Detection method, device, equipment and storage medium for autonomous driving vehicle dragon drawing behavior

Abstract

The present disclosure provides a method, device, equipment and storage medium for detecting the dragon-drawing behavior of an autonomous driving vehicle, and relates to the field of data processing technology, and in particular to the field of autonomous driving technology. The specific implementation scheme is: after obtaining the current angular velocity of the autonomous driving vehicle, the angular velocity peak or trough of the autonomous driving vehicle is determined based on the current angular velocity of the autonomous driving vehicle and the historical angular velocity of the autonomous driving vehicle, and then it is determined whether the angular velocity peak or trough of the autonomous driving vehicle meets the preset dragon-drawing condition. If so, it is determined that the autonomous driving vehicle has exhibited the dragon-drawing behavior. In the application of the embodiments of the present disclosure, the angular velocity peak or trough of the autonomous driving vehicle is used to determine whether the autonomous driving vehicle has exhibited the dragon-drawing behavior, so that the dragon-drawing behavior of the autonomous driving vehicle can be discovered in a timely manner, and then the autonomous driving vehicle can be effectively taken over in an emergency to avoid accidents and ensure the safety of people and vehicles.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to the field of autonomous driving technology. Background Art

[0002] During the autonomous driving process, due to abnormalities in the autonomous driving vehicle system or decision-making module, the planned path may deviate from the actual position and posture of the autonomous driving vehicle. This will cause the autonomous driving vehicle to behave like a dragon, that is, the autonomous driving vehicle will swing back and forth on the road. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, device and storage medium for detecting the dragon-drawing behavior of an autonomous driving vehicle, so as to detect the dragon-drawing behavior of an autonomous driving vehicle.

[0004] According to one aspect of the present disclosure, a method for detecting dragon-drawing behavior of an autonomous driving vehicle is provided, comprising:

[0005] Get the current angular velocity of the autonomous vehicle;

[0006] Determining a peak or trough in the angular velocity of the autonomous vehicle based on the current angular velocity of the autonomous vehicle and the historical angular velocity of the autonomous vehicle;

[0007] Determining whether a peak or trough of the angular velocity of the autonomous driving vehicle satisfies a preset dragon drawing condition;

[0008] If the angular velocity peak or trough meets the preset dragon-drawing condition, it is determined that the autonomous driving vehicle exhibits dragon-drawing behavior.

[0009] According to another aspect of the present disclosure, a device for detecting dragon-drawing behavior of an autonomous driving vehicle is provided, comprising:

[0010] The current angular velocity acquisition module is used to obtain the current angular velocity of the autonomous driving vehicle;

[0011] a peak or trough determination module, configured to determine a peak or trough of an angular velocity of the autonomous driving vehicle based on a current angular velocity of the autonomous driving vehicle and a historical angular velocity of the autonomous driving vehicle;

[0012] A peak or trough judgment module, used to determine whether the angular velocity peak or trough of the autonomous driving vehicle meets a preset dragon drawing condition;

[0013] The dragon-drawing behavior determination module is used to determine that the autonomous driving vehicle exhibits a dragon-drawing behavior if the angular velocity peak or trough meets the preset dragon-drawing condition.

[0014] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned methods for detecting the dragon-drawing behavior of an autonomous driving vehicle.

[0018] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any of the above-mentioned methods for detecting the dragon-drawing behavior of an autonomous driving vehicle.

[0019] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for detecting the dragon-drawing behavior of an autonomous driving vehicle.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a schematic diagram of a first embodiment of a method for detecting dragon-drawing behavior of an autonomous driving vehicle provided by the present disclosure;

[0023] Figure 2 is a schematic diagram of the angular velocity of the autonomous driving vehicle in the present disclosure;

[0024] Figure 3 is a schematic diagram of a second embodiment of a method for detecting dragon-drawing behavior of an autonomous driving vehicle provided by the present disclosure;

[0025] Figure 4 is a schematic diagram of a process for determining potential angular velocity peaks or troughs in the present disclosure;

[0026] Figure 5 This is a schematic diagram of a process for determining a true angular velocity peak or trough in the present disclosure;

[0027] Figure 6a This is a flowchart of a specific example of detecting the dragon-drawing behavior of an autonomous driving vehicle in the present disclosure;

[0028] Figure 6bThis is a schematic diagram of detecting the dragon-drawing behavior of an autonomous driving vehicle in the present disclosure;

[0029] Figure 7 is a schematic diagram of a first embodiment of a device for detecting dragon-drawing behavior of an autonomous driving vehicle provided by the present disclosure;

[0030] Figure 8 This is a block diagram of an electronic device used to implement the method for detecting the dragon-drawing behavior of an autonomous driving vehicle according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] For various reasons, such as system anomalies or illogical planning, autonomous vehicles can exhibit swerving behavior, which is difficult to prevent through planning alone. When autonomous vehicles engage in swerving behavior, they are highly susceptible to collisions or veer off the road, posing a high risk. Currently, there is no device capable of detecting swerving behavior, making it difficult to detect and implement timely countermeasures to mitigate the risk.

[0033] Based on this, the present disclosure provides a method, device, electronic device, and storage medium for detecting the dragon-drawing behavior of an autonomous vehicle. The following first provides an exemplary description of the method for detecting the dragon-drawing behavior of an autonomous vehicle provided by the present disclosure.

[0034] The method for detecting dragon-drawing behavior of an autonomous vehicle provided by the present disclosure can be applied to autonomous vehicle systems, etc. Figure 1 , Figure 1 FIG1 is a schematic diagram of a first embodiment of a method for detecting dragon-drawing behavior of an autonomous driving vehicle according to the present disclosure. The method may include the following steps:

[0035] Step S110, obtaining the current angular velocity of the autonomous driving vehicle.

[0036] In the disclosed embodiment, the angular velocity of the autonomous driving vehicle can be obtained through an angular velocity measurement module built into the autonomous driving vehicle, or through a roadside unit external to the autonomous driving vehicle and having an angular velocity measurement function.

[0037] In the embodiments of the present disclosure, the current angular velocity of the autonomous vehicle can be acquired in real time, or can be acquired periodically at a preset acquisition time interval, such as every 0.2 seconds. This disclosure does not impose any specific limitations on this.

