Dangerous behavior assessment method and system for autonomous vehicle

Abstract

The invention is suitable for the technical field of dangerous behavior assessment, and particularly relates to a dangerous behavior assessment method and system for an automatic driving vehicle, and the method comprises the steps: delimiting a dangerous warning region of the automatic driving vehicle, and enabling the dangerous warning region to be composed of a motor vehicle lane and a non-motor vehicle lane, the method comprises the following steps: acquiring video data by using monitoring equipment pre-deployed in a danger warning area, selecting traffic participants which influence each other, defining sample vehicles in a motor vehicle lane, and defining interference objects in a non-motor vehicle lane; behavior characteristics of the interference object are collected, and the linkage response of the sample vehicle is read in the preset step length time; according to the invention, by determining the target response, a real and referenceable decision sample can be provided for the autonomous vehicle, the response strategy of the autonomous vehicle in a complex scene is optimized, the situation of false triggering of emergency braking is reduced, the safety risk of the autonomous vehicle when passing through a dangerous warning area is reduced, and the traffic safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dangerous behavior assessment, and in particular to a dangerous behavior assessment method and system for an autonomous driving vehicle. Background Art

[0002] Autonomous driving vehicles are generally used in limited scenarios or closed areas, such as express delivery and inside industrial parks.

[0003] Taking the unmanned logistics vehicles of express logistics companies as an example, when driving on straight roads, the safety risks are relatively controllable due to the relatively simple road environment, fewer traffic participants, and stable vehicle driving trajectories; however, when passing through intersections, they are prone to dangerous behaviors because they cannot understand the intentions of other traffic participants on the road.

[0004] For example, when an unmanned logistics vehicle is preparing to turn right on the motor vehicle lane, an electric bicycle driver on the adjacent non-motor vehicle lane also turns on the right turn signal or slightly deviates to the right of the lane, expressing his intention to turn right; because the current unmanned logistics vehicles lack accurate recognition and understanding of the intentions of traffic participants, they are unable to predict the future behavior of the electric bicycle driver, and then trigger emergency braking to avoid a collision when approaching the intersection; however, the manned vehicle following closely behind may have judged from the riding behavior that the electric bicycle will turn right, and believes that the unmanned logistics vehicle will pass through the intersection at a constant speed, so it is not prepared for emergency braking, which ultimately creates a safety hazard and may even cause a rear-end collision.

[0005] Therefore, “how to identify the traffic intention of traffic participants on adjacent non-motorized vehicle lanes when passing through an intersection” is the technical problem that the present invention needs to solve. Summary of the Invention

[0006] The purpose of the present invention is to provide a dangerous behavior assessment method and system for an autonomous driving vehicle to solve the problem raised in the above background technology of "how to identify the traffic intentions of traffic participants on adjacent non-motorized vehicle lanes when passing through an intersection."

[0007] To achieve the above object, the present invention provides the following technical solutions: A method for assessing dangerous behavior of an autonomous driving vehicle, the method comprising: Delineate a danger warning area for autonomous vehicles, where the danger warning area consists of motor vehicle lanes and non-motor vehicle lanes. Utilize monitoring equipment pre-deployed in the danger warning area to collect video data, select traffic participants that affect each other, and define sample vehicles in the motor vehicle lanes and interference objects in the non-motor vehicle lanes. Collect the behavioral characteristics of the interference object and read the linkage response of the sample vehicle at the preset step time. Integrate the behavioral characteristics and linkage response to generate a rule base and insert risk level items. When a Bluetooth beacon signal from an autonomous vehicle is collected using a Bluetooth device deployed in a danger warning area, a target terminal is defined and the monitoring device is activated to collect real-time behavioral characteristics of traffic participants in the non-motorized vehicle lane, compare them with a rule library, and obtain a target response; A communication link is established between the target terminal and the Bluetooth device, and the target terminal is captured in the video data. When the target terminal reaches a preset identification point, the communication link is opened and a target response is sent to the target terminal.

