Abnormality determination device

Abstract

To provide an abnormality determination device capable of determining abnormality of peripheral recognition performance of an automatic drive system early.SOLUTION: An abnormality determination device 6 comprises an information acquisition part 13 which acquires determination information including at least any of a recognition result of an external situation, a state of intervention operation for drive by a driver, and vehicle behavior, a similarity determination part 14 which determines whether the situation that the determination information shows is similar to a predetermined abnormality determination situation by predetermined similarity or more, and an abnormality determination part 15 which determines whether peripheral recognition performance of an automatic drive system 1 is abnormal. When it is determined that the abnormality determination situation and the situation that the determination information shows are similar to each other by the predetermined similarity or more, the abnormality determination part 15 changes an abnormality determination threshold used for abnormality determination so as to make it easier to determine that the peripheral recognition performance of the automatic drive system 1 is abnormal.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an abnormality determination device that determines whether or not there is an abnormality in an autonomous driving system. [Background technology]

[0002] For example, Patent Document 1 describes a device that alerts a vehicle driver. The device acquires the external conditions of the vehicle. Based on the acquired external conditions, the device alerts the driver when there is a possibility that the vehicle will behave the same or similarly to past vehicle behavior. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-159410 A Summary of the Invention [Problem to be solved by the invention]

[0004] The above-mentioned device determines that an abnormality has occurred and warns the driver when the behavior is predicted to be similar to past behavior. Therefore, the criterion for determining whether or not an abnormality exists is only whether or not the behavior is similar to past behavior, and it is not possible to determine an abnormality early depending on the situation.

[0005] For this reason, the present disclosure describes an abnormality determination device that is capable of early detection of abnormalities in the surrounding recognition performance of an autonomous driving system. [Means for solving the problem]

[0006] One aspect of the present disclosure is an abnormality determination device that determines whether or not there is an abnormality in a vehicle's autonomous driving system, and includes an information acquisition unit that acquires determination information including at least one of the results of recognition of the vehicle's external situation, the status of any driving intervention operations by the driver performed during autonomous driving, and the vehicle behavior of the vehicle, a similarity determination unit that determines whether a predetermined abnormality determination situation and a situation indicated by the determination information are similar to each other by a predetermined similarity level or more, and an abnormality determination unit that determines whether or not there is an abnormality in the surrounding recognition performance of the autonomous driving system using a predetermined abnormality determination threshold, and the abnormality determination unit changes the abnormality determination threshold so as to make it easier to determine that there is an abnormality in the surrounding recognition performance of the autonomous driving system when it is determined that the abnormality determination situation and the situation indicated by the determination information are similar to each other by a predetermined similarity level or more, compared to when it is not determined that the abnormality determination situation and the situation indicated by the determination information are similar to each other by a predetermined similarity level or more.

[0007] In the above-mentioned abnormality judgment device, the judgment information acquired by the information acquisition unit includes the recognition result of the external condition of the vehicle, and the abnormality in the surrounding recognition performance judged by the abnormality judgment unit is an abnormality in the external sensor that detects the external condition of the vehicle, or an abnormality in the recognition of the external condition of the vehicle, and when it is judged that the external condition of the vehicle indicated by the abnormality judgment status and the external condition of the vehicle indicated by the judgment information are similar to each other to a predetermined degree or more, the abnormality judgment unit may change the abnormality judgment threshold for determining whether or not there is an abnormality in the external sensor so that it is easier to determine that there is an abnormality in the external sensor, compared to when it is not judged to be similar to each other to the predetermined degree or more, or may change the abnormality judgment threshold for determining whether or not there is an abnormality in the recognition of the external condition of the vehicle so that it is easier to determine that there is an abnormality in the recognition of the external condition of the vehicle.

[0008] In the above-mentioned abnormality judgment device, the judgment information acquired by the information acquisition unit includes the status of the driver's driving intervention operation, and the abnormality in the surrounding recognition performance judged by the abnormality judgment unit is an abnormality in an external sensor that detects the external situation of the vehicle, or an abnormality in the recognition of the vehicle's external situation, and when the driving intervention operation indicated by the abnormality judgment status and the driving intervention operation by the driver indicated by the judgment information are judged to be similar to each other to a predetermined degree or more, the abnormality judgment unit may change the abnormality judgment threshold for determining whether or not there is an abnormality in the external sensor so that it is easier to determine that there is an abnormality in the external sensor, compared to when it is not judged to be similar to each other to the predetermined degree or more, or may change the abnormality judgment threshold for determining whether or not there is an abnormality in the recognition of the external situation so that it is easier to determine that there is an abnormality in the recognition of the vehicle's external situation.