[0038] In the disclosed embodiment, when obtaining the current angular velocity of the autonomous vehicle, the specific value AVcur of the autonomous vehicle's current angular velocity and the acquisition timestamp Tcur of the autonomous vehicle's current angular velocity can be obtained, where Tcur represents the time when AVcur was acquired. In the disclosed embodiment, the positive and negative directions of the angular velocity can be predefined, and accordingly, the specific value of the angular velocity can be a signed value.

[0039] Step S120: Determine the peak or trough of the angular velocity of the autonomous driving vehicle based on the current angular velocity of the autonomous driving vehicle and the historical angular velocity of the autonomous driving vehicle.

[0040] As an embodiment of the present disclosure, Figure 2 As shown, the collected angular velocity of the autonomous driving vehicle can be visualized with the collection time as the horizontal axis (in seconds) and the angular velocity value as the vertical axis (in radians per second). Figure 2 The angular velocity peak shown in is the angular velocity maximum. Figure 2 The angular velocity troughs shown are the angular velocity minima.

[0041] Depend on Figure 2 It can be seen that at the angular velocity peak, the angular velocity changes from an upward trend to a downward trend; at the angular velocity trough, the angular velocity changes from a downward trend to an upward trend. Therefore, in the embodiments of the present disclosure, based on the current angular velocity of the autonomous vehicle and the historical angular velocity of the autonomous vehicle, the change in the angular velocity trend of the autonomous vehicle can be determined, and the angular velocity peak or trough can be determined.

[0042] Step S130, determining whether the angular velocity peak or trough of the autonomous driving vehicle meets the preset dragon drawing condition.

[0043] In the embodiment of the present disclosure, the preset dragon drawing condition may be: the time difference between two angular velocity peaks or troughs is less than a preset duration, and the angular velocities have opposite signs.

[0044] As described above, the dragon-drawing behavior of an autonomous vehicle refers to the vehicle swinging back and forth on the road. Therefore, if the vehicle exhibits dragon-drawing behavior, the vehicle's angular velocity will experience significant changes in value. As described above, an angular velocity peak or trough is a maximum or minimum angular velocity value, that is, at the angular velocity peak or trough, the angular velocity value may vary significantly. Therefore, in the disclosed embodiments, it is possible to determine whether the angular velocity peak or trough meets the aforementioned preset dragon-drawing conditions, thereby more quickly detecting the autonomous vehicle's dragon-drawing behavior.

[0045] In the embodiment of the present disclosure, the preset duration can be preset manually. For example, the preset duration can be 10 seconds, 8 seconds, 7 seconds, etc.

[0046] Step S140: If the angular velocity peak or trough meets the preset dragon-drawing condition, it is determined that the autonomous driving vehicle exhibits dragon-drawing behavior.

[0047] In this disclosed embodiment, if a vehicle is detected to be exhibiting dragon-drawing behavior, an anomaly can be reported, and the autonomous vehicle can be urgently stopped to prevent an accident. The autonomous vehicle can also be controlled to emit a warning sound to alert people around it to avoid the vehicle.

[0048] In the disclosed embodiment, after obtaining the current angular velocity of the autonomous vehicle, the angular velocity peak or trough of the autonomous vehicle is determined based on the current angular velocity of the autonomous vehicle and the historical angular velocities of the autonomous vehicle. It is then determined whether the angular velocity peak or trough of the autonomous vehicle satisfies a preset dragon-drawing condition. If so, it is determined that the autonomous vehicle is exhibiting dragon-drawing behavior. By using the disclosed embodiment, determining whether the autonomous vehicle is exhibiting dragon-drawing behavior based on the angular velocity peak or trough of the autonomous vehicle can timely detect the autonomous vehicle's dragon-drawing behavior, thereby effectively taking emergency control of the autonomous vehicle, avoiding accidents, and ensuring the safety of both the driver and the vehicle.

[0049] based on Figure 1 ,like Figure 3 As shown, in one embodiment of the present disclosure, the above step S120 can be refined as follows:

[0050] Step S121: Based on the current angular velocity of the autonomous driving vehicle and the historical angular velocity of the autonomous driving vehicle, a newly appeared angular velocity peak or trough is determined as a new potential angular velocity peak or trough.

[0051] In the disclosed embodiment, potential angular velocity peaks or troughs can be recorded, and the recorded historical potential angular velocity peaks or troughs can be updated. As a specific implementation method, when a potential angular velocity peak or trough appears, the following data can be recorded and stored: the peak value of the potential angular velocity peak or the trough value of the potential angular velocity trough, and the acquisition time of the potential angular velocity peak or trough. At the same time, the potential angular velocity peak or trough that appears can also be marked as a potential angular velocity peak or a potential angular velocity trough. The above-mentioned peak value and trough value can both be values ​​with positive and negative signs.

[0052] Step S122: Based on the new potential angular velocity peak or trough and the historical potential angular velocity peak or trough, determine a historical potential angular velocity peak or trough that meets a preset peak or trough condition as a new true angular velocity peak or trough.

[0053] It is understandable that although angular velocity peaks or troughs will be generated when the autonomous driving vehicle swings, angular velocity peaks or troughs may also be generated in other situations, such as when the autonomous driving vehicle's angular velocity fluctuates due to interference from noise signals, or when the autonomous driving vehicle adjusts its direction slightly. Therefore, not every angular velocity peak or trough is generated by the swinging of the autonomous driving vehicle.

[0054] The above-mentioned preset peak or trough conditions can be set manually based on actual application scenarios and / or requirements, and the present disclosure does not limit this. The above-mentioned preset peak or trough conditions will be exemplarily described in steps S1221-S1222 below, and will not be repeated here.

[0055] To distinguish angular velocity peaks or troughs generated by the swinging of an autonomous vehicle, this document identifies these peaks or troughs as true angular velocity peaks or troughs. When an angular velocity peak or trough is detected, it may be a true angular velocity peak or trough caused by the swinging of the autonomous vehicle, or it may be an angular velocity peak or trough caused by fluctuations in the angular velocity of the autonomous vehicle due to interference from a noise signal, or a small directional adjustment of the autonomous vehicle. Therefore, before determining a detected angular velocity peak or trough as a true peak or trough, it can be temporarily identified as a potential angular velocity peak or trough.

[0056] In the disclosed embodiment, true angular velocity peaks and troughs can be recorded. The recorded historical true angular velocity peaks and troughs can also be updated. As a specific implementation, the true angular velocity peak or trough value and the time of acquisition of the angular velocity can be recorded. It can also be marked whether the true angular velocity peak or trough occurs. The true angular velocity peak and trough values ​​can also be signed.

