Obstacle detection system and train equipped with it

Abstract

To provide a technology capable of continuously performing operation of a vehicle even in the case that a malfunction occurs in a portion of a plurality of sensors.SOLUTION: A representative obstacle detection device according to the present invention is an obstacle detection system having M sensors and a signal processing part corresponding to the M sensors, and includes an m-th sensor for detecting an M-th detection range being a range having expansion in the direction of travel being a direction in which the vehicle heads toward a course, and a controller for controlling the m-th sensor and the signal processing part. The controller performs at least either change processing of first change processing for making a first end part approach the vehicle or second change processing for keeping a second end part away from the vehicle, and changes an obstacle detection range by changing at least a p-th detection range.SELECTED DRAWING: Figure 1

Description

【Technical Field】 【0001】 The present invention relates to an obstacle detection system and a train equipped with the same. 【Background Art】 【0002】 Conventionally, regarding an obstacle detection system for vehicles, a technique for detecting an abnormality of an obstacle sensor used in the system is known. 【0003】 Patent Document 1 discloses an operation support device including a monitoring unit that monitors the operation / non-operation of a sensor that can be mounted on a vehicle, and an output unit that outputs information on the operation / non-operation being monitored by the monitoring unit. The monitoring unit detects a malfunction of the sensor based on the detection accuracy of the sensor input when the sensor is operating, and the output unit outputs malfunction information in accordance with the operation / non-operation information when the monitoring unit detects a malfunction of the sensor. 【Prior Art Documents】 【Patent Documents】 【0004】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2017-178267 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0005】 Here, when applying an obstacle detection system to a moving object that needs to have a long braking distance, such as a train, it is conceivable to divide the detection section in the traveling direction of the moving object, allocate sensors for each detection section, and secure a detection range up to a position away from the moving object. When a malfunction of the sensor occurs, it is conceivable to replace the detection range, but in Patent Document 1, such a viewpoint has not been sufficiently studied. 【0006】 Therefore, the present invention aims to provide a technology that enables the continued operation of a vehicle even if some of the multiple sensors malfunction. [Means for solving the problem] 【0007】 To solve the above problems, a typical obstacle detection system of the present invention is an obstacle detection system having M (M is a positive integer of 2 or more) sensors and a signal processing unit corresponding to the M sensors for detecting obstacles in the path of a vehicle, the system includes an m (m is an integer of 1 or more and less than or equal to M) sensor that detects an m detection range which is an area extending in the direction of travel which is the direction in which the vehicle is heading, and a controller that controls the m sensor and the signal processing unit, wherein the signal processing unit performs signal processing to detect an obstacle based on the output signal of the m sensor, the obstacle detection range which is the range of the entire obstacle detection system is configured to include the m detection range, the distance from the m+1 detection range to the vehicle is greater than the distance from the m detection range to the vehicle, and the controller When it is determined that a malfunction has occurred in the nth sensor (where n is an integer between 1 and M), the obstacle detection range is changed by changing at least the p detection range, based on at least one of the following: the nth detection range of the nth sensor, the presence or absence of a human alternative means for obstacle detection, the vehicle's travel speed, and the planned travel speed of the vehicle after a certain period of time or after traveling a certain distance. The p detection range of the p sensor (where p is an integer between 1 and M other than n) is defined as having a first end closest to the vehicle and a second end furthest from the vehicle, and at least one of the following modification processes is performed: a first modification process to bring the first end closer to the vehicle, or a second modification process to move the second end further away from the vehicle. [Effects of the Invention] 【0008】 According to the present invention, it is possible to continue operating a vehicle even if some of the multiple sensors malfunction. Issues, structures, and effects other than those mentioned above will be clarified by the following explanation of the implementation methods. [Brief explanation of the drawing] 【0009】 [Figure 1] Figure 1 shows a schematic configuration of an obstacle detection system and a vehicle equipped with it. [Figure 2] Figure 2 schematically shows the arrangement of the normal detection ranges of each sensor. [Figure 3] Figure 3 shows the detection range when a millimeter-wave radar sensor malfunctions. [Figure 4] Figure 4 shows the case where the detection range of the stereo camera sensor and the detection range of the monocular camera sensor are changed. [Figure 5] Figure 5 shows a case where the detection range of the LiDAR sensor becomes undetectable, and the detection range of the stereo camera sensor expands. [Figure 6] Figure 6 shows a case where the detection range of the monocular camera sensor becomes undetectable, and the detection range of the stereo camera sensor expands. [Figure 7] Figure 7 shows a case where the detection range of the stereo camera sensor becomes undetectable, and the detection range of the monocular camera sensor expands. [Figure 8] Figure 8 shows the configuration of the signal processing means for a stereo camera sensor. [Figure 9] Figure 9 is a flowchart illustrating the actions performed by the controller of the obstacle detection system. [Figure 10] Figure 10 schematically shows an image that has undergone the cropping and compression process in the cropping and compression means. [Figure 11] Figure 11 schematically shows an image that has undergone cropping and compression processing by the cropping and compression means when the detection range is changed. [Figure 12] Figure 12 shows the field of view of a stereo camera. [Figure 13]FIG. 13 is a diagram showing a case where the direction of one optical axis of the cameras constituting the stereo camera is changed. 【Embodiments for Carrying Out the Invention】 【0010】 Hereinafter, embodiments will be described with reference to the drawings. Note that the present invention is not limited by this embodiment. Also, in the description of the drawings, the same parts are denoted by the same reference numerals. 【0011】 In the present disclosure, the "detection range" refers to a range in which information such as the position and speed of an obstacle can be acquired using a detection device such as a sensor. Taking a stereo camera as an example of the detection device, the detection range is defined through the functions of the cameras constituting the stereo camera, a sensor that outputs the captured image as a signal, and a signal processing means that processes the output signal of the sensor to identify an obstacle. Such a detection range is specified by the detection device and is referred to as the "detection range of the stereo camera" or the "detection range of the sensor of the stereo camera". Also, "the detection range includes the range from distance x1 to distance x3" means that x1 and x3, which are the boundaries of the detection range, are also included. 【0012】 [Example 1] In Example 1, an example of an obstacle detection system and a vehicle equipped with the same will be described. FIG. 1 is a diagram showing a schematic configuration of an obstacle detection system and a vehicle equipped with the same. First, each functional block will be described. 