[0009] In the above-mentioned abnormality judgment device, the judgment information acquired by the information acquisition unit includes the vehicle behavior of the vehicle, and the abnormality in the surrounding recognition performance judged by the abnormality judgment unit is an abnormality in an external sensor that detects the external situation of the vehicle, or an abnormality in the recognition of the external situation of the vehicle, and when it is judged that the vehicle behavior indicated by the abnormality judgment status and the vehicle behavior indicated by the judgment information are similar to each other to a predetermined degree or more, the abnormality judgment unit may change the abnormality judgment threshold for determining whether or not there is an abnormality in the external sensor so that it is easier to determine that there is an abnormality in the external sensor, compared to when it is not judged to be similar to each other to the predetermined degree or more, or may change the abnormality judgment threshold for determining whether or not there is an abnormality in the recognition of the external situation so that it is easier to determine that there is an abnormality in the recognition of the external situation of the vehicle. Effect of the Invention

[0010] According to one aspect of the present disclosure, abnormalities in the surrounding recognition performance of an autonomous driving system can be determined early on. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing an example of an autonomous driving system including an abnormality determination device. [Diagram 2]FIG. 2 is a flowchart showing a flow of a process for determining whether or not there is an abnormality in the surrounding recognition performance, which is performed by the abnormality determination device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Exemplary embodiments will now be described with reference to the drawings.

[0013] The autonomous driving system 1 shown in FIG. 1 is mounted on a host vehicle (vehicle) V that is capable of driving autonomously. In other words, the host vehicle V is an autonomous driving vehicle. The autonomous driving system 1 executes autonomous driving to drive the host vehicle V autonomously. Note that some of the functions of the autonomous driving system 1 may be installed outside the host vehicle V. The autonomous driving system 1 includes an external sensor 2, an internal sensor 3, an HMI [Human Machine Interface] 4, and an ECU [Electronic Control Unit] 5.

[0014] The external sensor 2 is an on-board sensor that detects the external environment of the host vehicle V. The external sensor 2 may include a camera. The camera is an imaging device that captures images of the external environment of the host vehicle V. The camera is provided, for example, on the back side of the windshield of the host vehicle V, and captures images of the area in front of the vehicle. The camera transmits imaging information related to the external environment of the host vehicle V to the ECU 5. The camera may be a monocular camera or a stereo camera. Multiple cameras may be provided. The camera may capture images of the area in front of the host vehicle V, as well as the left and right sides, etc.

[0015] The external sensor 2 may include a radar sensor. The radar sensor is a detection device that detects objects around the vehicle V by using radio waves (e.g., millimeter waves) or light. The radar sensor includes, for example, a millimeter wave radar or a lidar (LIDAR: Light Detection and Ranging). The radar sensor detects objects by transmitting radio waves or light to the periphery of the vehicle V and receiving the radio waves or light reflected by the objects. The radar sensor transmits information about the detected objects to the ECU 5.

[0016] The internal sensor 3 is an in-vehicle sensor that detects the state of the host vehicle V. The internal sensor 3 may include, for example, a vehicle speed sensor that detects the speed of the host vehicle V, an acceleration sensor that detects the acceleration of the host vehicle V, a yaw rate sensor that detects the yaw rate of the host vehicle V, a steering angle sensor that detects the angle of the steering operation by the driver, an accelerator sensor that detects the amount of depression of the accelerator pedal by the driver, and a brake sensor that detects the amount of depression of the brake pedal by the driver.

[0017] The HMI 4 is an interface for inputting and outputting information between the vehicle V and the occupants. The HMI 4 has a display, a speaker, and the like.

[0018] The ECU 5 is an electronic control unit having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The ECU 5, for example, loads a program recorded in the ROM into the RAM and executes the program loaded into the RAM with the CPU, thereby realizing various functions. The ECU 5 may be composed of multiple electronic units.

