Failure detection device

Abstract

To provide an obstacle detection device capable of detecting an obstacle on a road with high accuracy.SOLUTION: An obstacle detection device includes: an acquisition unit which acquires behavior data indicating a behavior of a vehicle, position information indicating a position of the vehicle, and vehicle speed information indicating a speed of the vehicle from a plurality of vehicles traveling on a road in a predetermined direction; an identification unit which identifies an avoidance behavior of the vehicle for avoiding an object on a path on the basis of the behavior data; a detection unit which detects, on the basis of the position information, a position on the road at which the frequency at which the avoidance behavior is identified by the identification unit is equal to or higher than a threshold value; and a determination unit which determines whether the occurrence frequency of the avoidance behavior is equal to or higher than the threshold value. A fault detection device includes: a determination unit which determines whether or not the distribution of the speed of a vehicle in a predetermined direction of a position detected by a detection unit shows a bimodal distribution on the basis of vehicle speed information; and a detection unit which does not detect the occurrence of a fault at the position detected by the detection unit when the determination unit determines that the distribution shows the bimodal distribution and detects the occurrence of a fault at the position detected by the detection unit when the determination unit determines that the distribution does not show the bimodal distribution.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a fault detection device. [Background technology]

[0002] Regarding technology for detecting obstacles on roads, for example, Patent Document 1 describes a technology for detecting obstacles by determining whether or not a vehicle is behaving in a way to avoid an obstacle on the road, based on data showing the behavior of multiple vehicles while they are traveling. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2024-88500 A Summary of the Invention [Problem to be solved by the invention]

[0004] According to the above-mentioned method, there is a risk of false detection of a fault by determining behavior such as changing lanes to avoid congestion at the exit of a highway or the entrance to a service area.

[0005] SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned problems, and has as its object to provide an obstacle detection device that can detect obstacles on the road with high accuracy. [Means for solving the problem]

[0006] The obstacle detection device of the present invention comprises an acquisition unit that acquires, from each of a plurality of vehicles traveling on a road in a predetermined direction, behavior data indicating the behavior of the vehicle, position information indicating the position of the vehicle, and vehicle speed information indicating the speed of the vehicle; a recognition unit that identifies, based on the behavior data, an avoidance behavior in which the vehicle avoids an object on the path of the vehicle; a detection unit that detects, based on the position information, positions on the road where the frequency at which the avoidance behavior has been identified by the recognition unit is equal to or greater than a threshold; a determination unit that determines, based on the vehicle speed information, whether the distribution of the vehicle's speeds on the predetermined direction side of the position detected by the detection unit is bimodal; and a detection unit that, if the determination unit determines that the distribution is bimodal, does not detect the occurrence of an obstacle at the position detected by the detection unit, and, if the determination unit determines that the distribution does not show bimodal, detects the occurrence of an obstacle at the position detected by the detection unit. [Effects of the Invention]

[0007] According to the present invention, obstacles on the road can be detected with high accuracy. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a configuration diagram showing an example of a failure detection system. [Figure 2] FIG. 2(a) is a diagram showing an example of vehicle behavior and speed distribution information when an obstacle occurs on the road, and FIG. 2(b) is a diagram showing an example of vehicle behavior and speed distribution information when no obstacle occurs on the road. [Figure 3] FIG. 3 is a flowchart showing an example of the operation of the failure detection server. DETAILED DESCRIPTION OF THE INVENTION

[0009] (Configuration of the fault detection system) 1 is a configuration diagram showing an example of a fault detection system S. The fault detection system S includes a fault detection server 1 and a plurality of in-vehicle devices 2.

[0010] The in-vehicle device 2 is mounted on a vehicle such as a hybrid vehicle, an electric vehicle, etc. The in-vehicle device 2 includes a data communication module (DCM) 20, a yawing sensor 21, a vehicle speed sensor 22, and a GPS (Global Positioning System) 23.

[0011] The yaw sensor 21 detects the yaw rate, which is the angular acceleration of the vehicle in the yaw direction. The vehicle speed sensor 22 detects the speed of the vehicle. The GPS 3 detects the latitude and longitude of the vehicle.