【0013】 (Configuration) Figure 1 shows an obstacle detection system mounted on a vehicle. The obstacle detection system 100 detects obstacles in the path of the vehicle 400. The vehicle 400 is, for example, a train. The obstacle detection system 100 mounted on the vehicle 400 includes a plurality of sensors 111 to 114. The left camera sensor 111 constitutes the left camera of a stereo camera sensor. The right camera sensor 112 constitutes the right camera of a stereo camera. The left camera sensor 111 and the right camera sensor 112 constitute a stereo camera sensor. The LiDAR sensor 113 constitutes LiDAR (light detection and ranging). The millimeter-wave radar sensor 114 constitutes millimeter-wave radar. Signal processing means 121 to 124 perform signal processing to detect obstacles based on the output signals of each of the sensors 111 to 114. That is, the signal processing means 121 performs signal processing to detect obstacles based on the left and right camera images acquired by the left camera sensor 111 and the right camera sensor 112. Switch 130 selectively sends the image signal to signal processing means 122. Signal processing means 122 performs signal processing to detect obstacles based on the monocular camera image acquired by either the left camera sensor 111 or the right camera sensor 112. Signal processing means 123 performs signal processing to detect obstacles based on the output signal of the LiDAR sensor 113. Signal processing means 124 performs signal processing to detect obstacles based on the output signal of the millimeter-wave radar sensor 114. Signal processing means 121 to 124 perform their respective signal processing using the computing resources of memory 131 and arithmetic unit 132. User interface 133 is controlled by controller 140 and provides notifications to the crew. Controller 140 controls sensors 111 to 114 and signal processing means 121 to 124. Other functions of controller 140 will be described later. 【0014】 The left camera sensor 111 and the right camera sensor 112 constitute a stereo camera, while also being configured to function as a monocular camera by switching the switch 130. This configuration is merely an example, and the embodiments are not limited thereto. A configuration in which sensors for the stereo camera and sensors for the monocular camera are provided separately is also possible. 【0015】 The obstacle detection system 200 is installed in the rearmost vehicle when, for example, the obstacle detection system 100 is installed in the leading vehicle of the vehicle 400, and is used to detect obstacles when the vehicle 400 makes a U-turn and travels in the reverse direction. The obstacle detection system 200 has components equivalent to those of the obstacle detection system 100. That is, the obstacle detection system 200 includes a plurality of sensors 211 to 214. The left camera sensor 211 constitutes the left camera of the stereo camera. The right camera sensor 212 constitutes the right camera of the same stereo camera. The left camera sensor 111 and the right camera sensor 112 constitute a stereo camera sensor. The LiDAR sensor 213 constitutes a LiDAR (light detection and ranging). The millimeter-wave radar sensor 214 constitutes a millimeter-wave radar. The signal processing means 121 to 124 perform signal processing for detecting obstacles based on the output signals of the sensors 111 to 114 respectively. That is, the signal processing means 221 performs signal processing for detecting obstacles based on the left and right camera images acquired by the left camera sensor 211 and the right camera sensor 212. The switch 230 selectively sends the image signal to the signal processing means 222. The signal processing means 222 performs signal processing for detecting obstacles based on the monocular camera image acquired by either the left camera sensor 111 or the right camera sensor 112. The signal processing means 223 performs signal processing for detecting obstacles based on the output signal of the LiDAR sensor 113. The signal processing means 224 performs signal processing for detecting obstacles based on the output of the millimeter-wave radar sensor 214. The signal processing means 221 to 224 perform their respective signal processing using the computing resources of the memory 231 and the arithmetic unit 232. The user interface 233 is controlled by the controller 240 and gives notifications to the crew. The controller 240 controls the sensors 211 to 214 and the signal processing means 221 to 224. Other functions of the controller 240 will be described later. 【0016】 Furthermore, the vehicle controller 300 controls the obstacle detection system 100 and the obstacle detection system 200, or the vehicle 400 equipped with them. The vehicle 400 has communication means for the controller 140 of the obstacle detection system 100 and the controller 240 of the obstacle detection system 200 to exchange information. 【0017】 (Relationships between functions) Next, the relationships between each block will be described. The sensors 111 to 114 included in the obstacle detection system 100 detect obstacles in the direction of travel and in the surrounding area when the train is traveling with vehicle 400 at the front, for example, if vehicle 400 is at one end of the train. The direction of travel is, for example, the direction the train is heading along the tracks. The sensors 211 to 214 included in the obstacle detection system 200 are installed on the front of the vehicle at the other end of the train, opposite to the vehicle on which sensors 111 to 114 of the obstacle detection system 100 are installed, and when the train is traveling with vehicle 200 at the front, they detect obstacles in front of the train and in the surrounding area. Vehicle 400 does not have to be included in a train. If there is only one vehicle in the train, the sensors 111 to 114 of the obstacle detection system 100 may be installed on the front side of the vehicle, and the sensors 211 to 214 of the obstacle detection system 200 may be installed on the rear side of the vehicle. 【0018】 (Details of each sensor) The left camera sensor 111 and the right camera sensor 112 generate image signals indicating images captured synchronously from different viewpoints and send the generated image signals to the signal processing means 121. The image signals are also sent to the switch 130, which selectively sends the image signals to the signal processing means 122. The LiDAR sensor 113 sends a signal indicating scattered light detected by the LiDAR to the signal processing means 123. The millimeter-wave radar sensor 114 sends a signal indicating electromagnetic waves detected by the millimeter-wave radar to the signal processing means 124. Based on their respective input signals, the signal processing means 121 to 1124 perform signal processing such as noise reduction, grouping, labeling, and tracking using the memory 131 and the arithmetic unit 132, and send object information, including the coordinates and velocity of the detected object, to the controller 140. The controller 140 identifies obstacles based on object information sent from each signal processing means 121 to 124, detects the distance to the obstacle, and sends the detected information to the user interface 133 and the vehicle controller 300. While the obstacle detection system 100 is operating, the obstacle detection system 200 will detect obstacles in locations that have already been passed, so it may be stopped. However, in the event of a sensor malfunction described later, it is necessary to know the status of both systems, so communication is maintained between the controller 140, the controller 240, and the vehicle controller 300. 【0019】 In the obstacle detection system 100, the signal processing means 121-124 and the controller 140 may have a storage unit that stores input signals sent by sensors 111-114 and object information detected from the input signals. By analyzing changes in the input signals, it is also possible to detect the orientation and movement speed of the object. The obstacle detection system 200 may also have a storage unit. 【0020】 (Detection range of sensors in obstacle detection systems) Thus, since the obstacle detection systems 100 and 200 are composed of multiple sensors, robustness to the environment and operating conditions can be ensured. On the other hand, because each sensor has different characteristics and therefore excels at obstacle detection distance ranges and field of view, the detection range of each sensor is set so that an optimal detection range can be configured. 【0021】 (Example of sensor assignment) Figure 2 will be used to explain the normal detection range of each sensor. Figure 2 is a schematic diagram showing the arrangement of the normal detection ranges of each sensor. Sensors 111 to 114 of the obstacle detection system 100 are installed on the vehicle 400. The detection range of each sensor is indicated by an arrow, with detection range 403 for the LiDAR sensor 113, detection range 404 for the millimeter-wave radar sensor 114, detection range 401 for the stereo camera sensor (i.e., the sensor including the left camera sensor 111 and the right camera sensor 112), and detection range 402 for the monocular camera sensor (i.e., either the left camera sensor 111 or the right camera sensor 112). The obstacle detection range of the entire obstacle detection system 100 is comprised of detection ranges 401 to 404. 