[0057] In one embodiment of the present disclosure, Figure 3 As shown above Figure 1 Step S130 in the embodiment of the present invention is to determine whether the angular velocity peak or trough satisfies the preset dragon drawing condition, which can be further refined as follows:

[0058] Step S131 , determining whether the new true angular velocity peak or trough, and the historical true angular velocity peak or trough, meet a preset dragon drawing condition.

[0059] like Figure 3 As shown above Figure 1 Step S140 in the above process, determining that the autonomous driving vehicle has performed a dragon-drawing behavior, can be further refined as follows:

[0060] Step S141: If the true angular velocity peak or trough meets the preset dragon-drawing condition, it is determined that the autonomous driving vehicle exhibits dragon-drawing behavior.

[0061] In one embodiment of the present disclosure, the above-mentioned preset dragon-drawing condition may also include: the height difference between the two angular velocity peaks or troughs is greater than the preset height difference threshold. It is understandable that even if no dragon-drawing behavior occurs, the autonomous driving vehicle may swing back and forth in a short period of time. For example, an autonomous driving vehicle traveling in a straight line may swing back and forth slightly due to the impact of road bumps. By selecting this embodiment, by adding the criterion of the height difference to the preset dragon-drawing condition, the vehicle's small swing back and forth is avoided from being mistakenly identified as a dragon-drawing behavior, thereby more accurately judging the autonomous driving vehicle's dragon-drawing behavior and reducing misjudgment. The above-mentioned height difference threshold can be manually preset according to actual needs. For example, it can be 20 radians per second, or 10 radians per second, etc., and this is not specifically limited in the present disclosure.

[0062] Accordingly, in this embodiment, it can be determined whether the time difference between the new true angular velocity and the historical true angular velocity peak or trough is less than the preset duration, the angular velocity signs are opposite, and the drop height is greater than the preset drop height threshold.

[0063] As mentioned above, the positive and negative directions of the angular velocity can be manually predetermined. Therefore, the preset dragon-drawing conditions may not specify the direction of the angular velocity. Specifically, the preset dragon-drawing conditions may also include: the time difference between two angular velocity peaks or troughs is less than the preset duration, and the drop height is greater than the preset drop height threshold.

[0064] As can be seen from the above, in the disclosed embodiments, determining whether an autonomous vehicle is engaging in dragon-drawing behavior requires only determining whether the interval between two true angular velocity peaks or troughs satisfies the preset dragon-drawing condition. Furthermore, determining the true angular velocity peaks or troughs requires only the current potential angular velocity peaks or troughs and the recorded potential angular velocity peaks or troughs, eliminating the need to query and compare each historical angular velocity. This reduces the amount of data processing and facilitates implementation.

[0065] As described above, in an embodiment of the present disclosure, the autonomous vehicle angular velocity, potential angular velocity peaks or troughs, and actual angular velocity peaks or troughs may be recorded. In one embodiment of the present disclosure, the historical autonomous vehicle angular velocity may specifically be the most recently acquired autonomous vehicle angular velocity.

[0066] In the disclosed embodiment, the acquisition time of the angular velocity of each autonomous vehicle can be a series of discrete time points. The previously acquired angular velocity of the autonomous vehicle can be: the angular velocity acquired before the current angular velocity and the acquisition time closest to the current angular velocity acquisition time. For example, assuming that angular velocity 1 is acquired at t=0s, angular velocity 2 is acquired at t=0.05s, angular velocity 3 is acquired at t=0.1, and angular velocity 4 is acquired at t=0.15, and the current angular velocity is angular velocity 4, then the previously acquired angular velocity of the autonomous vehicle is angular velocity 3.

[0067] Of course, the previously acquired angular velocity of the autonomous driving vehicle may also be any angular velocity acquired before the current angular velocity and acquired within a preset time period (e.g., 0.15 seconds). Still using the example of angular velocities 1-4, the current angular velocity may be any angular velocity from 1-3.

[0068] As an embodiment of the present disclosure, when recording the last acquired angular velocity of the autonomous driving vehicle, the value AVlast of the last acquired angular velocity of the autonomous driving vehicle and the corresponding timestamp Tlast may be recorded.

[0069] In one embodiment of the present disclosure, the above-mentioned historical potential angular velocity peak or trough may specifically be the previous potential angular velocity peak or trough. In the embodiment of the present disclosure, the above-mentioned previous potential angular velocity peak or trough may be the potential angular velocity peak or trough recorded in the previous round of autonomous driving vehicle dragon drawing behavior detection. As a specific implementation method of the embodiment of the present disclosure, when recording the above-mentioned previous potential angular velocity peak or trough P(v, t), the peak value or valley value Pv of the above-mentioned previous potential angular velocity peak or trough and the corresponding timestamp Pt may be recorded.

[0070] In one embodiment of the present disclosure, the above-mentioned historical true angular velocity peak or trough may refer to the previous true angular velocity peak or trough. For example, it may be the true peak or trough obtained in the previous round of dragon-drawing behavior detection of the autonomous driving vehicle. As a specific implementation of the embodiment of the present disclosure, when recording the above-mentioned previous potential angular velocity peak or trough P'(v, t), the peak value or trough value P'v of the previous true angular velocity peak or trough and the corresponding timestamp P't may be recorded.

[0071] In one embodiment of the present disclosure, based on Figure 1 ,like Figure 3 As shown, the above method may further include:

[0072] Step S350: Update the historical autonomous driving vehicle angular velocity, the historical potential angular velocity peaks or troughs, and the historical true angular velocity peaks or troughs.

[0073] As a specific implementation, if no new angular velocity peak or trough appears, and the current angular velocity of the autonomous driving vehicle is greater than the historical potential angular velocity peak or trough, then the previous potential angular velocity peak or trough and the last acquired angular velocity of the autonomous driving vehicle are updated with the current angular velocity of the autonomous driving vehicle;

[0074] If there is no historical potential angular velocity peak or trough that meets the preset peak or trough conditions, the previous potential angular velocity peak or trough is updated with the new potential angular velocity peak or trough, and the last acquired autonomous driving vehicle angular velocity is updated with the current angular velocity of the autonomous driving vehicle.