[0012] The DCM 5 is connected to a communication network (not shown) such as the Internet by wireless communication means. The DCM 5 transmits the detected values ​​of the yaw sensor 21, the vehicle speed sensor 22, and the GPS 23 to the failure detection server 1.

[0013] The failure detection server 1 is an example of a failure detection device. The failure detection server 1 includes a CPU (Central Processing Unit) 10, a ROM (Read Only Memory) 11, a RAM (Random Access Memory) 12, an SSD (Solid State Drive) 13, and a communication port 14, all of which are connected to one another via a bus 19.

[0014] The ROM 11 stores a program that drives the CPU 10. The RAM 12 functions as a working memory for the CPU 10. The communication port 14 is connected to a communication network.

[0015] When the CPU 10 reads a program from the ROM 11, it forms, as software functions, a control unit 100, an acquisition unit 101, an identification unit 102, a detection unit 103, a determination unit 104, and a detection unit 105. In addition, the SSD 13 stores behavior data 130, position information 131, vehicle speed information 132, and speed distribution information 133. The control unit 100 instructs the acquisition unit 101, the identification unit 102, the detection unit 103, the determination unit 104, and the detection unit 105 to operate in accordance with the program sequence.

[0016] The acquisition unit 101 acquires behavior data 130 indicating the behavior of each vehicle, location information 131 indicating the location of each vehicle, and vehicle speed information 132 indicating the speed of each vehicle from each of a plurality of vehicles traveling on a road in a predetermined traveling direction. The behavior data 130, location information 131, and vehicle speed information 132 are acquired from the yawing sensor 21, the GPS 23, and the vehicle speed sensor 22, respectively.

[0017] The identification unit 102 identifies avoidance behaviors by which the vehicle avoids an object on its path based on the behavior data 130. The identification unit 102 identifies, for example, a course change or lane change as an avoidance behavior based on the time change of each acceleration of yawing.

[0018] The detection unit 103 detects positions on a road where the frequency at which the avoidance behavior is identified by the identification unit 102 is equal to or greater than a threshold, based on the position information 131. For example, the detection unit 103 stores the number of times the avoidance behavior is detected within a predetermined time period in association with the position information 131.

[0019] The determination unit 104 determines whether or not the distribution of the speeds of vehicles on the road in the traveling direction of the position detected by the detection unit 103 exhibits bimodalities based on the vehicle speed information 132. For example, the determination unit 104 generates speed distribution information 133 indicating the distribution of the speeds of vehicles that have passed through each road section within a predetermined time, for example, from the vehicle speed information 132 and the position information 131, and determines whether or not bimodalities exist from the speed distribution information 133.

[0020] If the determination unit 104 determines that the speed distribution exhibits bimodality, the detection unit 105 does not detect the occurrence of an obstacle at the position detected by the detection unit 103 (detection position), and if the determination unit 104 determines that the speed distribution does not exhibit bimodality, the detection unit 105 detects the occurrence of an obstacle at the detection position.

[0021] (Example of fault detection) 2(a) is a diagram showing an example of the behavior and speed distribution information 133 of vehicles V, Vx when an obstacle occurs on road R. Road R has two lanes, L1 and L2, and multiple vehicles V, Vx are traveling in a traveling direction D. Each vehicle V, Vx is equipped with an on-board device 2.

[0022] An obstacle X, such as a broken-down vehicle or earth and sand, exists on lane L1. Therefore, vehicle Vx on lane L1 changes lanes to the other lane L2 to avoid obstacle X (see symbol K). After that, vehicle V following vehicle Vx also behaves in the same way. This causes congestion in lanes L1 and L2, and the speeds of vehicles V and Vx ahead of obstacle X decrease.

[0023] The identification unit 102 identifies the avoidance behavior of the vehicle Vx. The detection unit 103 calculates the number of times the avoidance behavior is identified within a predetermined time at a position Pa on the road R as a frequency. The detection unit 103 detects a position Pa where the frequency is equal to or greater than a threshold, based on the position information 131.

[0024] The determination unit 104 generates speed distribution information 133 of the vehicle V passing through a position Pb on the traveling direction side of the position Pa detected by the detection unit 103, from the vehicle speed information 132 and the position information 131. In this example, because a traffic jam is occurring due to the obstacle X, low speeds are frequent in both lanes L1 and L2, which appears as a peak P0 in the speed distribution information 133. Therefore, the determination unit 104 determines that the speed distribution information 133 does not have a bimodal characteristic, and the detection unit 105 detects an obstacle on the road R.

