Sensor device

Abstract

To improve the reliability of sensor devices. [Solution] The sensor device comprises: an information acquisition means for acquiring shape information of a target area; a projection means for projecting a predetermined projection light onto the target area; a detection means for detecting the projection light projected onto the target area; an estimation means for estimating how the projection light would appear when projected onto the target area, based on the shape information acquired by the information acquisition means; and a determination means for determining the soundness of the information acquisition means based on the shape of the projection light detected by the detection means and the appearance of the projection light estimated by the estimation means.

Description

Technical Field

[0001] The present invention relates to a sensor device.

Background Art

[0002] A sensor device mounted on a vehicle or the like to acquire surrounding information is known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] If the certainty of the determination of the sensor device can be objectively guaranteed, the reliability of the sensor device is improved. An object of the present invention is to improve the reliability of a sensor device.

Means for Solving the Problems

[0005] To achieve the above object, an embodiment of the present invention is a sensor device, comprising: information acquisition means for acquiring shape information of a target area; projection means for projecting predetermined projection light onto the target area; detection means for detecting the projection light projected onto the target area; estimation means for estimating how the projection light looks when the projection light is projected onto the target area based on the shape information acquired by the information acquisition means; determination means for determining the soundness of the information acquisition means based on the shape of the projection light detected by the detection means and the appearance of the projection light estimated by the estimation means; and.

Effects of the Invention

[0006] According to the present invention, the appearance of the projected light when it is projected is estimated based on the shape information acquired by the information acquisition means. Then, the soundness of the information acquisition means is determined based on the estimated appearance of the projected light and the shape of the projected light detected by the detection means. This allows for a suitable determination of the soundness of the information acquisition means, and consequently, the reliability of the sensor device can be improved. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing a schematic control configuration of the sensor system according to the embodiment. [Figure 2] This is a flowchart showing the operation flow of the sensor system according to the embodiment. [Figure 3A] This is a diagram illustrating the operation of the sensor system according to the embodiment. [Figure 3B] This is a diagram illustrating the operation of the sensor system according to the embodiment. [Figure 3C] This is a diagram illustrating the operation of the sensor system according to the embodiment. [Figure 4A] This is a diagram illustrating the operation of a sensor system according to a modified embodiment. [Figure 4B] This is a diagram illustrating the operation of a sensor system according to a modified embodiment. [Figure 4C] This is a diagram illustrating the operation of a sensor system according to a modified embodiment. [Figure 5A] This is a diagram illustrating the operation of a sensor system according to a modified embodiment. [Figure 5B] This is a diagram illustrating the operation of a sensor system according to a modified embodiment. [Figure 5C] This is a diagram illustrating the operation of a sensor system according to a modified embodiment. [Modes for carrying out the invention]

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0009] [Configuration of Sensor System] FIG. 1 is a block diagram showing a schematic control configuration of a sensor system 1 according to the present embodiment. The sensor system 1 according to the present embodiment is an example of the sensor device according to the present invention, and is mounted on a moving body such as a vehicle to acquire surrounding information. Specifically, as shown in FIG. 1, the sensor system 1 includes a detection sensor 22, a projector 23, a camera 24, a notification unit 25, a storage unit 26, and a control unit 27.

[0010] The detection sensor 22 detects (senses) an object within the scan area by acquiring distance information within a predetermined scan area in front of the moving body, for example, and outputs the result to the control unit 27. The type of the detection sensor 22 is not particularly limited, and may be, for example, a camera, 3D-LiDAR (Laser Imaging Detection and Ranging), a millimeter wave sensor, or the like.

[0011] The projector 23 projects predetermined projection light 41 (see FIG. 3B etc.) within the scan area of the detection sensor 22 based on a command from the control unit 27. The camera 24 captures the projection light 41 projected by the projector 23 based on a command from the control unit 27 and acquires the image thereof.

[0012] The notification unit 25 notifies various information to the passengers of the moving body based on a command from the control unit 27. The notification unit 25 is, for example, a display unit configured by a liquid crystal display, an organic electroluminescence display, or other displays. Alternatively, the notification unit 25 may include an audio output unit configured by a speaker.

[0013] The storage unit 26 is a memory composed of, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), or the like. The storage unit 26 stores various programs and data, and also functions as a working area for the control unit 27. The control unit 27 is composed of, for example, a CPU (Central Processing Unit) or the like, and controls the operations of each part of the sensor system 1. In addition, each of the above components of the sensor system 1 may be a part of a moving body on which the sensor system 1 is mounted.