[0008] Furthermore, the steps of collecting video data, selecting traffic participants that affect each other, defining sample vehicles in motor vehicle lanes, and defining interference objects in non-motor vehicle lanes include: A behavior pattern recognition model is constructed. When a sample vehicle reaches a marked point, a snapshot of the non-motorized vehicle lane area is captured from the video data, and the snapshot is input into the behavior pattern recognition model to output a potential intention. Based on the potential intention, it is determined whether there are traffic participants that affect each other in the motor vehicle lane and the non-motor vehicle lane.

[0009] Furthermore, the step of defining an interference object in the non-motorized vehicle lane includes: Acquiring driving data of the interference object, wherein the driving data at least includes: vehicle speed and driving position; The risk level of the target response is shifted via the driving data.

[0010] Furthermore, the steps of collecting behavioral characteristics of the interference object, reading the linkage response of the sample vehicle at a preset step time, integrating the behavioral characteristics and the linkage response, generating a rule base, and inserting the risk level item include: Create a corresponding treatment plan for each risk level, and once the target response is determined, initiate the corresponding treatment plan; Delete abnormal responses from the rule base, integrate the rule base of all dangerous warning areas, build a management platform that coordinates all monitoring devices and Bluetooth devices, and upload the integrated rule base to the management platform.

[0011] Furthermore, when a Bluetooth beacon signal of an autonomous vehicle is collected by a Bluetooth device deployed in a danger warning area, the steps of defining a target terminal and activating the monitoring device include: Using the monitoring device, collecting attribute characteristics of the autonomous driving vehicle, wherein the attribute characteristics include at least: a license plate and an appearance; It is determined whether the target terminal meets the attribute characteristics. If not, the target terminal is redefined.

[0012] Furthermore, the method further comprises: With the monitoring device as the center and the preset distance as the radius, a data processing range is constructed to find the edge nodes; The video data is sent to an edge node, wherein each monitoring device corresponds to at least one edge node.

[0013] Furthermore, when the target terminal reaches a preset identification point, the step of opening the communication link and sending the target response to the target terminal includes: From the video data, abnormal events are defined and the total number of abnormal events in each danger warning area is counted; Danger warning areas with a total number greater than a threshold are selected and defined as slow-moving sections. When the autonomous vehicle reaches the slow-moving section, the pre-configured deceleration control strategy is called and executed.

[0014] Furthermore, the system includes: The delineation module is used to delineate a danger warning area for autonomous vehicles, where the danger warning area consists of motor vehicle lanes and non-motor vehicle lanes. Monitoring equipment pre-deployed in the danger warning area is used to collect video data, select traffic participants that affect each other, and define sample vehicles in the motor vehicle lanes and interference objects in the non-motor vehicle lanes. Insertion module, used to collect behavioral characteristics of interference objects, and read the linkage response of sample vehicles at a preset step time, integrate behavioral characteristics and linkage response, generate a rule base, and insert risk level items; The obtaining module is used to define a target terminal when a Bluetooth beacon signal of an autonomous vehicle is collected by a Bluetooth device deployed in a danger warning area, and activate the monitoring device to collect real-time behavioral characteristics of traffic participants in the non-motorized vehicle lane, compare them with the rule library, and obtain a target response; The sending module is used to establish a communication link between the target terminal and the Bluetooth device, and capture the target terminal in the video data. When the target terminal reaches a preset identification point, the communication link is opened and the target response is sent to the target terminal.

[0015] Furthermore, the delineation module includes: a construction unit for constructing a behavior pattern recognition model, wherein when a sample vehicle arrives at a marked point, a snapshot of the non-motor vehicle lane area is captured from the video data, and the snapshot is input into the behavior pattern recognition model to output a potential intention; a judgment unit, configured to judge whether there are traffic participants that affect each other on the motor vehicle lane and the non-motor vehicle lane according to the potential intention; An acquisition unit, configured to acquire driving data of an interfering object, wherein the driving data includes at least vehicle speed and driving position; An offset unit is configured to offset the risk level of the target response based on the driving data.