[0025] 2(b) is a diagram showing an example of the behavior and speed distribution information 133 of vehicles V and Vx when no obstacles occur on road R. Lane L1 is congested because it is a route leading to, for example, an exit of a highway or an entrance to a service area. Vehicle Vx changes lanes to the other lane L2 to avoid the congestion (see symbol K).

[0026] The detection unit 103 detects a position Pc where the frequency is equal to or greater than a threshold value based on the position information 131. The determination unit 104 generates speed distribution information 133 of a vehicle V passing through a position Pb on the traveling direction side of the position Pa detected by the detection unit 103, from the vehicle speed information 132 and the position information 131. In this example, lane L1 is congested, so low speeds are frequent, which appears as peak P1 in the speed distribution information 133. On the other hand, lane L2 is not congested, so high speeds are frequent, which appears as another peak P2 in the speed distribution information 133. Therefore, the determination unit 104 determines that the speed distribution information 133 has bimodality, and the detection unit 105 does not detect an obstacle on road R. Note that the determination unit 104 can detect, for example, a boundary speed P3 between high and low speeds, and determine the bimodality from the frequency difference between the boundary speed P3 and peaks P1 and P2, and the speed difference between peaks P1 and P2.

[0027] (Failure detection server operation) 3 is a flowchart showing an example of the operation of the failure detection server 1. This operation is executed, for example, at regular intervals, and includes the following steps St1 to St8.

[0028] First, the acquisition unit 101 acquires the behavior data 130, the position information 131, and the vehicle speed information 132 from the in-vehicle device 2 (St1). Next, the identification unit 102 determines whether or not the avoidance behavior of the vehicle has been identified (St2). If it has not been identified (No in St2), this operation ends.

[0029] If an avoidance behavior is identified (Yes in St2), the detection unit 103 detects the position where the avoidance behavior is identified (St3). The detection unit 103 compares the detection frequency of the position with a predetermined threshold (St4). If the frequency is less than or equal to the threshold (No in St4), this operation ends.

[0030] If the frequency is greater than the threshold (Yes in St4), the speed distribution information 133 of the vehicle ahead of the detected position is generated (St5). Next, the determination unit 104 determines whether the speed distribution information 133 is bimodal (St6). If there is no bimodal presence (Yes in St6), the detection unit 105 detects a fault (St7). If there is bimodal presence (No in St6), the detection unit 105 does not detect a fault (St8). In this manner, the fault detection server 1 operates.

[0031] As described above, the obstacle detection server 1 detects obstacles based on whether or not there is a bimodal distribution of speed ahead of the location where avoidance behavior frequently occurs, and therefore can distinguish between congestion caused by obstacle X and congestion at an exit of a highway or an entrance to a service area. Therefore, the obstacle detection server 1 can detect obstacles on the road with high accuracy. [Explanation of symbols]

[0032] 1 Fault detection server (fault detection device), 10 CPU, 101 acquisition unit, 102 identification unit, 103 detection unit, 104 determination unit, 105 detection unit, 133 speed distribution information

Claims

[Claim 1] an acquisition unit that acquires, from each of a plurality of vehicles traveling on a road in a predetermined direction, behavior data indicating the behavior of the vehicle, position information indicating the position of the vehicle, and vehicle speed information indicating the speed of the vehicle; an identification unit that identifies an avoidance behavior of the vehicle to avoid an object on a path based on the behavior data; a detection unit that detects, based on the position information, a position on the road where the frequency at which the avoidance behavior is identified by the identification unit is equal to or greater than a threshold; a determination unit that determines whether a distribution of the speed of the vehicle on the predetermined direction side of the position detected by the detection unit exhibits bimodal distribution based on the vehicle speed information; a detection unit that, when the determination unit determines that the distribution exhibits bimodalities, does not detect the occurrence of a fault at the position detected by the detection unit, and, when the determination unit determines that the distribution does not exhibit bimodalities, detects the occurrence of a fault at the position detected by the detection unit. Fault detection device.

Images