[0075] In some embodiments, if the new true angular velocity peaks or troughs, as well as historical true angular velocity peaks or troughs, meet the preset dragon-drawing conditions, it can be determined that the autonomous vehicle is exhibiting dragon-drawing behavior. In other embodiments, if the new true angular velocity peaks or troughs, as well as historical true angular velocity peaks or troughs, do not meet the preset dragon-drawing conditions, in these embodiments, it can be determined that the autonomous vehicle is not exhibiting dragon-drawing behavior, and dragon-drawing behavior detection can continue.

[0076] For example, if the new true angular velocity peak or trough, and the historical true angular velocity peak or trough, do not meet the preset dragon drawing condition, then the new true angular velocity peak or trough is used to update the previous true angular velocity peak or trough, the new potential angular velocity peak or trough is used to update the previous potential angular velocity peak or trough, and the current angular velocity of the autonomous driving vehicle is used to update the last acquired autonomous driving vehicle angular velocity.

[0077] The specific process of updating the previously acquired autonomous driving vehicle angular velocity, the previous potential angular velocity peak or trough, and the previous actual angular velocity peak or trough is described below and is not detailed here.

[0078] In the disclosed embodiment, only the last acquired autonomous vehicle angular velocity, the last potential angular velocity peak or trough, and the last actual angular velocity peak or trough need to be recorded and stored. It is not necessary to store all acquired data. This greatly reduces the amount of data to be stored and saves storage space.

[0079] In one embodiment of the present disclosure, Figure 4 As shown, the above step S121 can be refined as follows:

[0080] Step S1211: Calculate the angular velocity change trend of the current autonomous driving vehicle based on the current angular velocity of the autonomous driving vehicle and the last acquired angular velocity of the autonomous driving vehicle.

[0081] In this embodiment, the current angular velocity change trend Trendcur of the autonomous vehicle can be calculated based on the current angular velocity AVcur and the last acquired angular velocity AVlast. As a specific implementation, if the current angular velocity AVcur is greater than the last acquired angular velocity AVlast, the current angular velocity change trend of the autonomous vehicle is increasing, and Trendcur can be assigned a value of 1. If the current angular velocity AVcur is less than the last acquired angular velocity AVlast, the current angular velocity change trend of the autonomous vehicle is decreasing, and Trendcur can be assigned a value of 0.

[0082] Step S1212: Determine whether the current angular velocity change trend of the autonomous driving vehicle is consistent with the previous angular velocity change trend of the autonomous driving vehicle.

[0083] In the disclosed embodiment, the last angular velocity change trend of the autonomous vehicle, Trendlast, can be recorded. After calculating the value of the current angular velocity change trend of the autonomous vehicle, Trendcur, Trendcur can be compared with the last angular velocity change trend, Trendlast.

[0084] In the disclosed embodiment, the previously recorded angular velocity trend of the autonomous vehicle, Trendlast, can be updated. As a specific implementation, if the autonomous vehicle's current angular velocity determines that the autonomous vehicle is not exhibiting dragon-drawing behavior, the previous angular velocity trend Trendlast can be updated to the value of the current angular velocity trend Trendcur. The next round of autonomous vehicle dragon-drawing behavior detection can then be performed.

[0085] In the disclosed embodiment, the initial values ​​of the previous autonomous vehicle angular velocity AVlast and its corresponding acquisition time Tlast, the current autonomous vehicle angular velocity AVcur and its corresponding acquisition time Tcur, the previous autonomous vehicle angular velocity change trend Trendlast, and the current autonomous vehicle angular velocity change trend Trendcur can all be preset. As a specific implementation, the initial values ​​of AVlast, Tlast, AVcur, and Tcur can be set to 0, while the initial values ​​of Trendlast and Trendcur can be set to 1.

[0086] like Figure 4 As shown, in step S1213, based on the judgment result of whether the angular velocity change trend of the autonomous driving vehicle is consistent, it is determined whether a new angular velocity peak or trough appears.

[0087] In the disclosed embodiment, if the value of the current autonomous vehicle angular velocity change trend Trendcur is different from the value of the previous autonomous vehicle angular velocity change trend Trendlast, that is, the current autonomous vehicle angular velocity change trend is different from the previous autonomous vehicle angular velocity change trend (e.g., the previous autonomous vehicle angular velocity change trend was increasing / decreasing, while the current autonomous vehicle angular velocity change trend is decreasing / increasing), then it can be determined that a new angular velocity peak or trough has occurred.

[0088] Step S1214: taking the newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough.

[0089] In the disclosed embodiment, if a new angular velocity peak or trough is determined, the new angular velocity peak or trough can be used as a potential angular velocity peak or trough for further determination. In this way, the presence of a new angular velocity peak or trough can be determined based on the current angular velocity of the autonomous vehicle, the last acquired angular velocity of the autonomous vehicle, and the last recorded angular velocity change trend of the autonomous vehicle, without having to query all historical data for determination. This allows for faster determination of potential angular velocity peaks or troughs, and reduces the amount of data query required.

[0090] In one embodiment of the present disclosure, after determining that a new angular velocity peak or trough has appeared, the peak value or trough value of the angular velocity peak or trough may be judged again to determine whether the new angular velocity peak or trough is regarded as a potential angular velocity peak or trough.

[0091] Since each angular velocity value in the disclosed embodiment is a signed value, it is possible to determine whether the absolute value of the new angular velocity peak or valley is greater than a preset angular velocity threshold AVDT. If so, the new angular velocity peak or valley can be considered a potential angular velocity peak or valley. If not, the peak or valley value of the new angular velocity peak or valley is within a normal range, and therefore, the new angular velocity peak or valley can be ignored as a potential peak or valley.

[0092] In the embodiment of the present disclosure, if the newly appeared angular velocity peak or trough cannot be used as a potential peak or trough, it is possible to determine whether the current angular velocity of the autonomous driving vehicle is greater than the potential angular velocity peak or trough recorded in the historical record (i.e., determine whether the current angular velocity of the autonomous driving vehicle is greater than the previous potential angular velocity peak, or less than the previous potential angular velocity trough). If the current angular velocity of the autonomous driving vehicle is greater than the previous potential angular velocity peak or trough, the current angular velocity of the autonomous driving vehicle can be used to update the above-mentioned previous potential angular velocity peak or trough. That is, Pv is updated with the value of AVcur, and Pt is updated with the value of Tcur. If the current angular velocity of the autonomous driving vehicle is less than the previous potential angular velocity peak or trough, the current angular velocity of the autonomous driving vehicle can be used to update the last acquired angular velocity of the autonomous driving vehicle. That is, AVlast is updated with the value of AVcur, and Tlast is updated with the value of Tcur. After that, the next round of detection of the autonomous driving vehicle's dragon-drawing behavior can be carried out.