[0016] Furthermore, the insertion module includes: The startup unit is used to create a treatment plan that corresponds to the risk level. When the target response is determined, the corresponding treatment plan is started; The upload unit is used to delete abnormal responses from the rule base, integrate the rule base of all dangerous warning areas, build a management platform that coordinates all monitoring devices and Bluetooth devices, and upload the integrated rule base to the management platform.

[0017] Compared with the prior art, the present invention has the following beneficial effects: By demarcating danger warning areas, potential conflict behaviors can be perceived in advance, assisting autonomous vehicles in understanding traffic intentions and improving the safety of traffic behaviors. By selecting interference objects, potential conflict targets can be identified in advance, providing a data basis for traffic intention identification. By building a rule base, artificial experience can be used to supplement the decision-making ability of autonomous vehicles in uncertain environments, and "imitation learning" can be used to assist in decision optimization and provide a reference for emergency response of autonomous vehicles. By determining target responses, real and referenceable decision samples can be provided for autonomous vehicles, optimizing the response strategies of autonomous vehicles in complex scenarios, reducing false triggering of emergency braking, reducing the safety risks of autonomous vehicles passing through danger warning areas, and improving traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the location of the danger warning area; Figure 2 A flowchart of a dangerous behavior assessment method for an autonomous driving vehicle provided in an embodiment of the present invention; Figure 3 A block diagram of the first sub-process of the dangerous behavior assessment method for an autonomous driving vehicle provided by an embodiment of the present invention; Figure 4 A block diagram of the second sub-process of the method for assessing dangerous behavior of an autonomous driving vehicle provided by an embodiment of the present invention; Figure 5 A block diagram of the third sub-process of the dangerous behavior assessment method for an autonomous driving vehicle provided in an embodiment of the present invention; Figure 6 A fourth sub-flow chart of the dangerous behavior assessment method for an autonomous driving vehicle provided in an embodiment of the present invention; Figure 7 A block diagram of a method for assessing dangerous behavior of an autonomous vehicle provided by an embodiment of the present invention; Figure 8 A block diagram of the composition of the delineation module in the dangerous behavior assessment system for an autonomous driving vehicle provided by an embodiment of the present invention; Figure 9 A block diagram of the components of the insertion module in the dangerous behavior assessment system for an autonomous driving vehicle provided by an embodiment of the present invention; Figure 10 A block diagram of the components of the module in the dangerous behavior assessment system for an autonomous driving vehicle provided by an embodiment of the present invention Figure 11 This is a block diagram of the composition of the sending module in the dangerous behavior assessment system for autonomous driving vehicles provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] In Example 1, Figure 1 and Figure 2 The following is a detailed description of the implementation process of the dangerous behavior assessment method for an autonomous driving vehicle provided by an embodiment of the present invention. S100: Delineate a danger warning area for autonomous vehicles, where the danger warning area consists of motor vehicle lanes and non-motor vehicle lanes. Utilize monitoring equipment pre-deployed in the danger warning area to collect video data, select traffic participants that affect each other, and define sample vehicles in the motor vehicle lanes and interference objects in the non-motor vehicle lanes.

[0021] Define the danger warning area for the autonomous vehicle, where the danger warning area is located at a traffic light intersection or other intersection. The danger warning area includes: the motor vehicle lane and the adjacent non-motor vehicle lane; for example, the danger warning area is the right turn lane and the adjacent non-motor vehicle lane at a four-way intersection (see the attached manual). Figure 1The two groups of A areas shown in the figure are taken as an example in this application for an autonomous driving vehicle that needs to turn right, and the same applies to left turns). Monitoring equipment deployed in the danger warning area is used, where the monitoring equipment can be a high-definition camera or other video acquisition equipment to collect video data in the danger warning area and obtain dynamic information of all traffic participants in the area, including motor vehicles, non-motor vehicles (such as electric bicycles), pedestrians and other traffic entities. The image recognition and behavior analysis algorithms in the existing technology are used to perform target detection, tracking and behavior recognition on the collected video stream to screen out traffic participants with potential conflicts in space and time, that is, traffic participants that affect each other. The analysis and processing of the video stream data can be processed in the edge node.