[0019] The ECU 5 functionally includes a recognition unit 11, a driving execution unit 12, an information acquisition unit 13, a similarity determination unit 14, and an abnormality determination unit 15. In this embodiment, the information acquisition unit 13, the similarity determination unit 14, and the abnormality determination unit 15 function as an abnormality determination device 6 that determines whether or not an abnormality exists in the autonomous driving system 1 of the host vehicle V.

[0020] The recognition unit 11 recognizes the external situation of the host vehicle V based on the detection results of the external sensor 2. The external situation also includes information on targets around the host vehicle V. For example, the recognition unit 11 can recognize surrounding targets using AI [Artificial Intelligence] technology such as machine learning based on the detection results of the external sensor 2. Targets recognized by the recognition unit 11 include, for example, surrounding vehicles, white lines (division lines) on the road, pedestrians, etc. The recognition unit 11 can recognize the type of target in addition to the position and shape of the target.

[0021] The driving execution unit 12 executes automatic driving of the host vehicle V based on a well-known method. The driving execution unit 12 can control the driving of the host vehicle V by issuing instructions to actuators (drive actuators, brake actuators, steering actuators, etc.) used to control the driving of the host vehicle V. For example, the driving execution unit 12 generates a route plan for automatic driving based on the recognition results of the recognition unit 11, etc., and controls the driving of the host vehicle V according to the route plan.

[0022] The information acquisition unit 13 acquires judgment information used to judge the presence or absence of an abnormality in the autonomous driving system 1. The judgment information includes at least one of the result of recognition of the external situation of the host vehicle V, the state of the driver's intervention in driving performed during autonomous driving, and the vehicle behavior of the host vehicle V.

[0023] The information acquisition unit 13 can acquire the recognition result of the recognition unit 11 as the recognition result of the external situation of the vehicle V. The recognition result of the external situation may include the reliability (confidence) of the recognition of the recognized object and the target such as the lane marking. The recognition result of the external situation may include information on the temporal stability (continuity) of the recognition of the recognized target. When a target is recognized using a plurality of sensors, the recognition result of the external situation may include information on the consistency of the recognition results between the sensors. The recognition result of the external situation may include the recognition result of the recognition unit 11 of the target grasped based on map information or the like. The recognition result of the external situation may include the effectiveness of the sensor used for recognition. This effectiveness may be set to decrease, for example, in the case of rain or nighttime, may be set to decrease when the object to be recognized is small, or may be set to decrease when there is an abnormality in the sensor. For example, there are cases where the recognition result of the surrounding target can be acquired from other vehicles or the like in the vicinity. In this case, the recognition result of the external situation may include the consistency between the recognition result of the recognition unit 11 and the recognition result performed by the other vehicles or the like.

[0024] The information acquisition unit 13 can acquire the status of the driver's intervention in driving based on the detection result of the internal sensor 3. For example, the status of the intervention may include the driver's steering operation, accelerator pedal operation, and brake pedal operation.

[0025] The information acquisition unit 13 can acquire the vehicle behavior of the host vehicle V based on the detection result of the internal sensor 3. This vehicle behavior may be the behavior of the host vehicle V during autonomous driving. The behavior of the host vehicle V may include the approach status to surrounding vehicles and the approach status to lane markings.

[0026] The similarity determination unit 14 determines whether a predetermined abnormality determination situation and a situation indicated by the determination information acquired by the information acquisition unit 13 are similar to each other by a predetermined similarity or more. As the abnormality determination situation, a situation corresponding to the determination information to be compared is determined in advance. The abnormality determination situation may be determined in advance based on, for example, a situation in which an abnormality occurred in the surrounding recognition performance in the autonomous driving system 1 in the past. The predetermined similarity is determined in advance according to the content of the determination information to be compared.

[0027] The abnormality determination unit 15 determines the presence or absence of an abnormality in the surrounding recognition performance of the autonomous driving system 1 using a preset abnormality determination threshold. The abnormality determination unit 15 can determine the presence or absence of an abnormality based on the abnormality determination threshold. The abnormality in the surrounding recognition performance determined by the abnormality determination unit 15 includes an abnormality in the external sensor 2 that detects the external situation of the host vehicle V, or an abnormality in the recognition of the external situation of the host vehicle V. The abnormality in recognition may include, for example, erroneous recognition of the type of target.