【0022】 In Figure 2, the direction in which the vehicle 400 is moving is indicated by an arrow as the direction of travel Td. The m-th sensor (where m is an integer between 1 and M, and M is a positive integer of 2 or more) detects the m-th detection range, which is an area extending in the direction of travel Td. The m-th signal processing means performs signal processing to detect obstacles based on the output signal of the m sensor. The distances moving away from the vehicle 400 in the direction of travel Td are denoted as x1 (first distance), x2 (second distance), x3 (third distance), ..., and the m-th distance (where m is an integer between 1 and M, and M is a positive integer of 2 or more). The LiDAR sensor 113 (first sensor) detects the detection range 403 (first detection range) which includes at least the range from x1 to x3. In other words, of the detection range 403 of the LiDAR sensor 113, x1 is the edge of the detection range 403 closest to the vehicle 400 (first edge), and x3 is the edge of the detection range 403 furthest from the vehicle 400 (second edge). Similarly, the millimeter-wave radar sensor 114 (second sensor) detects a detection range 404 (second detection range) that includes at least the range from x2 to x5. The stereo camera sensor (third sensor) detects a detection range 401 (third detection range) that includes at least the range from x4 to x7. The monocular camera sensor (fourth sensor) detects a detection range 402 (fourth detection range) that includes at least the range from x6 to x8. The obstacle detection system 100 is configured to include M sensors and M signal processing means (M=4 here), but the configuration of the sensors and signal processing means is not limited to this. The system may be configured to include four or more sensors and signal processing means, or it may be configured to handle M sensors and perform signal processing using a single signal processing means. 【0023】 In this way, the detection ranges can be arranged according to the characteristics of each sensor, and the overall detection range of the vehicle 400 can be configured. Here, detection range 403 and detection range 404 have an overlapping range between x2 and x3. Detection range 403 and detection range 404 can be said to be arranged continuously. Also, detection range 404 and detection range 401 have an overlapping range between x4 and x5. Detection range 401 and detection range 402 have an overlapping range between x6 and x7. For example, if an obstacle is detected by the LiDAR sensor 113 in the overlapping range from x2 to x3, but not by the millimeter-wave radar sensor 114, it can be determined that the millimeter-wave radar sensor 114 has malfunctioned. By arranging the detection ranges continuously in this way, it is possible to determine sensor malfunctions at an early stage. Since the obstacle detection systems 100 and 200 are composed of multiple sensors, robustness to the environment and operating conditions can be ensured. 【0024】 It should be noted that the arrangement of the detection ranges shown here is just one example, and the order of the detection ranges and the length of the detection distances are not limited to this. Furthermore, while it is assumed here that detection ranges 401 to 404 include the range between distances measured from vehicle 400 in the direction of travel, detection ranges 401 to 404 also extend in directions other than the direction of travel. For example, if the direction of travel Td is the X-axis direction, detection ranges 401 to 404 will also extend to a certain extent in the ±Y and ±Z directions. 【0025】 (Measures to take in case of malfunction in some sensors) When the controller 140 determines that a sensor has malfunctioned, it considers at least one of the following: the detection range of the malfunctioning sensor, the presence or absence of a human alternative means for obstacle detection, the vehicle speed 400, and the planned vehicle speed 400 after a certain period of time or after traveling a certain distance. For example, the vehicle's speed is limited by the obstacle detection range. That is, until the vehicle stops, a stopping distance is required, which is the sum of the reaction distance before the brakes are applied and the braking distance during which the brakes are applied. Here, there is a predetermined upper limit to the vehicle's deceleration, so there is a limit to how much the braking distance can be shortened. Also, there are hardware and software limitations on the sensor in order to increase the detection range. Therefore, in order to stop the vehicle before reaching an obstacle, it is necessary to limit the vehicle's speed based on the obstacle detection range. In Figure 2, the upper limit of the vehicle 400's speed is set based on x8, which is the furthest point in the detection range. The human alternative means will be discussed later. 【0026】 The smaller the detection range, the more necessary it is to limit the driving speed to reduce the stopping distance. Therefore, in Example 1, the detection range of a properly functioning sensor is modified to avoid a reduction in the detection range. This helps to suppress a decrease in driving speed. 【0027】 (If the mid-range sensor is malfunctioning) Figures 3 to 6 illustrate how the detection range of other normal sensors changes when one of the sensors malfunctions. Figure 3 shows the detection range when the millimeter-wave radar sensor 114 malfunctions. When the millimeter-wave radar sensor 114 malfunctions, an undetectable area 409 occurs between the detection range 403 of the LiDAR sensor 113 and the detection range 401 of the stereo camera sensor, where obstacle detection is not possible. Since the vehicle 400 is moving, the undetectable area 409 is initially detected by the monocular camera sensor and the stereo camera sensor, but after the absence of obstacles is confirmed, there is a possibility that an obstacle may enter that area of ​​the vehicle. Therefore, in this case, the range in which the obstacle detection system 100 can guarantee the presence or absence of obstacles is equivalent to the detection range 403 of the LiDAR sensor 113, and the upper limit of the vehicle's travel speed is set based on x3, which is the boundary of the detection range 403. In other words, if the controller 140 determines that the millimeter-wave radar sensor 114 has malfunctioned, it sets an upper limit for the vehicle's speed based on the distance x3 from the vehicle 400 to the boundary of the detection range 403. 【0028】 Therefore, measures are taken to eliminate the undetectable range. Figure 4 shows the case when the detection range of the stereo camera sensor and the detection range of the monocular camera sensor are changed. Here, when the controller 140 determines that the aforementioned n sensor (where n is an integer between 1 and M) has malfunctioned, it performs a modification process to change the detection range of the p sensor (where p is an integer between 1 and M, excluding n) so that it includes at least a part of the n detection range. That is, it performs a modification process (first modification process) to bring the end x4 closest to the train 400 in the detection range 401 closer to the train 400, thereby changing the detection range 401 to detection range 401a. As a result, the detection range 401 of the stereo camera sensor is expanded overall. Also, if the distance between x5 and x6 is xi1, the modified detection range 401a of the stereo camera sensor includes the range from x2 to xi1. As a result, the detection range 401a includes the detection range 404 of the millimeter-wave radar sensor 114 (the range from x2 to x5). Furthermore, because the detection range of the stereo camera sensor has changed to move closer to the vehicle 400, a modification process is performed to supplement the detection range of the stereo camera sensor with the monocular camera sensor. Here, the modified detection range 402a of the monocular camera sensor includes the range from x5 to xi2, where xi2 is the distance between x7 and x8. Regarding the obstacle detection range, which is the detection range of the entire obstacle detection system 100, the modified obstacle detection range consists of detection ranges 403, 401a, and 402a arranged in a continuous sequence. 【0029】 By changing the detection range 401a of the stereo camera sensor and the detection range 402a of the monocular camera sensor in this way, the undetectable range 409 is eliminated by the detection range 401a, and the overall detection range of the obstacle detection system 100 can be set to a continuous distance xi2 from the vehicle 400 to the boundary of the detection range 402a. The controller 140 also sets an upper limit on the vehicle 400's travel speed based on the detection range after the modification process. Since the boundary of the overall detection range of the obstacle detection system 100 was only narrowed from x8 to xi2, the restriction on the upper limit of the vehicle 400's travel speed can be minimized. The method for shortening the obstacle detection range by the stereo camera can be, for example, by compressing the image according to the degree of proximity. The method for extending the detection range can be by increasing the magnification of the image and, if it is handled in image processing, performing detection based on the super-resolution image, or if it is handled in the optical system such as a lens, performing geometric correction of the stereo camera as necessary. Details on how to change the detection range of the stereo camera sensor will be described later. 