[0093] In one embodiment of the present disclosure, if the value of the current autonomous vehicle angular velocity change trend Trendcur is the same as the value of the previous autonomous vehicle angular velocity change trend Trendlast, that is, it is determined that no new angular velocity peak or trough has appeared. Then, it can be determined whether the historical potential angular velocity peak or trough is empty. If the historical potential angular velocity peak or trough is empty (no potential angular velocity peak or trough has appeared before), AVlast can be updated with the value of AVcur, and Tlast can be updated with the value of Tcur. Then, the next round of autonomous vehicle dragon drawing behavior detection is carried out.

[0094] If the historical potential angular velocity peak or trough is not empty, the magnitude of the current autonomous vehicle angular velocity AVcur relative to the historical potential angular velocity peak or trough Pv can be determined. Specifically, since each angular velocity value recorded in the disclosed embodiment is a signed value, it is possible to determine whether the current autonomous vehicle angular velocity is greater than the potential angular velocity peak, or whether the current autonomous vehicle angular velocity is less than the potential angular velocity trough.

[0095] In the embodiment of the present disclosure, if it is determined that the current angular velocity of the autonomous driving vehicle is greater than the potential angular velocity peak or less than the potential angular velocity trough, that is, no new angular velocity peak or trough appears, and the current angular velocity of the autonomous driving vehicle is greater than the historical potential angular velocity peak or trough, then the current angular velocity AVcur of the autonomous driving vehicle can be used to update the previous potential angular velocity peak or trough Pv and the last acquired angular velocity of the autonomous driving vehicle AVlast, and the acquisition time Tcur of the current angular velocity of the autonomous driving vehicle can be used to update the time Pt ​​of the previous potential angular velocity peak or trough and the time Tlast of the last acquired angular velocity of the autonomous driving vehicle.

[0096] If the autonomous vehicle's current angular velocity is less than the potential angular velocity peak or greater than the potential angular velocity trough, then only the autonomous vehicle's current angular velocity AVcur and Tcur values ​​are used to update the last acquired autonomous vehicle AVlast and Tlast. The last potential angular velocity peak or trough does not need to be updated.

[0097] In one embodiment of the present disclosure, the above step S122, determining the historical potential angular velocity peak or trough that meets the preset peak or trough conditions as the new true angular velocity peak or trough, can be refined into the following steps: Figure 5 As shown:

[0098] Step S1221: Based on the historical potential angular velocity peaks or troughs, determine whether the new potential angular velocity peak or trough is the same as the previous potential angular velocity peak or trough.

[0099] Step S1222: If the new potential angular velocity peak or trough is different from the previous potential angular velocity peak or trough, the previous potential angular velocity peak or trough is used as the actual angular velocity peak or trough.

[0100] That is, in the embodiment of the present disclosure, the preset peak or trough condition may be that the new potential angular velocity peak or trough is different from the previous potential angular velocity peak or trough.

[0101] In the disclosed embodiment, if the previous potential angular velocity peak or trough is the same as the new potential peak or trough, it indicates that the autonomous vehicle's angular velocity did not undergo a significant change in direction during the corresponding period. Therefore, it cannot be determined that the autonomous vehicle is exhibiting dragon-drawing behavior.

[0102] As a specific implementation of the embodiment of the present disclosure, if the previous potential angular velocity peak or trough is the same as the new potential angular velocity peak or trough, that is, there is no historical potential angular velocity peak or trough that meets the preset peak or trough conditions, then the previous potential angular velocity peak or trough may be updated with the new potential angular velocity peak or trough, and the previously acquired autonomous vehicle angular velocity may be updated with the current angular velocity of the autonomous vehicle.

[0103] In the disclosed embodiment, if the new potential angular velocity peak or trough differs from the previous potential angular velocity peak or trough by a single peak or trough, that is, the previous potential angular velocity peak / trough is a potential angular velocity peak / trough, and the new potential angular velocity trough / peak is a potential angular velocity trough / peak, then it can be determined that a historical potential angular velocity peak or trough that meets the preset peak or trough conditions exists. In this way, the previous potential angular velocity peak or trough P(v,t) can be used as the true angular velocity peak or trough. This allows for faster determination of the true angular velocity peak or trough, while minimizing the amount of data query required.

[0104] In one embodiment of the present disclosure, after determining the presence of a historical potential angular velocity peak or trough that meets the preset peak or trough conditions, it is further determined whether the height / depth of the historical potential angular velocity peak value or trough value is greater than a preset peak absolute threshold PAT (peak absolute threshold). This peak threshold can be manually preset based on actual needs. This disclosure does not specifically limit this.

[0105] If the height / depth of the historical potential angular velocity peak or trough is no greater than the preset peak threshold, the vehicle's angular velocity is within the normal range and can be disregarded as the actual angular velocity peak or trough. At this point, the previous actual peak or trough P'(v, t) can be updated to the value of the historical potential peak or trough P(v, t). The previously acquired angular velocities AVlast and Tlast can also be updated to the current angular velocities AVcur and Tcur. The next round of autonomous vehicle dragon-drawing behavior detection can then be performed.

[0106] If the height / depth of the historical potential angular velocity peak value or trough value is greater than the preset peak threshold value, the historical potential angular velocity peak value or trough value may be regarded as the actual angular velocity peak value or trough value.

[0107] In the embodiment of the present disclosure, after determining that a new true angular velocity peak or trough appears, the above step S131 can be executed to determine whether the new true angular velocity peak or trough, as well as the historical true angular velocity peaks or troughs, meet the preset dragon drawing conditions.

[0108] In an embodiment of the present disclosure, if the historical true angular velocity peak or trough is empty, a new true angular velocity peak or trough can be determined, and it is determined that the historical true angular velocity peak or trough does not meet the preset dragon drawing condition. Then, the previous true angular velocity peak or trough can be updated with the new true angular velocity peak or trough, and the current angular velocity of the autonomous vehicle can be used to update the previously obtained angular velocity of the autonomous vehicle. That is, the previous true peak or trough P'(v,t) is updated to the value of the new true peak or trough P(v,t), and AVlast and Tlast are updated to the values of AVcur and Tcur respectively.