[0028] The abnormality determination unit 15 can change the abnormality determination threshold used to determine whether or not there is an abnormality, based on the determination result of the similarity determination unit 14. Here, when it is determined that the abnormality determination situation and the situation indicated by the determination information are similar to each other by a predetermined similarity or more, the abnormality determination unit 15 changes the abnormality determination threshold so as to make it easier to determine that there is an abnormality in the surrounding recognition performance of the autonomous driving system 1, compared to when it is not determined that they are similar to each other by the predetermined similarity or more. In other words, when the recognition result of the external situation, etc. is similar to the abnormality determination situation, the abnormality determination unit 15 can more easily determine that there is an abnormality in the surrounding recognition performance of the autonomous driving system 1.

[0029] In this way, when the situation is similar to a predetermined abnormality judgment situation, the abnormality judgment unit 15 changes the abnormality judgment threshold so as to make it easier to judge that there is an abnormality. As a result, the abnormality judgment device 6 can quickly determine that there is an abnormality in the surrounding recognition performance of the autonomous driving system 1 by changing the abnormality judgment threshold.

[0030] More specifically, the abnormality determination unit 15 can determine the presence or absence of an abnormality in the surrounding recognition performance of the autonomous driving system 1 by, for example, any one of the following first to third methods. Two or more of the first to third methods may be combined.

[0031] (First Method) When the presence or absence of an abnormality is determined by the first method, the determination information acquired by the information acquisition unit 13 includes a recognition result of the external situation of the host vehicle V. In this case, the similarity determination unit 14 determines whether the external situation of the host vehicle V indicated by the predetermined abnormality determination situation and the external situation of the host vehicle V indicated by the determination information acquired by the information acquisition unit 13 are similar to each other by a predetermined similarity or more.

[0032] When the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity, the abnormality determination unit 15 changes the abnormality determination threshold for determining whether or not there is an abnormality in the external sensor 2 so as to make it easier to determine that there is an abnormality in the external sensor compared to when the similarity determination unit 14 has not determined that there is an abnormality. Alternatively, when the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity, the abnormality determination unit 15 changes the abnormality determination threshold for determining whether or not there is an abnormality in the recognition of the external situation of the host vehicle V so as to make it easier to determine that there is an abnormality in the recognition of the external situation of the host vehicle V compared to when the similarity determination unit 14 has not determined that there is an abnormality. The abnormality determination unit 15 uses the abnormality determination threshold set based on the determination result of the similarity determination unit 14 to determine whether or not there is an abnormality in the external sensor 2 or the recognition of the external situation.

[0033] (Second Method) When the second method is used to determine whether or not there is an abnormality, the state of the driver's intervention in driving is included in the determination information acquired by the information acquisition unit 13. In this case, the similarity determination unit 14 determines whether or not the intervention in driving indicated by the predetermined abnormality determination state and the intervention in driving indicated by the determination information acquired by the information acquisition unit 13 are similar to each other by a predetermined similarity or more.

[0034] When the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity, the abnormality determination unit 15 changes the abnormality determination threshold for determining whether or not there is an abnormality in the external sensor 2 so as to make it easier to determine that there is an abnormality in the external sensor 2 compared to when the similarity determination unit 14 has not determined that the similarity is equal to or greater than the predetermined similarity, or when the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity, the abnormality determination unit 15 changes the abnormality determination threshold for determining whether or not there is an abnormality in the recognition of the external situation so as to make it easier to determine that there is an abnormality in the recognition of the external situation of the host vehicle V compared to when the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity. The abnormality determination unit 15 determines whether or not there is an abnormality in the external sensor 2 or the recognition of the external situation using the abnormality determination threshold set based on the determination result of the similarity determination unit 14.

[0035] (Third Method) When the presence or absence of an abnormality is determined by the third method, the determination information acquired by the information acquisition unit 13 includes the vehicle behavior of the host vehicle V. In this case, the similarity determination unit 14 determines whether the vehicle behavior indicated by the predetermined abnormality determination situation and the vehicle behavior indicated by the determination information acquired by the information acquisition unit 13 are similar to each other by a predetermined similarity level or more.