【0030】 The reason why the detection areas of the stereo camera sensor and monocular camera sensor in Figure 4 are each indicated by two arrows is to clearly show that the detection range has expanded compared to Figure 2. This indicates that because the operation of the signal processing means 124 of the millimeter-wave radar sensor 114 is no longer necessary, the computing resources of the memory 131 and arithmetic unit 132 that were used by the signal processing means 124 are allocated and used by the signal processing means 121 and 122 of the stereo camera and monocular camera, making it possible to detect obstacles over a wider range. Such allocation of computing resources can be performed, for example, by the controller 140. For example, the signal processing means 121 to 124 determine that detection by the sensor is no longer possible, send a flag signal indicating this to the controller 140, and stop and release the use of computing resources. When the controller 140 detects a flag signal from the signal processing means 121 to 124, it determines that a malfunction has occurred in the sensor corresponding to the flag signal, and preferentially allocates the computing resources assigned to the sensor that is the target of modification processing and the signal processing means of that sensor. 【0031】 (If the short-range sensor malfunctions) Figure 5 shows a case where the detection range 403 of the LiDAR sensor 113 becomes undetectable, and the detection range of the stereo camera sensor is expanded. Figure 5 shows a case where the LiDAR sensor 113 malfunctions, and the detection range 401b of the stereo camera sensor compensates for the undetectable range of the LiDAR sensor 113, i.e., the detection range 401 which includes the range from x1 to x3. Figure 8 shows the operation of the stereo camera in this case. Furthermore, while the detection range 401b from x1 to x3 and the detection range 401 from x4 to x7 are assigned to the stereo camera sensor, the range from x3 to x4 is excluded from the stereo camera sensor's detection range. The computing resources that were assigned to the malfunctioning LiDAR sensor 113 are also assigned to the stereo camera sensor, but in the example shown in Figure 5, it is shown that the stereo camera sensor is not allocated sufficient computing resources to detect the entire range from x1 to x7. Since allowing the stereo camera sensor to detect the range from x3 to x4 would increase the processing load, the detection range of the stereo camera sensor is limited to detection range 401b and detection range 401. 【0032】 Figure 8 shows the configuration of the signal processing means 121 of the stereo camera sensor. Normally, the stereo camera operates by geometrically correcting the image signal Sl based on the left camera and the image signal Sr based on the right camera using geometric correction means 1211 and 1212, and then appropriately compressing the geometrically corrected image by cropping and compressing the necessary area using cropping and compression means 1213 and 1214. After that, a disparity image is calculated using the left and right cropped images with the stereo matching means 1215, and the distance to an obstacle is detected using the disparity image with the obstacle detection means 1216. 【0033】 On the other hand, when detecting the detection range 401b near the vehicle using a stereo camera sensor as an alternative to the detection range 401 of the LiDAR sensor 113, the necessary area is cut out using the cropping and compression means 1217 and 1218 of the corrected image, and the image is compressed at a higher compression ratio than in the normal case. This is a process to detect distances closer than the normal detection range 401. Subsequently, the stereo matching means 1219 and the obstacle detection means 1220 detect obstacles at close range and send the obstacle detection information to the subsequent controller 140. 【0034】 Furthermore, if there are insufficient resources to compensate for the undetectable range of the LiDAR sensor 113 in addition to the detection range of the conventional stereo camera sensor, priority will be given to detecting an alternative range for the undetectable range of the LiDAR sensor 113. This is to prevent an undetectable range from remaining in the distance x2 from the vehicle 400 to the boundary of the detection range 404 of the millimeter-wave radar sensor. In addition, if the signal processing resources of the normal stereo camera become insufficient and the detection range 401 of the stereo camera is shortened, resulting in an undetectable range between x4 and x7, it is possible to compensate for the undetectable range by changing the boundary x6 of the detection range 402 of the monocular camera sensor to a point on the vehicle 400 side. 【0035】 (If the long-range sensor malfunctions) Figure 6 shows a case where the detection range 402 of the monocular camera sensor becomes undetectable, and the detection range 401 of the stereo camera sensor is expanded. Figure 6 shows a case where the monocular camera sensor malfunctions. The modified detection range 401c of the stereo camera sensor is extended to the farther side compared to the normal detection range 401. That is, a modification process (second modification process) is performed to move the end x7 of the detection range 401 furthest from the train 400 further away from the train 400, thereby changing the detection range 401 to detection range 401c. As a result, the detection range 401 of the stereo camera sensor is expanded overall. That is, if the distance between x7 and x8 is xi3, the modified detection range 401c of the stereo camera sensor includes the range from x4 to xi3. This is a result of the stereo camera sensor's signal processing means 121 expanding the detection range of the stereo camera sensor by using the resources that were being used by the monocular camera's signal processing means 122. In this way, the detection range 401c of the stereo camera can supplement a portion of the detection range 402 of the monocular camera, which is outside the detection range. Although it does not supplement the entire area of ​​the monocular camera's detection range 402, the boundary of the overall detection range of the obstacle detection system 100 can be kept between x8 and xi3, thus minimizing the restriction on the driving speed. 【0036】 (If the stereo camera is malfunctioning) Figure 7 shows a case where the detection range 401 of the stereo camera sensor becomes undetectable, and the detection range of the monocular camera sensor is expanded. Figure 7 shows a case where the stereo camera, composed of the left camera sensor 111 and the right camera sensor 112, malfunctions. The detection range 402a of the monocular camera sensor is expanded to compensate for the range that was previously the detection range 401 of the stereo camera sensor. That is, if the distance between x7 and x8 is xi4, the modified detection range 402a of the monocular camera sensor includes the range from x4 to xi4. The signal processing means 122 of the monocular camera sensor utilizes the computing resources that were used by the signal processing means 121 of the stereo camera to expand the detection range of the monocular camera and compensate for a portion of the undetectable range. In Embodiment 1, the input image of the monocular camera is used in combination with either the left or right image of the stereo camera, so if the cause of the stereo camera malfunction lies in the camera unit, the input of the signal processing means 122 is switched by the switch 130. This means that the switch 130 can be configured to switch to the signal processing means 122 if an abnormality is detected in at least one of the signals from the left camera sensor 111 and the right camera sensor 112. Alternatively, the signal processing means 121 may send a flag to the controller 140 indicating that obstacle detection by the stereo camera is not possible, and the controller 140 may issue an instruction to switch the switch. This does not apply if a camera and sensor dedicated to a monocular camera are provided. 【0037】 (Summary of changes to the detection range) As described above, if some sensors malfunction, the detection range is changed to compensate for the range that other normal sensors cannot detect. In other words, the detection range of each sensor is changed so that the detection range of the obstacle detection system 100 as a whole extends continuously from the vehicle 400 to as far as possible. This is not simply a change in the system's detection range due to some sensors failing to function, but rather a change to create a new detection range that is different from the normally positioned detection range in order to compensate for the range that cannot be detected, and also a change that compensates for at least a portion of the range that cannot be detected. By performing this modification process, it becomes possible to continue operating the vehicle even if some of the sensors malfunction. 