 being towed recognizes the towing vehicle 20 from an image captured by the onboard camera 105 and determines that the vehicle itself is being towed. This makes it possible to determine the towing state without receiving information from an external source. In addition, it is possible to determine the towing state without providing an additional user interface for determining the towing state (for example, a switch for setting that the vehicle 10 is in a towing state), and erroneous operation of these user interfaces by the occupants is reliably suppressed.

[0014] When the vehicle 10 determines that the vehicle is being towed, it performs vehicle control different from that performed during normal driving, and does not perform some of the controls that are performed during normal driving. This prevents normal vehicle control from being erroneously activated while the vehicle is being towed.

[0015] 2 is a schematic diagram showing the configuration of a vehicle control system 100 mounted on a vehicle 10. The vehicle control system includes an in-vehicle camera 105, a positioning information receiver 110, a vehicle control device 120, a wireless terminal 130, one or more sensors 140, a navigation device 150, an electronic control unit (ECU: Electronic Control Unit, hereinafter referred to as ECU) 160, a display device 170, and a speaker 180. These components are connected to each other so as to be able to communicate with each other via an in-vehicle network.

[0016] The vehicle-mounted camera 105 has a two-dimensional detector configured with an array of photoelectric conversion elements, such as a CCD or a C-MOS, that are sensitive to visible light, and an imaging optical system that forms an image of an area to be photographed on the two-dimensional detector. The vehicle-mounted camera 105 is provided on a dashboard or near a windshield inside the vehicle, and captures an image of the surroundings of the vehicle 10 at a predetermined photographing period (for example, 1 / 30 to 1 / 10 seconds) to generate an image representing the surroundings of the vehicle 10. Specifically, the vehicle-mounted camera 105 captures an image in front of the vehicle, as shown in FIG. 1. The image obtained by the vehicle-mounted camera 105 is preferably a color image. The vehicle-mounted camera 105 may also be configured with a stereo camera. Every time the vehicle-mounted camera 105 generates an image, it outputs the generated image to the ECU 160 via the in-vehicle network.

[0017] The positioning information receiver 110 acquires positioning information that indicates the current position and attitude of the vehicle 10. For example, the positioning information receiver 110 may be a GPS (Global Positioning System) receiver. Every time the positioning information receiver 110 receives positioning information, the positioning information receiver 110 outputs the acquired positioning information to the ECU 160 via the in-vehicle network.

[0018] The vehicle control device 120 is various devices related to vehicle control, and includes an engine 120a and a motor 120b as drive sources for driving the vehicle 10, and a battery 120c for storing electric power. The vehicle control device 120 also includes a steering device and a braking device. Note that FIG. 1 illustrates a case where the vehicle 10 is a PHV, and if the vehicle 10 is an EV, the vehicle control device 120 does not include the engine 120a. Also, if the vehicle is an engine vehicle, the vehicle control device 120 does not need to include the motor 120b.

[0019] The wireless terminal 130 communicates with the outside world by using a wireless communication network such as 4G, 5G, etc. The one or more sensors 140 include sensors for monitoring the periphery of the vehicle 10, such as a Lidar (Light Detection and Ranging) sensor, a Radar sensor, etc.

[0020] The navigation device 150 determines a planned driving route from the current location of the vehicle 10 to the destination according to a predetermined route search method such as the Dijkstra algorithm. For this reason, the navigation device 150 includes a memory for storing map information.

[0021] The ECU 160 includes a processor 162, a memory 164, and a communication interface 166. The processor 162 includes one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 162 may further include other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The processor 162 provides functions that meet a predetermined purpose by executing a computer program that is executablely deployed in a working area of ​​the memory 164. The memory 164 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. Various types of information are stored in the memory 164. The communication interface 166 includes an interface circuit for connecting the ECU 160 to an in-vehicle network.

[0022] The display device 170 is configured, for example, by a liquid crystal display (LCD), and is provided near the meter panel or dashboard to display various information. The speaker 180 outputs various information by voice.

[0023] FIG. 3 is a schematic diagram showing functional blocks of the processor 162 of the ECU 160 provided in the vehicle 10. The processor 162 is one aspect of a towing state determination device for a vehicle, and includes an image acquisition unit 162a, a preceding vehicle recognition unit 162b, a distance estimation unit 162c, a towing state determination unit 162d, and a vehicle control unit 162e. Each of these units in the processor 162 is a functional module realized by, for example, a computer program that runs on the processor 162. That is, each of these units in the processor 162 is composed of the processor 162 and a program (software) for making the processor 162 function. The program may be recorded in the memory 164 of the ECU 160 or a recording medium connected from the outside. Alternatively, each of these units in the processor 162 may be a dedicated arithmetic circuit provided in the processor 162.

[0024] The image acquisition unit 162a acquires an image of the surroundings of the vehicle, that is, an image captured and generated by the in-vehicle camera 105. The preceding vehicle recognition unit 162b recognizes the preceding vehicle from the image acquired by the image acquisition unit 162a. At this time, the preceding vehicle is recognized from the image, for example, by template matching between a template image showing the vehicle and the image acquired by the image acquisition unit 162a, or by inputting the image acquired by the image acquisition unit 162a to a classifier trained by machine learning for vehicle detection.

[0025] The preceding vehicle recognition unit 162b may use, as the above-mentioned classifier, a classifier for segmentation that is pre-trained to output, for each pixel of an input image, the likelihood that an object is represented by that pixel for each type of object that may be represented by that pixel, and to classify the object with the maximum likelihood as being represented. The preceding vehicle recognition unit 162b may use, as such a classifier, a deep neural network (DNN) having a convolutional neural network type (CNN) architecture for segmentation, such as a fully convolutional network (FCN). The preceding vehicle recognition unit 162b may recognize the preceding vehicle by using, as supplemental information, information unique to towing, such as the tail lamp or license plate of the towing vehicle 20 obtained from the image and the scenery flowing around the towing vehicle 20.