[0036] When the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity, the abnormality determination unit 15 changes the abnormality determination threshold for determining whether or not there is an abnormality in the external sensor 2 so as to make it easier to determine that there is an abnormality in the external sensor 2 compared to when the similarity determination unit 14 has not determined that there is a similarity equal to or greater than the predetermined similarity. Alternatively, when the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity, the abnormality determination unit 15 changes the abnormality determination threshold for determining whether or not there is an abnormality in the recognition of the external situation of the host vehicle V so as to make it easier to determine that there is an abnormality in the recognition of the external situation of the host vehicle V compared to when the similarity determination unit 14 has not determined that there is a similarity equal to or greater than the predetermined similarity. The abnormality determination unit 15 uses the abnormality determination threshold set based on the determination result of the similarity determination unit 14 to determine whether or not there is an abnormality in the external sensor 2 or whether or not there is an abnormality in the recognition of the external situation.

[0037] In each of the above-mentioned methods, the abnormality determination unit 15 may change the abnormality determination threshold when the number of times that the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity is equal to or greater than a predetermined number of times. In each of the above-mentioned methods, the abnormality determination unit 15 may change the abnormality determination threshold when the frequency at which the similarity determination unit 14 has determined that the similarity is equal to or greater than the predetermined similarity is equal to or greater than a predetermined frequency. By changing the abnormality determination threshold based on these, the abnormality determination unit 15 can more appropriately determine whether or not there is an abnormality in the surrounding recognition performance.

[0038] In this way, in each of the above methods, the similarity determination unit 14 determines whether the abnormality determination situation is similar to or greater than a predetermined similarity between the recognition result of the external situation of the vehicle V, the situation of the driver's intervention in driving, or the vehicle behavior of the vehicle V. The abnormality determination unit 15 changes the abnormality determination threshold based on the determination result of the similarity determination unit 14, and determines the presence or absence of an abnormality. This allows the abnormality determination device 6 to more appropriately determine an abnormality in the surrounding recognition performance of the autonomous driving system 1 based on the recognition result of the external situation of the vehicle V, etc.

[0039] Furthermore, the abnormality determination unit 15 determines the presence or absence of an abnormality in the external sensor 2 or an abnormality in the recognition of the external situation of the vehicle V as the determination of an abnormality in the surrounding recognition performance of the autonomous driving system 1. This allows the abnormality determination device 6 to more appropriately determine the presence or absence of an abnormality in the external sensor 2 that is of high importance for the autonomous driving of the vehicle V or the abnormality in the recognition of the external situation of the vehicle V. Note that, when determining the presence or absence of an abnormality, the abnormality determination device 6 may determine the presence or absence of an abnormality in the external sensor 2 that detects the front, or the presence or absence of an abnormality in the recognition of the front. In this case, the abnormality determination device 6 can quickly determine the abnormality of the front sensor or the abnormality in the recognition of the front situation, which are of high importance for the autonomous driving of the vehicle V.

[0040] In addition, if the abnormality determination unit 15 determines that there is an abnormality in the surrounding recognition performance of the autonomous driving system 1, it notifies the occupants of the vehicle V using the HMI 4 that there is an abnormality.

[0041] In this embodiment, as an example, the abnormality determination device 6 is provided integrally with the automatic driving system 1. However, the abnormality determination device 6 may be provided separately from the automatic driving system 1 that performs automatic driving. In addition, for example, the abnormality determination device 6 may also notify a monitor other than the occupants of the vehicle V. In this case, for example, the abnormality determination device 6 may notify a monitor (for example, a remote operator of the vehicle V) in an information center that manages the traveling of multiple vehicles.

[0042] Next, a flow of the process of determining surrounding recognition performance performed by the abnormality determination device 6 will be described. The process shown in Fig. 2 is performed, for example, while the vehicle V is in autonomous driving mode. However, this process may be performed at a timing other than when the vehicle V is in autonomous driving mode. In addition, when the process shown in Fig. 2 reaches an end, the process is restarted from the start after a predetermined time.

[0043] 2, in S101, the information acquisition unit 13 acquires the recognition result of the recognition unit 11 as judgment information used to judge the presence or absence of an abnormality in the autonomous driving system 1. In S102, the similarity judgment unit 14 judges whether a predetermined abnormality judgment situation and a situation indicated by the judgment information are similar to each other by a predetermined similarity or more. If they are not similar to each other by the predetermined similarity or more (S103: NO), the abnormality judgment device 6 performs the process of S105. If they are similar to each other by the predetermined similarity or more (S103: YES), in S104, the abnormality judgment unit 15 changes the abnormality judgment threshold value so that an abnormality is more likely to be judged.