【0038】 (Handover to crew) The controller 140 recognizes whether obstacle detection can be performed by human resources (such as the crew of train 400). When obstacle detection by human resources is possible, if the controller 140 determines that at least one of the M sensors is malfunctioning, it determines whether the malfunctioning range can be compensated for by the healthy sensors excluding the one used for obstacle detection by human resources, and whether the actual damage is within an acceptable range. As a result, if obstacle detection by human resources is necessary, the controller 140 outputs information indicating that it will perform a handover to transfer the obstacle detection operation and range to the human resources. Here, the controller outputs information indicating that it will perform a handover to transfer the obstacle detection operation and range to the human resources, and then outputs information indicating that the handover is possible by the human resources before executing the handover, or the human resources switch to the handover and recognize the execution of the handover, and then communicate the human detection range to the human resources via a user interface such as a monitor or head-mounted display (HMD). 【0039】 Here, if the controller 140 recognizes that obstacle detection in the range where detection has become impossible is possible by the train crew, there is no need to change the detection range of other sensors. If the controller 140 determines that any sensor has malfunctioned, it determines whether the detection range of the malfunctioning sensor is within a range that can be handed over by the train crew. As a criterion for this determination, for example, it may be determined whether the detection range is within a distance that can be visually assessed. Taking the case of Figure 3 as an example, if the crew can immediately take over the detection range of the millimeter-wave radar sensor 114, the obstacle detection will be handed over to the crew, and the normal sensors will continue to operate the system without changing their detection range. The controller 140 of the obstacle detection system 100 may share information with the controller 240 and the vehicle controller 300 to know in advance whether or not there is a crew member who can take over obstacle detection. When a replacement is available, the controller 140 indicates the human detection range to the crew of the vehicle 400 via the user interface 133. After receiving information from the crew indicating that a replacement is available via the user interface 133, the controller 140 performs a handover regarding obstacle detection. To ensure a smooth transition of monitoring, it is desirable that the trigger for the handover be issued by the replacement crew member. Note that the human detection range is not limited to the detection range of the malfunctioning sensor. It also includes the range in which the crew member is responsible for obstacle detection after the correction process. Furthermore, since the distance that can be seen visually is limited, it is conceivable that another sensor A covers the range of the malfunctioning sensor, and the crew member covers the range of sensor A. For example, the obstacle detection range after the change process includes the human detection range based on visual inspection by human resources. 【0040】 At this time, it is important to more clearly indicate the area to be monitored to the crew member assigned to obstacle detection. For example, the user interface 133 is equipped with a monitor or HMD (head-mounted display) and uses so-called augmented reality (AR) technology to clearly indicate and superimpose the detection area assigned to the crew member onto the real-time forward image, thereby informing the crew member of the detection area. In addition, it is also possible to equip the vehicle's windshield with a head-up display function and project the detection area onto the windshield. 【0041】 (Actions from sensor malfunction to change in detection range) (Detection and recovery of malfunctions) Figure 9 illustrates the determination of a malfunction and the subsequent operation procedure. Figure 9 is a flowchart showing the operations performed by the controller 140 of the obstacle detection system 100. The controller 140 determines whether a malfunction has occurred (step 901). The determination of a malfunction can be made by sensors 111-114 and signal processing means 121-124, or by hardware or software not shown. If a malfunction is determined by any of these methods (yes in step 901), the controller 140 attempts to restore the area where the malfunction occurred (step 902). If no malfunction occurs (no in step 901), the controller 140 continues obstacle detection. 【0042】 Depending on the cause, malfunctions can be either immediately recoverable or not immediately recoverable. For example, the former might be an object obstructing the view on the window in front of the camera, or forgetting to turn on the headlights or wipers. In some cases, the crew can remove the cause of these temporary malfunctions, so the controller 140 issues a warning via voice or screen display through the user interface 133, and if it detects that action has been taken to remove the cause, it considers the malfunction to be recovered. 【0043】 (Judgment based on the vehicle's condition) If a certain period of time elapses without detection of recovery actions being taken, and it is determined that recovery is impossible (step 903), the controller 140 formulates a plan for rearranging the detection ranges of the remaining normal sensors. In this case, the controller 140 considers, for example, the detection range of the malfunctioning sensor, whether or not there are crew members covering that detection range, etc. The controller 140 also calculates the upper limit of the vehicle's speed based on the rearrangement plan (step 904). This is because the operating schedules of other vehicles are adjusted based on the vehicle 400's speed, and if vehicle 400 continues to travel at a speed exceeding the upper limit, it will affect the operating schedule. 【0044】 Furthermore, information such as the presence or absence of crew members, the maximum speed of the vehicle on the tracks, the current location, map information, and the presence or absence of crew members may be acquired in advance by the vehicle controller 300 or acquired from an external source and sent to controllers 140 and 240. 【0045】 (Determining the direction of travel) Next, the controller 140 determines the direction of travel (step 905). Normally, if a malfunction is detected in the obstacle detection system, the vehicle crew may take over and continue normal operation. However, if the detection range is rearranged, it would be ideal if the vehicle crew could supplement the detection range by visual inspection, but there is a risk that an undetectable range will remain that cannot be detected by visual inspection. Also, if the travel speed is restricted and there is a high possibility that it will disrupt the operation of other vehicles, the vehicle must be moved to a safe place, and passengers must also be evacuated quickly. Furthermore, when an obstacle detection system is applied to an automated driving system that achieves driverless or licenseless (license-free) operation without an onboard driver, if a malfunction is detected in the obstacle detection system, it becomes difficult to continue operation. In such cases, passengers must be safely disembarked, and the vehicle must be moved off the main line to avoid disrupting other services. If the vehicle's speed is restricted, or if it becomes unable to move at all, it not only impairs passenger convenience but also exacerbates subsequent disruptions to the operating schedule. 【0046】 Taking these factors into consideration, the controller 140 determines the direction of travel based on map information such as the upper limit of the travel speed, the current location, the distance to the stations ahead and behind, the presence or absence of passengers, the results of the confirmation of the soundness of the rear obstacle detection system 200, and the location where assistance from human resources can be obtained, taking into account the time to reach the nearest stations before and after, the presence or absence of crew members at the nearest stations before and after, and the impact on the operating schedule. If the direction of travel is not changed (no in step 905), the controller 140 compares the calculated upper limit of the travel speed with the current actual speed and decelerates if the actual speed is higher (yes in step 906). If deceleration is completed after the actual speed has fallen below the upper limit of the travel speed (yes in step 907), the controller 140 modifies the detection range of each sensor based on the rearrangement plan (step 908). 【0047】 On the other hand, if the direction of travel is changed (yes in step 905), the controller 140 safely stops the vehicle 400 and then starts traveling using the obstacle detection system 200 (step 909). When arriving at the destination station, passengers are allowed to disembark or auxiliary crew members are allowed to board. The controller 140 then formulates and implements a new detection range layout. When formulating the layout, the vehicle may be moved to the final repair yard, or it may be temporarily moved to a siding to minimize the impact on the operating schedule and then moved to the final repair yard or depot after operation. 