[0014] [Operation of Sensor System] FIG. 2 is a flowchart showing the flow of the sensing operation of the sensor system 1, and FIGS. 3A to 3C are diagrams for explaining the sensing operation. The sensing operation of the sensor system 1 is executed, for example, when the moving body starts a predetermined operation, by the control unit 27 reading out and expanding the corresponding program from the storage unit 26. Here, for example, the case where a moving body in motion performs sensing with respect to the front (traveling direction) where the scenery shown in FIG. 3A can be seen will be described.

[0015] As shown in FIG. 2, first, the control unit 27 detects distance information in front of the moving body by the detection sensor 22 (step S1). Thereby, the terrain information (shape information) within the scan range of the detection sensor 22 is acquired and stored in the storage unit 26. In this step, it is only necessary to acquire the terrain information of a predetermined area. For example, position information may be acquired by a GNSS (Global Navigation Satellite System) receiver, or map data may be acquired from a database or the like.

[0016] Next, the control unit 27 projects (irradiates) a predetermined projection light 41 in front of the moving body by the projector 23 (step S2; FIG. 3B). Here, the projected light 41 can be anything that can be recognized by the camera 24, and may be invisible light, for example. The shape (illumination shape) of the projected light 41 is not particularly limited and may be a simple line or may include a predetermined shape pattern (e.g., a hatching pattern). When the projected light 41 includes a shape pattern, the accuracy of terrain recognition is improved compared to when it is a simple line. Also, the position (range) where the projected light 41 is projected may be within the range of the scan area of ​​the detection sensor 22 that acquired terrain information in step S1.

[0017] Next, the control unit 27 estimates how the projected light 41 from the moving object will appear based on the terrain information acquired in step S1 (step S3). Here, "how the projected light 41 will appear" refers to the shape of the projected light 41 in the captured image when the projected light 41 is photographed by the camera 24. Here, as shown in Figure 3C, the control unit 27 simulates how the projected light 41 would appear when projected under the same conditions as in step S2 in a virtual space 50 generated from terrain information. Hereafter, the projected light estimated in the simulation will be identified as the one actually projected by adding "s" to the end of its code. Note that step S3 may be performed before step S2.

[0018] Next, the control unit 27 uses the camera 24 to capture (detect) the projected light 41 that was actually projected in step S2, and acquires the image data (step S4).

[0019] Next, the control unit 27 compares the simulated projection light 41s estimated in step S3 with the captured image of the projection light 41 acquired in step S4 (step S5), and determines whether the difference is greater than or equal to a threshold (step S6). The threshold can be set appropriately according to the desired anomaly detection accuracy. Then, if the control unit 27 determines that the difference between the projected light 41s in the simulation and the projected light 41 in the captured image is not greater than or equal to a threshold (step S6; No), the control unit 27 proceeds to step S8, which will be described later.

[0020] In step S6, if the control unit 27 determines that the difference between the projected light 41s in the simulation and the projected light 41 in the captured image is greater than or equal to a threshold (step S6; Yes), the control unit 27 notifies the user of the sensor system 1 (e.g., the driver of the moving vehicle) that there may be an abnormality in the detection sensor 22 (step S7). In other words, if the degree of agreement between the projected light 41s in the simulation and the projected light 41 in the captured image is low, it is determined that the terrain recognition by the detection sensor 22 is inaccurate, and the possibility of an abnormality in the detection sensor 22 is notified. The notification method at this time is not particularly limited; for example, the notification unit 25 may simply output a warning image or a warning sound, or the intensity of the warning may be changed according to the size of the difference.

[0021] Next, the control unit 27 determines whether or not to terminate the sensing operation of the sensor system 1 (step S8). If it determines not to terminate the operation (step S8; No), it proceeds to step S1 described above. On the other hand, if it is determined that the sensing operation of the sensor system 1 should be terminated, for example, when the moving object stops (step S8; Yes), the control unit 27 terminates the control processing of the sensor system 1.

[0022] [Technical effects of this embodiment] As described above, according to this embodiment, the appearance of the projected light 41 when it is projected is estimated based on the shape information acquired by the detection sensor 22. Then, the health of the detection sensor 22 is determined based on the estimated appearance of the projected light 41 and the shape of the projected light 41 detected by the camera 24. This allows for an objective determination of the accuracy of the sensor system 1's situational judgment. Consequently, the reliability of the sensor system 1 can be improved. Ultimately, this reduces the need for humans to monitor the situation. In other words, while the detection sensor 22 itself has the general function of simply acquiring data from the external environment, in this embodiment, an action is performed on the external environment by outputting video, and the result is then used. Therefore, reliability can be increased compared to simply calculating the data acquired by the detection sensor 22 on a computer.