[0026] The distance estimation unit 162c estimates the relative distance between the preceding vehicle recognized by the preceding vehicle recognition unit 162b and the vehicle itself. For example, when the vehicle-mounted camera 105 is a stereo camera, the distance estimation unit 162c estimates the distance to the preceding vehicle on the image from the parallax between the left and right images, and estimates the relative distance between the preceding vehicle and the vehicle itself. Also, for example, the distance estimation unit 162c estimates the relative distance between the preceding vehicle and the vehicle itself from the output value of a sensor such as a lidar or radar.

[0027] The towing state determination unit 162d determines that the vehicle is in a towing state when the preconditions for determining the towing state are met. The preconditions are that the transmission shift lever is continuously in the neutral range while the vehicle 10 is running, that there is no passenger present, and other conditions that do not occur during normal running continue to exist.

[0028] The towing state determination unit 162d determines that the host vehicle is being towed by the preceding vehicle when the state in which the relative distance between the same preceding vehicle and the host vehicle remains below a predetermined distance for a predetermined period of time or more. FIG. 4 is a schematic diagram for explaining the determination process by the towing state determination unit 162d. In FIG. 4, the horizontal axis indicates time, and the vertical axis indicates the towing state duration time T. When the precondition is met at time t0 and the relative distance between the preceding vehicle and the host vehicle falls below the predetermined distance, counting up of the towing state duration time T begins. Then, at time t1, the towing state duration time T reaches the towing determination threshold value T. th When the relative distance between the preceding vehicle and the host vehicle reaches time t2, the towing state determination unit 162d determines that the host vehicle is being towed by the preceding vehicle. On the other hand, when the precondition is cleared or the relative distance exceeds a predetermined distance at time t2, the towing state duration time T is reset to 0. As shown by the dashed dotted line in Figure 4, when the precondition is met and the relative distance between the preceding vehicle and the host vehicle becomes equal to or shorter than the predetermined distance, counting up the towing state duration time T begins again.

[0029] When it is determined that the host vehicle is being towed by the preceding vehicle, the vehicle control unit 162e performs vehicle control different from that during normal driving. For example, the vehicle control unit 162e may turn off the control (acceleration, braking, steering) by the driving assistance system that is turned on during normal driving, and may also turn off the calibration of the in-vehicle camera 105. The vehicle control unit 162e may also control the lights to be automatically turned on in order to alert the surroundings that the host vehicle is being towed. The vehicle control unit 162e may also operate the braking device of the vehicle control device 120 when the inter-vehicle distance between the host vehicle and the towing vehicle 20 becomes closer than a predetermined threshold value, so that the host vehicle does not collide with the towing vehicle 20 from the rear. The vehicle control unit 162e may also control the braking device so that the vehicle speed detected by the vehicle speed sensor or the vehicle speed estimated from the image captured by the in-vehicle camera 105 does not exceed a predetermined speed. The vehicle control unit 162e may also turn off the power of the navigation device 150 or accessories (air conditioner, display device 170, speaker 180, audio device, etc.) that are turned on during normal driving. The vehicle control unit 162e may also predict that the towing vehicle 20 will decelerate based on the display of traffic lights around the vehicle 10 or the presence of pedestrians around the vehicle 10, which are obtained from images generated by the in-vehicle camera 105, and control the braking device based on the prediction, thereby preventing the vehicle 10 from colliding with the towing vehicle 20 from behind. The vehicle control unit 162e may also control the steering device so that the vehicle follows the towing vehicle 20, based on the lateral position of the towing vehicle 20, which is obtained from images generated by the in-vehicle camera 105.

[0030] 5 is a flowchart showing the process performed by the processor 162 of the ECU 160. First, a precondition is verified (step S10). If the precondition is met (YES in step S12), the preceding vehicle recognition unit 162b recognizes a preceding vehicle (step S14).

[0031] Next, the distance estimation unit 162c estimates the relative distance L between the preceding vehicle and the vehicle itself (step S16). thIt is determined whether the relative distance L is equal to or smaller than the predetermined distance L (step S18). th In the following cases (YES in step S18), the time T that the preceding vehicle travels in front of the host vehicle, that is, the towing state duration T, is measured (step S20).

[0032] Next, the towing state duration T is set to the towing judgment threshold T th It is determined whether the towing state duration T is equal to or greater than the towing determination threshold T (step S22). th In the above cases (YES in step S22), the towing state determination unit 162d determines that the host vehicle is being towed by the preceding vehicle (step S24). Next, the vehicle control unit 162e performs vehicle control different from that during normal driving (step S26).

[0033] On the other hand, if the precondition is not satisfied in step S12, the relative distance L is set to the predetermined distance L th If the time T exceeds the predetermined time T th If it is less than this, it is not determined that the host vehicle is being towed by the preceding vehicle. [Explanation of symbols]

[0034] 162 processors 162a Image acquisition section 162b Leading vehicle recognition unit 162c Distance estimation part 162d Towing state determination unit 162e Vehicle control unit

Claims

[Claim 1] a preceding vehicle recognition unit that recognizes a preceding vehicle from an image captured around the host vehicle; a distance estimation unit that estimates a relative distance between the preceding vehicle and the host vehicle; a towing state determination unit that determines that the host vehicle is being towed by the preceding vehicle when the state in which the relative distance is equal to or shorter than a predetermined distance continues for a predetermined period of time or more; A vehicle towing state determination device comprising:

Images