【0048】 When an obstacle detection system is applied to a driverless or license-free vehicle in this way, passengers can be quickly disembarked and the vehicle can be moved to a safe location to avoid disrupting other operations. Furthermore, since the driving speed is limited by the process of changing the detection range, it is desirable to avoid changing the detection range more than necessary. The operation shown in Figure 9 is performed periodically while vehicle 400 is in operation. By performing this operation, it is possible to reliably determine when a malfunction has occurred and when a change in the detection range is necessary, and to avoid changing the detection range more than necessary. 【0049】 (Details of the process for changing the stereo camera sensor) (When changing the detection range) Here, the details of the process for changing the detection range in a stereo camera will be explained using Figures 10 to 13. Figure 10 is a schematic diagram showing an image that has been processed by cropping and compression means 1213 and 1214. Figure 11 is a schematic diagram showing an image that has been processed by cropping and compression means 1217 and 1218 when the detection range is changed. 【0050】 Figure 10 shows the image after the input images of Figure 8, cropped and compressed by cropping and compression means 1213 and 1214, have been appropriately cropped. Here, the closer the object, the larger the parallax obtained from the left and right images. Therefore, to make the detection range closer, the search range of stereo matching should be widened. However, simply widening the search range increases the processing load and memory usage. On the other hand, the closer the object, the smaller the influence of the distance error on the parallax error. Therefore, when changing and widening the detection range, for the nearby detection range, the method of compressing the image as shown in Figure 11 is appropriate. This is performed by cropping and compression means 1217 and 1218. The calculation formula for obtaining the object distance from the parallax is shown as follows (Equation 1). 【0051】 【number】 【0052】 Here, L is the object distance, d is the object's parallax, pp is the pixel pitch, fc is the focal length of the camera lens, and B is the baseline length of the stereo camera. Compression reduces the image size, so the number of pixels decreases and the pixel pitch increases. For example, the parallax obtained from an image compressed to half its size is d / 2, and the pixel pitch considering compression is 2·pp, so the object distance L obtained will be the same when using the following equation (2). 【0053】 【number】 【0054】 Therefore, if the obstacle detection means 1220 knows the compression ratio of the disparity image sent from the stereo matching means 1219, it can appropriately obtain the object distance. For example, the controller 140 determines the compression ratio when rearranging the detection range, and the signal processing means 121 performs signal processing based on the determined compression ratio to obtain the object distance. 【0055】 (Stereo camera eye-crossing control) Correction for tilting the optical axis of the stereo camera will be explained with reference to Figures 12 and 13. Figure 12 is a diagram showing the field of view of the stereo camera. Figure 13 is a diagram showing the case when the orientation of one of the optical axes of the cameras constituting the stereo camera is changed. The controller 140 changes the detection range by performing at least one of the following: changing the magnification of the images acquired by the left and right cameras, changing the search range of the stereo matching, or rotating the optical axis of at least one of the left and right cameras inward in the yaw direction. 【0056】 For detection using a stereo camera to work, a three-dimensional object must be visible in both the left and right images. If you try to detect an extremely nearby object, the three-dimensional object may not be within the field of view of one of the images. Figure 12 shows the left camera corresponding to the left camera sensor 111 and the right camera corresponding to the right camera sensor 112. Both the left and right cameras have a field of view (FOV). Let the optical axis of the left camera be OA1 and the optical axis of the right camera be OA2. The optical axes of the left and right cameras are generally set up parallel to each other as shown in Figure 12, but as shown in Figure 13, the optical axis of one of the cameras may be pointed inward. In this case, detection of distant objects may become difficult, but it is effective when prioritizing the detection of nearby objects. When the optical axis is pointed inward, in addition to the normal geometric correction, the geometric correction means 1211 or geometric correction means 1212 in Figure 8 requires image correction based on the rotation angle, rotation axis, and position of the imaging plane. In this case, the correction calculation can be simplified by aligning the rotation axis with the entrance pupil position of the camera lens. 【0057】 (Variations of changing the detection range) After changing the detection range, the detection performance and distance measurement performance of the sensor may be briefly verified. The controller 140 uses a sensor whose detection range includes the first end that was changed after the first modification process, or a sensor whose detection range includes the second end that was changed after the second modification process, to verify the detection performance in the modified detection range. For example, as shown in Figures 4 and 5, by overlapping the modified detection range with the detection range of other normal sensors, the object detection performance and detection distance performance can be evaluated in the overlapping range. For example, in Figure 4, the controller 140 evaluates the detection performance and detection distance performance of the modified detection range 401a using the LiDAR sensor 113 corresponding to detection range 403 and the monocular camera sensor corresponding to detection range 402a. 【0058】 (Methods for determining dysfunction) Here are some examples of how to determine if a malfunction has occurred in a stereo camera or monocular camera. If the camera's frame rate is kept constant, if the output signal sent from the camera is not updated for a certain period of time, a malfunction may have occurred in the camera body or camera cable, etc. Furthermore, the controller 140 estimates the cause of the malfunction of the n sensor based on statistical information such as the average brightness, brightness variance, and brightness histogram for the entire image or for each area, as well as the difference in statistical information between areas. For example, if the brightness is significantly lower than the brightness information of the acquired image, it is possible that there is an obstruction in front of the camera lens. If the brightness is at an appropriate value but the brightness variance of the entire screen is small, it may be due to a blizzard or backlighting. If the difference with adjacent pixels is small, or if the signal level of high spatial frequencies is small, it is possible that the wipers are not operating despite heavy rain. In this way, the controller 140 or the stereo camera sensor may analyze the image contained in the output signal of the stereo camera sensor, estimate the cause of the malfunction, and instruct the crew of the vehicle 400 to take action to resolve the cause. 【0059】 (If the stereo camera sensor malfunctions) A stereo camera sensor may malfunction. For example, suppose a left camera sensor 111 and a right camera sensor 112 constitute a stereo camera sensor, and the signal processing unit 121 uses the left camera sensor 111 as input to perform obstacle detection using a monocular image. If the left camera sensor 111 malfunctions, the controller 140 will cause the controller 140 to perform obstacle detection using a monocular image with the right camera sensor 112 as input. Specifically, the controller 140 identifies the malfunctioning sensor among the left camera sensor 111 and the right camera sensor 112 that constitute the stereo camera. It is also assumed that the signal processing unit 122 is performing obstacle detection using a monocular image, such as AI. If it is determined that one sensor is malfunctioning and the other sensor is not, the controller 140 switches the switch 130 to use the sensor that is not malfunctioning as input to the signal processing unit 122. 【0060】 (Effects / Actions) As described above, in this disclosure, by changing the detection range of a properly functioning sensor, it is possible to continue driving the vehicle while suppressing the speed limit. According to this disclosure, even if some of the multiple sensors malfunction, it is possible to continue driving the vehicle. 