[0023] Furthermore, according to this embodiment, if the difference between the shape of the projected light 41 detected by the camera 24 and the estimated appearance of the projected light 41 is greater than or equal to a threshold, an abnormality in the detection sensor 22 is reported. This allows a warning to be issued to the user (such as the driver of a moving vehicle) if an abnormality is suspected in the detection sensor 22. Furthermore, the situation in which the user is prompted to pay attention can be adjusted by setting the threshold appropriately. Furthermore, by dynamically and precisely determining the health of sensor system 1, it becomes possible to issue situation-appropriate warnings to the user, thereby improving safety in autonomous driving and other applications.

[0024] Furthermore, according to this embodiment, the projected light 41 may include a predetermined shape pattern (for example, a hatching pattern). This improves the accuracy of terrain recognition compared to the case where the projected light 41 is a simple line.

[0025] [others] Although embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above. For example, the area onto which the projected light 41 is projected in step S2 described above is preferably a terrain (or part thereof) with irregularities rather than a flat terrain. For example, as shown in Figure 4A, the projection light 41 may be projected onto a gravel road 61 or the like, which has many small bumps and ridges. In this case, if the projected light 41s in the simulation does not reflect the change in appearance due to the gravel road 61 (Figure 4B), and the difference between it and the actual projected light 41 (Figure 4C) is greater than or equal to a threshold, an abnormality in the detection sensor 22 is reported. Alternatively, as shown in Figure 5A, the projection light 41 may be projected onto a structure 62 or the like that has large irregularities. In this case, if the projected light 41s in the simulation does not reflect the change in appearance due to the structure 62 (Figure 5B), and the difference between it and the actual projected light 41 (Figure 5C) exceeds a threshold, an abnormality in the detection sensor 22 is reported. Thus, by making the area onto which the projected light 41 is projected an uneven terrain rather than a flat terrain, the appearance of the projected light 41 can be easily changed. Therefore, the difference between the actual trajectory of the projected light 41 and the estimated trajectory in the simulation can be made larger. In turn, the accuracy of anomaly detection by the detection sensor 22 can be improved.

[0026] Furthermore, the health determination of the detection sensor 22 by steps S2 to S7 described above does not have to be performed every time the detection sensor 22 senses, but may be performed at desired time intervals or after each sensing cycle.

[0027] Furthermore, in the above embodiment, a camera 24 was exemplified as a detection means for detecting the projected light 41. However, the detection means only needs to be capable of detecting the actual projected light 41, and the type of sensor is not particularly limited. However, in order to avoid similar shape misidentifications caused by the type of sensor, it is preferable that the sensor is of a different type from the detection sensor 22 that is the target of determination. Furthermore, if laser light is used for the projection light 41, the projection shall satisfy the required safety standards.

[0028] Furthermore, the above embodiments described the case in which the present invention is applied to a sensor system mounted on a moving body such as a vehicle. However, the present invention can also be suitably applied to sensor devices mounted on moving bodies other than vehicles, sensor devices mounted on objects other than moving bodies, and standalone sensor devices.

[0029] Furthermore, details shown in the above embodiments can be modified as appropriate without departing from the spirit of the invention. [Explanation of Symbols]

[0030] 1. Sensor system (sensor device) 22 Detection sensor (information acquisition means) 23. Projector (projection means) 24 Camera (detection means) 25 Hochi Department 27 Control Unit (Estimation means, Determination means) 41 Projection light 41s (Simulated) Projected light

Claims

1. Information acquisition means for acquiring shape information of the target area, A projection means for projecting a predetermined projection light onto the target area, A detection means for detecting the projected light projected onto the target area, An estimation means for estimating how the projected light will appear when it is projected onto the target area, based on the shape information acquired by the information acquisition means, A determination means that determines the soundness of the information acquisition means based on the shape of the projected light detected by the detection means and the appearance of the projected light estimated by the estimation means, A sensor device equipped with the following features.

2. The determination means reports an abnormality in the information acquisition means if the difference between the shape of the projected light detected by the detection means and the appearance of the projected light estimated by the estimation means is greater than or equal to a threshold. The sensor device according to claim 1.

3. The projection means projects the projection light onto the portion of the target area that has irregularities. The sensor device according to claim 1.

4. The projected light includes a predetermined shape pattern, The sensor device according to claim 1.

Images