[0109] In an embodiment of the present disclosure, if the previous true angular velocity peak or trough is not empty. Then it can be determined whether the previous true angular velocity peak or trough P'(v,t) and the new true angular velocity peak or trough P(v,t) meet the preset dragon drawing condition.

[0110] In an embodiment of the present disclosure, the time difference Tdiff = Pt - P't between two true angular velocity peaks or troughs can be calculated, S = Pv * P'v can be calculated, and the height difference Vdiff = math.abs(Pv - P'v) between the two true angular velocity peak values or trough values can be calculated. If Tdiff < TW (Time window, the above preset duration) and S < 0 (the positive and negative signs of the two true angular velocities are opposite, that is, one is a true angular velocity peak and the other is a true angular velocity trough), and Vdiff > AVG (angular velocity gap, the above preset height difference), it can be determined that a dragon drawing behavior occurs at this time.

[0111] In an embodiment of the present disclosure, if the new true angular velocity peak or trough and the historical true angular velocity peak or trough do not meet the above preset dragon drawing condition, the previous true angular velocity peak or trough P'(v,t) can be updated to the value of the new true angular velocity peak or trough P(v,t), the previous potential peak or trough P(v,t) can be updated to the new potential angular velocity peak or trough, and the previously obtained angular velocity AVlast and Tlast of the autonomous vehicle can be updated to the current angular velocity AVcur and Tcur of the autonomous vehicle. After that, the current angular velocity of the autonomous vehicle can be re-obtained to perform a new round of detection of the dragon drawing behavior of the autonomous vehicle.

[0112] To more clearly illustrate the method for detecting the dragon drawing behavior of the autonomous vehicle provided by the present disclosure, the following will be described by way of specific embodiments for illustrative purposes:

[0113] In this example, the execution subject maintains the following variables: AVcur, AVlast, Tcur, Tlast, Trendcur, Trendlast. Figure 6a The process shown below implements the detection of dragon-drawing behavior of autonomous vehicles:

[0114] S601, initialize AVcur, AVlast, Tcur, Tlast, Trendcur, and Trendlast.

[0115] Among them, AVcur and Avlast are initially 0, Tcur and Tlast are initially 0, and Trendcur and Trendlast are initially 1.

[0116] S602, obtaining the angular velocity of the autonomous driving vehicle in real time, recording the obtained angular velocity in AVcur, and recording the time when the angular velocity is obtained in Tcur.

[0117] S603, compare AVcur with AVlast, if AVcur < AVlast, set Trendcur = 1, if AVcur > AVlast, set Trendcur = 0. Determine whether Trendcur is not equal to Trendlast, if so, execute S604, if not, execute S613.

[0118] S604, determining the presence of a potential angular velocity peak or trough, and judging whether AVcur is greater than a preset angular velocity threshold AVDT. If so, execute S605; otherwise, execute S612.

[0119] S605 , determining whether there is a previous potential angular velocity peak or trough, if so, executing S606 , otherwise executing S611 .

[0120] S606, determining whether the potential angular velocity peak or trough that appears this time is the same as the previous potential angular velocity peak or trough, if not, executing S607, if not, executing S612.

[0121] S607, determine whether Pv is greater than a preset peak threshold PAT, if so, execute S608, if not, execute S611.

[0122] Here, Pv is the angular velocity recorded in P(v, t).

[0123] S608, whether P'(v, t) is recorded, if so, execute S609, if not, execute S610.

[0124] S609: Determine whether the following conditions are met: Tdiff < TW, Vdiff > AVG, and S < 0. If so, it is determined that a dragon drawing behavior occurs; otherwise, execute S610.

[0125] Wherein, Tdiff=Pt-P't, Vdiff=math.abs(Pv-P'v), S=Pv*P'v, Pt is the time recorded in P(v, t), P'v is the angular velocity recorded in P'(v, t), and P't is the time recorded in P'(v, t).

[0126] S610, let P'(v, t) = P(v, t).

[0127] S611, determining whether a potential angular velocity peak or trough occurs, and recording the peak value or trough value.

[0128] S612, set Trendlast = 1-Trendcur.

[0129] S613, determine whether there is a previous potential angular velocity peak or trough, if so, execute S614, otherwise execute S616.

[0130] S614, determine whether AVcur is greater than the peak value or trough value of the previous potential angular velocity peak or trough, if so, execute S615, otherwise execute S616.

[0131] S615, record AVcur and AVlast in P(v, t).

[0132] S616, let AVlast = AVcur, Tlast = Tcur, and return to execute S601.

[0133] As a specific embodiment of the present disclosure, Figure 6b As shown, if the current autonomous vehicle angular velocity is A, the current angular velocity change trend, derived based on the previously acquired autonomous vehicle angular velocity and the current autonomous vehicle angular velocity, is downward, i.e., Trendcur = 0. However, the previous autonomous vehicle angular velocity change trend, Trendlast, was 1. This means the trends are different, and therefore, point B, where the angular velocity change trend occurs, is a new angular velocity peak. If this angular velocity peak is greater than the preset angular velocity threshold AVDT, then point B is a potential angular velocity peak. It is then possible to determine whether a potential angular velocity peak or trough occurred before this potential angular velocity peak B, i.e., whether the historical potential angular velocity peak or trough is empty.

[0134] like Figure 6bAs shown, a change in the angular velocity trend occurs at point F. However, due to the low angular velocity value at point F, F is not a potential angular velocity peak. Therefore, before the new potential angular velocity peak B, the historical potential angular velocity peak or trough is point C, which is also a potential angular velocity trough. Since the new potential angular velocity peak B and the historical potential angular velocity trough C are both potential peaks and potential troughs, respectively, points B and C meet the preset peak or trough conditions. If the depth of the angular velocity trough at point C exceeds the preset peak threshold PAT, then the historical potential angular velocity trough C can be considered the true angular velocity trough.

[0135] like Figure 6b As shown, before the true angular velocity trough C, there is a historical true angular velocity peak or trough D, and D is a true angular velocity peak. At this point, it can be determined whether the true angular velocity trough C and the true angular velocity peak D meet the preset dragon-drawing conditions. If the time interval between C and D is less than the preset duration, has opposite signs, and the drop height exceeds the preset drop height threshold, then the autonomous vehicle is considered to be exhibiting dragon-drawing behavior. Emergency takeover of the autonomous vehicle can be initiated.