【0061】 Although embodiments of the present invention have been described above, this disclosure is not limited to the embodiments described above, and various modifications are possible without departing from the spirit of the present invention. For example, in Embodiment 1, the obstacle detection systems 100 and 200 are installed on the vehicle, but they are not limited to being installed on a vehicle. For example, only sensors 111-114 and sensors 211-214 may be installed on the vehicle, while the other signal processing means, controller, memory, and CPU may be installed outside the train. 【0062】 [Other examples] This disclosure also includes the following aspects: (Aspect 1) An obstacle detection system having M (where M is a positive integer of 2 or more) sensors and a signal processing unit corresponding to the M sensors, for detecting obstacles in the path of a vehicle, A first m sensor (where m is an integer between 1 and M) detects a first m detection range which is an area that extends in the direction of travel of the vehicle, which is the direction in which the vehicle is moving along the aforementioned path. The system includes a controller that controls the m sensor and the signal processing unit, The signal processing unit performs signal processing to detect an obstacle based on the output signal of the m-th sensor. The obstacle detection range, which is the entire range of the aforementioned obstacle detection system, is configured to include the mth detection range, The distance from the m+1 detection range to the vehicle is greater than the distance from the m detection range to the vehicle. The aforementioned controller, If it is determined that a malfunction has occurred in the nth sensor (where n is an integer between 1 and M), Based on at least one of the nth detection range of the nth sensor, the presence or absence of a human substitute for obstacle detection, the vehicle's travel speed, and the planned travel speed of the vehicle after a certain period of time or after traveling a certain distance, When the p detection range of the p sensor (where p is an integer between 1 and M, excluding n) is defined as the first end of the range closest to the vehicle and the second end of the range furthest from the vehicle, The obstacle detection range is changed by performing at least one of the following modification processes: a first modification process that brings the first end closer to the vehicle, or a second modification process that moves the second end away from the vehicle, thereby changing at least the p detection range. An obstacle detection system characterized by the following features. (Aspect 2) An obstacle detection system according to Embodiment 1, The modified p detection range of the p sensor includes at least a portion of the n detection range. An obstacle detection system characterized by the following features. (Aspect 3) An obstacle detection system according to embodiment 1 or 2, The obstacle detection range after the modification process has detection ranges arranged in a continuous sequence. An obstacle detection system characterized by the following features. (Aspect 4) An obstacle detection system according to any one of embodiments 1 to 3, The obstacle detection range after the aforementioned modification process includes the range of human detection by visual inspection. An obstacle detection system characterized by the following features. (Aspect 5) An obstacle detection system according to any one of embodiments 1 to 4, The controller sets an upper limit for the vehicle's travel speed based on the obstacle detection range in which the modification process is scheduled to be performed. Obstacle detection system. (Aspect 6) An obstacle detection system according to any one of embodiments 1 to 5, The controller performs the modification process after the actual speed of the vehicle falls below the upper limit of the driving speed. An obstacle detection system characterized by the following features. (Aspect 7) An obstacle detection system according to any one of embodiments 1 to 6, The signal processing unit further has computing resources used when performing the signal processing, The controller allocates the computational resources that were assigned to the signal processing of the n sensor, which is determined to be malfunctioning, to the signal processing of the p sensor, which is the target of the modification process. An obstacle detection system characterized by the following features. (Pattern 8) An obstacle detection system according to any one of embodiments 1 to 7, The sensor on which the modification process is performed includes a stereo camera sensor that includes left and right cameras. The aforementioned controller, The detection range is changed by performing at least one of the following: changing the magnification of the images acquired by the left and right cameras, changing the search range of the stereo matching, or rotating the optical axis of at least one of the left and right cameras inward in the yaw direction. An obstacle detection system characterized by the following features. (Aspect 9) An obstacle detection system according to any one of embodiments 1 to 8, The aforementioned controller, The detection performance in the modified p-th detection range is confirmed using a sensor whose detection range includes the first end modified after the first modification process, or a sensor whose detection range includes the second end modified after the second modification process. An obstacle detection system characterized by the following features. (Aspect 10) An obstacle detection system according to any one of embodiments 1 to 9, The aforementioned controller, Recognize whether obstacle detection is possible using human resources. When obstacle detection is possible using the aforementioned human resources, if it is determined that at least one of the M sensors is malfunctioning, Output information indicating that a handover will be performed to transfer the operation and range of obstacle detection to human resources. After outputting information indicating that a handover is possible by the aforementioned human resources, the handover is performed, or the handover is switched over by the aforementioned human resources and the execution of the handover is recognized. The human detection range is communicated to the human resource via a user interface such as a monitor or head-mounted display. An obstacle detection system characterized by the following features. (Aspect 11) An obstacle detection system according to any one of embodiments 1 to 10, The aforementioned controller, If the output signal of the aforementioned sensor n is not updated for a certain period of time, it is determined that a malfunction has occurred. An obstacle detection system characterized by the following features. (Aspect 12) An obstacle detection system according to any one of embodiments 1 to 11, The aforementioned controller, Based on statistical information such as the average brightness, brightness variance, and brightness histogram for the entire image or for each area, and the differences in statistical information for each area, the cause of the malfunction of the aforementioned sensor n is estimated. The crew of the vehicle is instructed to take measures to resolve the aforementioned cause. An obstacle detection system characterized by the following features. (Aspect 13) An obstacle detection system according to any one of embodiments 1 to 12, The nth sensor and the qth sensor (where q is an integer between 1 and M, other than n) constitute a stereo camera sensor. When the signal processing unit is performing obstacle detection using a monocular image with the n sensor as input, The controller switches to the monocular image, which is input from the q sensor, to perform obstacle detection. An obstacle detection system characterized by the following features. (Aspect 14) A train equipped with a first obstacle detection system and a second obstacle detection system, which are obstacle detection systems according to any one of embodiments 1 to 13, The first obstacle detection system is provided in the leading car of the train, and the second obstacle detection system is provided in the last car of the train. The first obstacle detection system detects an obstacle when the train is moving in the direction of travel, and the second obstacle detection system detects an obstacle when the train is moving in the reverse direction opposite to the direction of travel. The train has communication means for the controller of the first obstacle detection system and the controller of the second obstacle detection system to exchange information. If a malfunction is detected in the first obstacle detection system, The controller of the first obstacle detection system is: The system checks the health of the second obstacle detection system and, in addition to the information regarding the confirmed health, determines whether or not to change the direction of travel, or the location at which to change the direction of travel, based on at least one of the vehicle's current location information, route map information, the presence or absence of passengers, a location where assistance from human resources can be obtained, and the upper limit of the travel speed calculated by the controller of the first obstacle detection system. A train characterized by the following features. [Explanation of symbols] 【0063】 100, 200 Obstacle Detection System 111, 211 Left camera sensor 112, 212 Right camera sensor 113, 213 LiDAR sensors 114, 214 mm wave radar sensors 121-124, 221-224 Signal processing means 130, 230 switches 131, 231 memory 132, 232 Arithmetic unit 133, 233 User Interfaces 140, 240 controllers 300 Vehicle Controller 400 vehicles Detection range 401~404, 401a, 401b, 401c, 402a 1211, 1212 Geometric correction means 1213, 1214, 1217, 1218 Cutting and Compression Methods 1215, 1219 Stereo matching means 1216, 1220 Obstacle detection means