[0044] In S105, the abnormality determination unit 15 uses the various methods described above to determine whether or not there is an abnormality in the surrounding recognition performance of the autonomous driving system 1. If there is an abnormality in the surrounding recognition performance (S105: YES), in S106 the abnormality determination unit 15 notifies the presence of an abnormality in the surrounding recognition performance using the HMI 4. If there is no abnormality in the surrounding recognition performance (S105: NO), the abnormality determination device 6 restarts the process from the start after a predetermined time.

[0045] As described above, the abnormality determination device 6 changes the abnormality determination threshold so as to make it easier to determine that there is an abnormality in the surrounding recognition performance in a situation similar to the abnormality determination situation. This allows the abnormality determination device 6 to quickly determine an abnormality in the surrounding recognition performance of the autonomous driving system 1 in a situation similar to the abnormality determination situation.

[0046] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments. At least a portion of the embodiments and various examples described above may be combined in any desired manner. [Explanation of symbols]

[0047] 1...Autonomous driving system, 2...External sensor, 13...Information acquisition unit, 14...Similarity determination unit, 15...Abnormality determination unit, V...Own vehicle (vehicle).

Claims

1. An abnormality determination device for determining whether or not there is an abnormality in an automatic driving system of a vehicle, An information acquisition unit that acquires determination information including at least one of a result of recognizing an external situation of the vehicle, a state of an intervention operation of a driver during automatic driving, and a vehicle behavior of the vehicle; a similarity determination unit that determines whether a predetermined abnormality determination situation and a situation indicated by the determination information are similar to each other by a predetermined similarity level or more; an abnormality determination unit that determines whether or not there is an abnormality in the surrounding recognition performance of the autonomous driving system using a preset abnormality determination threshold; Equipped with The abnormality judgment unit changes the abnormality judgment threshold when it is judged that the abnormality judgment situation and the situation indicated by the judgment information are similar to each other to a predetermined degree or more, so that it becomes easier to judge that there is an abnormality in the surrounding recognition performance of the autonomous driving system, compared to when it is not judged that the abnormality judgment situation and the situation indicated by the judgment information are similar to each other to the predetermined degree or more.

2. The determination information acquired by the information acquisition unit includes a recognition result of an external situation of the vehicle, The abnormality in the surrounding recognition performance determined by the abnormality determination unit is an abnormality in an external sensor that detects an external situation of the vehicle, or an abnormality in recognition of the external situation of the vehicle, 2. The abnormality judgment device according to claim 1, wherein when it is judged that the external situation of the vehicle indicated by the abnormality judgment status and the external situation of the vehicle indicated by the judgment information are similar to each other by a predetermined degree or more, the abnormality judgment unit changes the abnormality judgment threshold for determining whether or not there is an abnormality in the external sensor so that it is easier to determine that there is an abnormality in the external sensor, compared to when it is not judged that the external situation is similar to each other by the predetermined degree or more.

3. The determination information acquired by the information acquisition unit includes a situation of an intervention operation of the driver, The abnormality in the surrounding recognition performance determined by the abnormality determination unit is an abnormality in an external sensor that detects an external situation of the vehicle, or an abnormality in recognition of the external situation of the vehicle, 2. The abnormality judgment device according to claim 1, wherein, when it is determined that the driving intervention operation indicated by the abnormality judgment status and the driving intervention operation by the driver indicated by the judgment information are similar to each other by a predetermined degree or more, the abnormality judgment unit changes the abnormality judgment threshold for determining whether or not there is an abnormality in the external sensor so that it is easier to determine that there is an abnormality in the external sensor, compared to when it is not determined that the driving intervention operation is similar to each other by the predetermined degree or more.

4. The determination information acquired by the information acquisition unit includes a vehicle behavior of the vehicle, The abnormality in the surrounding recognition performance determined by the abnormality determination unit is an abnormality in an external sensor that detects an external situation of the vehicle, or an abnormality in recognition of the external situation of the vehicle, 2. The abnormality judgment device according to claim 1, wherein when the vehicle behavior indicated by the abnormality judgment status and the vehicle behavior indicated by the judgment information are judged to be similar to each other to a predetermined degree or more, the abnormality judgment unit changes the abnormality judgment threshold for determining whether or not there is an abnormality in the external sensor so that it is easier to determine that there is an abnormality in the external sensor, compared to when the vehicle behavior is not judged to be similar to the predetermined degree or more.

Images