[0136] According to an embodiment of the present disclosure, the present disclosure also provides a device for detecting the dragon-drawing behavior of an autonomous driving vehicle, such as Figure 7 As shown, the device may include:

[0137] The current angular velocity acquisition module 710 is used to obtain the current angular velocity of the autonomous driving vehicle;

[0138] a peak or trough determination module 720 for determining a peak or trough of an angular velocity of the autonomous driving vehicle based on a current angular velocity of the autonomous driving vehicle and a historical angular velocity of the autonomous driving vehicle;

[0139] A peak or trough determination module 730 is configured to determine whether the angular velocity peaks or troughs of the autonomous driving vehicle meet a preset dragon-drawing condition; wherein the preset dragon-drawing condition is: the time difference between the two angular velocity peaks or troughs is less than a preset duration, and the angular velocities have opposite signs;

[0140] The dragon-drawing behavior determination module 740 is configured to determine that the autonomous driving vehicle exhibits a dragon-drawing behavior if the angular velocity peak or trough satisfies the preset dragon-drawing condition.

[0141] In the disclosed embodiment, after obtaining the current angular velocity of the autonomous vehicle, the angular velocity peak or trough of the autonomous vehicle is determined based on the current angular velocity of the autonomous vehicle and the historical angular velocities of the autonomous vehicle. It is then determined whether the angular velocity peak or trough meets a preset dragon-drawing condition. If so, it is determined that the autonomous vehicle is exhibiting dragon-drawing behavior. By using the disclosed embodiment, determining whether the autonomous vehicle is exhibiting dragon-drawing behavior based on the angular velocity peak or trough of the autonomous vehicle can timely detect the autonomous vehicle's dragon-drawing behavior, thereby effectively taking emergency control of the autonomous vehicle, avoiding accidents, and ensuring the safety of both the driver and the vehicle.

[0142] In one embodiment of the present disclosure, the peak or trough determination module 720 is configured to determine a newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough based on the current angular velocity of the autonomous driving vehicle and the historical angular velocity of the autonomous driving vehicle;

[0143] Based on the new potential angular velocity peak or trough and the historical potential angular velocity peak or trough, determining a historical potential angular velocity peak or trough that meets a preset peak or trough condition as a new true angular velocity peak or trough;

[0144] The peak or trough determination module 730 is configured to determine whether the new true angular velocity peak or trough, and the historical true angular velocity peak or trough, meet a preset dragon drawing condition.

[0145] In one embodiment of the present disclosure, the above-mentioned device may further include an angular velocity update module (not shown in the figure) for updating the historical autonomous driving vehicle angular velocity, the historical potential angular velocity peaks or troughs, and the historical true angular velocity peaks or troughs.

[0146] In one embodiment of the present disclosure, the historical autonomous driving vehicle angular velocity is the last acquired autonomous driving vehicle angular velocity; the historical potential angular velocity peak or trough is the last potential angular velocity peak or trough;

[0147] The angular velocity updating module is configured to update the previous potential angular velocity peak or trough and the last acquired angular velocity of the autonomous driving vehicle with the current angular velocity of the autonomous driving vehicle if no new angular velocity peak or trough appears and the current angular velocity of the autonomous driving vehicle is greater than the historical potential angular velocity peak or trough;

[0148] If there is no historical potential angular velocity peak or trough that meets the preset peak or trough conditions, the previous potential angular velocity peak or trough is updated with the new potential angular velocity peak or trough, and the last acquired autonomous driving vehicle angular velocity is updated with the current angular velocity of the autonomous driving vehicle.

[0149] In one embodiment of the present disclosure, the historical true angular velocity peak or trough is the previous true angular velocity peak or trough;

[0150] The angular velocity update module can also be used to update the previous true angular velocity peak or trough with the new true angular velocity peak or trough, and the previous potential angular velocity peak or trough with the new potential angular velocity peak or trough, if the new true angular velocity peak or trough and the historical true angular velocity peak or trough do not meet the preset dragon drawing condition, and update the previous potential angular velocity peak or trough with the new potential angular velocity peak or trough, and update the last acquired autonomous driving vehicle angular velocity with the current angular velocity of the autonomous driving vehicle.

[0151] In one embodiment of the present disclosure, determining a newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough based on the current angular velocity of the autonomous driving vehicle and the historical angular velocity of the autonomous driving vehicle includes:

[0152] Calculating a change trend of the current angular velocity of the autonomous driving vehicle based on the current angular velocity of the autonomous driving vehicle and the last acquired angular velocity of the autonomous driving vehicle;

[0153] Determining whether the current angular velocity change trend of the autonomous driving vehicle is consistent with a previous angular velocity change trend of the autonomous driving vehicle;

[0154] Determining whether a new angular velocity peak or trough appears based on a determination result of whether the angular velocity change trend of the autonomous driving vehicle is consistent;

[0155] The newly appeared angular velocity peak or trough is regarded as a new potential angular velocity peak or trough.

[0156] In one embodiment of the present disclosure, determining, based on the new potential angular velocity peak or trough and the historical potential angular velocity peak or trough, a historical potential angular velocity peak or trough that meets a preset peak or trough condition as a new true angular velocity peak or trough includes:

[0157] Based on the historical potential angular velocity peaks or troughs, determining whether the new potential angular velocity peak or trough is the same as the previous potential angular velocity peak or trough;

[0158] If the new potential angular velocity peak or trough is different from the previous potential angular velocity peak or trough, the previous potential angular velocity peak or trough is taken as the actual angular velocity peak or trough.

[0159] In one embodiment of the present disclosure, the preset dragon drawing conditions are:

[0160] The time difference between the two angular velocity peaks or troughs is less than a preset duration, the angular velocity signs are opposite, and the drop height is greater than a preset drop height threshold.

[0161] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0162] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0163] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0164] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0165] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0166] The computing unit 801 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the detection method for the dragon-drawing behavior of an autonomous driving vehicle. For example, in some embodiments, the detection method for the dragon-drawing behavior of an autonomous driving vehicle can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the detection method for the dragon-drawing behavior of the autonomous driving vehicle described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method for detecting the dragon-drawing behavior of an autonomous driving vehicle in any other appropriate manner (e.g., by means of firmware).