Claims

[Claim 1] An obstacle detection system having M sensors (where M is a positive integer of 2 or more) and signal processing units corresponding to the M sensors, for detecting obstacles in the path of a vehicle, A first m sensor (where m is an integer between 1 and M) detects a first m detection range which is an area that extends in the direction of travel of the vehicle, and The system includes a controller that controls the m sensor and the signal processing unit, The signal processing unit performs signal processing to detect an obstacle based on the output signal of the m-th sensor. The obstacle detection range, which is the entire range of the aforementioned obstacle detection system, is configured to include the mth detection range, The distance from the m+1 detection range to the vehicle is greater than the distance from the m detection range to the vehicle. The aforementioned controller, If it is determined that a malfunction has occurred in the nth sensor (where n is an integer between 1 and M), Based on at least one of the nth detection range of the nth sensor, the presence or absence of a human substitute for obstacle detection, the vehicle's travel speed, and the planned travel speed of the vehicle after a certain period of time or after traveling a certain distance, When the p detection range of the p sensor (where p is an integer between 1 and M, excluding n) is defined as the first end of the range closest to the vehicle and the second end of the range furthest from the vehicle, The obstacle detection range is changed by performing at least one of the following modification processes: a first modification process that brings the first end closer to the vehicle, or a second modification process that moves the second end further away from the vehicle, thereby changing at least the p detection range. The obstacle detection range after the modification process has detection ranges arranged in a continuous sequence. An obstacle detection system characterized by the following features. [Claim 2] An obstacle detection system according to claim 1, The modified p detection range of the p sensor includes at least a portion of the n detection range. An obstacle detection system characterized by the following features. [Claim 3] An obstacle detection system according to claim 1, The obstacle detection range after the aforementioned modification process includes the range of human detection by visual inspection. An obstacle detection system characterized by the following features. [Claim 4] An obstacle detection system according to claim 1, The controller sets an upper limit for the vehicle's travel speed based on the obstacle detection range in which the modification process is scheduled to be performed. Obstacle detection system. [Claim 5] An obstacle detection system according to claim 4, The controller performs the modification process after the actual speed of the vehicle falls below the upper limit of the driving speed. An obstacle detection system characterized by the following features. [Claim 6] An obstacle detection system according to claim 1, The signal processing unit further has computing resources used when performing the signal processing, The controller allocates the computing resources that were assigned to the signal processing of the n sensor, which is determined to be malfunctioning, to the signal processing of the p sensor, which is the target of the modification process. An obstacle detection system characterized by the following features. [Claim 7] An obstacle detection system according to claim 1, The sensor on which the modification process is performed includes a stereo camera sensor that includes left and right cameras. The aforementioned controller, The detection range is changed by performing at least one of the following: changing the magnification of the images acquired by the left and right cameras, changing the search range of the stereo matching, or rotating the optical axis of at least one of the left and right cameras inward in the yaw direction. An obstacle detection system characterized by the following features. [Claim 8] An obstacle detection system according to claim 1, The aforementioned controller, The detection performance in the modified p detection range is confirmed using a sensor whose detection range includes the first end modified after the first modification process, or a sensor whose detection range includes the second end modified after the second modification process. An obstacle detection system characterized by the following features. [Claim 9] An obstacle detection system according to claim 3, The aforementioned controller, Recognize whether obstacle detection is possible using human resources. When obstacle detection is possible using the aforementioned human resources, if it is determined that at least one of the M sensors is malfunctioning, Output information indicating that a handover will be performed to transfer the operation and range of obstacle detection to human resources. After outputting information indicating that a handover is possible by the aforementioned human resources, the handover is performed, or the handover is switched over by the aforementioned human resources and the execution of the handover is recognized. The human detection range is communicated to the human resource via the user interface of a monitor or head-mounted display. An obstacle detection system characterized by the following features. [Claim 10] An obstacle detection system according to claim 1, The aforementioned controller, If the output signal of the aforementioned sensor n is not updated for a certain period of time, it is determined that a malfunction has occurred. Obstacle detection system. [Claim 11] An obstacle detection system according to claim 1, The aforementioned controller, Based on statistical information such as the average brightness, brightness variance, and brightness histogram for the entire image or for each area, and the differences in statistical information for each area, the cause of the malfunction of the aforementioned sensor n is estimated. The crew of the vehicle is instructed to take measures to resolve the aforementioned cause. Obstacle detection system. [Claim 12] An obstacle detection system according to claim 1, The nth sensor and the qth sensor (where q is an integer between 1 and M, other than n) constitute a stereo camera sensor. When the signal processing unit is performing obstacle detection using a monocular image with the n sensor as input, The controller switches to the monocular image, which is input from the q sensor, to perform obstacle detection. Obstacle detection system. [Claim 13] A train equipped with a first obstacle detection system and a second obstacle detection system, which are obstacle detection systems according to claim 4, The first obstacle detection system is provided in the leading car of the train, and the second obstacle detection system is provided in the last car of the train. The first obstacle detection system detects an obstacle when the train is moving in the direction of travel, and the second obstacle detection system detects an obstacle when the train is moving in the reverse direction opposite to the direction of travel. The train has communication means for the controller of the first obstacle detection system and the controller of the second obstacle detection system to exchange information. If a malfunction is detected in the first obstacle detection system, The controller of the first obstacle detection system is: The system checks the health of the second obstacle detection system, and in addition to the information regarding the confirmed health, it determines whether or not to change the direction of travel, or the location at which to change the direction of travel, based on at least one of the following: the vehicle's current location information, route map information, the presence or absence of passengers, a location where assistance from human resources can be obtained, and the upper limit of the travel speed calculated by the controller of the first obstacle detection system. A train characterized by the following features.

Images