[0167] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0168] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0169] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0170] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0171] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0172] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0173] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0174] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for detecting dragon-drawing behavior of an autonomous driving vehicle, comprising: Get the current angular velocity of the autonomous vehicle; Based on the current angular velocity of the autonomous vehicle and the historical angular velocity of the autonomous vehicle, determining a newly occurring angular velocity peak or trough of the autonomous vehicle, and recording the peak or trough as a new potential angular velocity peak or trough; wherein the historical angular velocity of the autonomous vehicle is the most recently acquired angular velocity of the autonomous vehicle; If the new potential angular velocity peak or trough is different from the historical potential angular velocity peak or trough, and the height / depth of the historical potential angular velocity peak or trough is greater than a preset peak threshold, then the historical potential angular velocity peak or trough is determined as the new true angular velocity peak or trough; Determining whether a peak or trough of the angular velocity of the autonomous driving vehicle satisfies a preset dragon drawing condition; If the angular velocity peak or trough satisfies the preset dragon-drawing condition, it is determined that the autonomous driving vehicle has performed a dragon-drawing behavior; The angular velocity peaks or troughs used to determine whether the preset dragon-drawing conditions are met are the new true angular velocity peaks or troughs and the historical true angular velocity peaks or troughs, the historical potential angular velocity peaks or troughs are the potential angular velocity peaks or troughs recorded in the previous round of autonomous driving vehicle dragon-drawing behavior detection, and the historical true angular velocity peaks or troughs are the true angular velocity peaks or troughs obtained in the previous round of autonomous driving vehicle dragon-drawing behavior detection; The preset dragon drawing conditions are: the time difference between two angular velocity peaks or troughs is less than a preset duration, the angular velocity signs are opposite, and the drop height is greater than a preset drop height threshold; The determining, based on the current angular velocity of the autonomous vehicle and the historical angular velocity of the autonomous vehicle, a newly appeared angular velocity peak or trough of the autonomous vehicle, and recording the newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough, includes: Based on the current angular velocity of the autonomous driving vehicle and the last acquired angular velocity of the autonomous driving vehicle, calculate the current angular velocity change trend of the autonomous driving vehicle; determine whether the current angular velocity change trend of the autonomous driving vehicle is consistent with the last angular velocity change trend of the autonomous driving vehicle; if the current angular velocity change trend of the autonomous driving vehicle is different from the last angular velocity change trend of the autonomous driving vehicle, determine that a new angular velocity peak or trough has appeared; and use the newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough.

2. The method according to claim 1, further comprising: Update the historical autonomous driving vehicle angular velocity, the historical potential angular velocity peaks or troughs, and the historical true angular velocity peaks or troughs.

3. The method according to claim 2, wherein: The historical true angular velocity peak or trough is the previous true angular velocity peak or trough; The step of updating the historical autonomous driving vehicle angular velocity, the historical potential angular velocity peaks or troughs, and the historical actual angular velocity peaks or troughs further includes: If the new true angular velocity peak or trough, and the historical true angular velocity peak or trough, do not meet the preset dragon drawing condition, then the new true angular velocity peak or trough is used to update the previous true angular velocity peak or trough, the new potential angular velocity peak or trough is used to update the previous potential angular velocity peak or trough, and the current angular velocity of the autonomous driving vehicle is used to update the last acquired autonomous driving vehicle angular velocity.

4. A device for detecting dragon-drawing behavior of an autonomous driving vehicle, comprising: The current angular velocity acquisition module is used to obtain the current angular velocity of the autonomous driving vehicle; a peak or trough determination module, configured to determine a newly occurring angular velocity peak or trough of the autonomous driving vehicle based on the current angular velocity of the autonomous driving vehicle and a historical angular velocity of the autonomous driving vehicle, and record the peak or trough as a new potential angular velocity peak or trough; wherein the historical angular velocity of the autonomous driving vehicle is a previously acquired angular velocity of the autonomous driving vehicle; A peak or trough judgment module, used to determine whether the angular velocity peak or trough of the autonomous driving vehicle meets a preset dragon drawing condition; a dragon-drawing behavior determination module, configured to determine that the autonomous driving vehicle exhibits dragon-drawing behavior if the angular velocity peak or trough satisfies the preset dragon-drawing condition; and to determine the historical potential angular velocity peak or trough as the new true angular velocity peak or trough if the new potential angular velocity peak or trough is different from the historical potential angular velocity peak or trough, and the height / depth of the historical potential angular velocity peak or trough is greater than a preset peak threshold; The angular velocity peaks or troughs used to determine whether the preset dragon-drawing conditions are met are the new true angular velocity peaks or troughs and the historical true angular velocity peaks or troughs, the historical potential angular velocity peaks or troughs are the potential angular velocity peaks or troughs recorded in the previous round of autonomous driving vehicle dragon-drawing behavior detection, and the historical true angular velocity peaks or troughs are the true angular velocity peaks or troughs obtained in the previous round of autonomous driving vehicle dragon-drawing behavior detection; The preset dragon drawing conditions are: the time difference between two angular velocity peaks or troughs is less than a preset duration, the angular velocity signs are opposite, and the drop height is greater than a preset drop height threshold; The determining, based on the current angular velocity of the autonomous driving vehicle and the historical angular velocity of the autonomous driving vehicle, of a newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough includes: Based on the current angular velocity of the autonomous driving vehicle and the last acquired angular velocity of the autonomous driving vehicle, calculate the current angular velocity change trend of the autonomous driving vehicle; determine whether the current angular velocity change trend of the autonomous driving vehicle is consistent with the last angular velocity change trend of the autonomous driving vehicle; if the current angular velocity change trend of the autonomous driving vehicle is different from the last angular velocity change trend of the autonomous driving vehicle, determine that a new angular velocity peak or trough has appeared; and use the newly appeared angular velocity peak or trough as a new potential angular velocity peak or trough.

5. The apparatus according to claim 4, further comprising: An angular velocity update module is used to update the historical autonomous driving vehicle angular velocity, the historical potential angular velocity peaks or troughs, and the historical true angular velocity peaks or troughs.

6. The device according to claim 5, wherein The historical true angular velocity peak or trough is the previous true angular velocity peak or trough; The angular velocity update module is also used to update the previous true angular velocity peak or trough with the new true angular velocity peak or trough, update the previous potential angular velocity peak or trough with the new potential angular velocity peak or trough, and update the last acquired autonomous driving vehicle angular velocity with the current angular velocity of the autonomous driving vehicle if the new true angular velocity peak or trough and the historical true angular velocity peak or trough do not meet the preset dragon drawing condition.

7. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-3.

9. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 3.

Images