[0022] A vehicle that is in the motor vehicle lane and is about to turn right is defined as a sample vehicle, and a pedestrian or non-motor vehicle that is in the non-motor vehicle lane and may conflict with the sample vehicle is defined as an interference object.

[0023] S200: Collect behavioral features of the interference object, and read the linkage response of the sample vehicle at a preset step time, integrate the behavioral features and linkage response, generate a rule base, and insert risk level items.

[0024] Using monitoring equipment, video data containing interfering objects is collected. Image recognition and pedestrian analysis algorithms are used to extract the behavioral characteristics of the interfering objects, such as turning on the turn signal (indicating an intention to change lanes or turn), the brake lights are on (indicating that the vehicle is slowing down or about to stop), and the vehicle body is slightly offset to the right of the lane (possibly a precursor to changing lanes, avoiding or turning). After detecting the preset step time interval of the behavioral characteristics (for example, 0.5 seconds or 1 second), the linkage responses of the sample vehicles are collected and recorded, such as deceleration, steering, emergency braking, path adjustment, or maintaining the current state, etc., to construct a "behavioral characteristic-linked response" mapping relationship, and integrate all behavioral characteristics and linked responses to generate a rule base; risk level items are inserted into the rule base to determine the risk level of each mapping relationship.

[0025] For example, when a sample vehicle is about to turn right, the monitoring equipment captures the following behavioral characteristics of an electric bicycle on the right non-motorized vehicle lane: turning on the right turn signal, slightly deviating to the right of the lane, but not slowing down; the time when the behavioral characteristics appear is recorded, assuming it is T seconds, and the preset step size is set to 1 second; after the sample vehicle finds that the interference object shows the intention to turn right, it does not slow down, but passes through the intersection at a slower speed and at a constant speed; then the linkage response of the sample vehicle after T+1 second is recorded, that is, it does not slow down and passes through the intersection at a constant speed; integrating the behavioral characteristics and linkage responses, a mapping relationship is obtained: "turning on the right turn signal, slightly deviating to the right of the lane, but not slowing down - not slowing down, passing through the intersection at a constant speed", the corresponding risk level is determined, and all the obtained mapping relationships are integrated to obtain a rule base; the higher the risk level, the higher the possibility of the sample vehicle colliding with the interference object.

[0026] In this application, by collecting the linkage responses of sample vehicles when passing through intersections, a data basis is provided for the driving operations and emergency handling of autonomous driving vehicles under the same traffic conditions, thereby avoiding sudden braking and reducing the possibility of safety accidents.

[0027] S300: When the Bluetooth beacon signal of the autonomous driving vehicle is collected using the Bluetooth device deployed in the danger warning area, the target terminal is defined and the monitoring device is activated to collect the real-time behavior characteristics of traffic participants in the non-motorized vehicle lane, compare them with the rule library, and obtain the target response.

[0028] Using Bluetooth devices pre-deployed in the danger warning area, the Bluetooth beacon signals of all devices within the signal coverage are collected. Based on the unique identifier in the Bluetooth beacon signal, the Bluetooth beacon signal corresponding to the autonomous driving vehicle is identified, and the corresponding autonomous driving vehicle is defined as the target terminal; the Bluetooth beacon signal can be judged whether it comes from the autonomous driving vehicle based on the fixed prefix or suffix of the unique identifier; after the target terminal is identified, the monitoring equipment is activated to collect the real-time behavioral characteristics of traffic participants in the non-motorized vehicle lane, and compare them with the rule library to find the linkage response corresponding to the same behavioral characteristics and define it as the target response. Simply put, the target response is the driving action performed by the sample vehicle under the same traffic conditions.

[0029] Continuing to elaborate on the example in S200, when the real-time behavior feature is "turning on the right turn signal, slightly shifting to the right of the lane, but not slowing down", the corresponding "but not slowing down - not slowing down, passing through the intersection at a constant speed" is defined as the target response. In other words, under the same traffic conditions, the autonomous driving vehicle does not need to slow down and can pass through the intersection at a constant speed. The deceleration here refers to an additional secondary deceleration. The autonomous driving vehicle should slow down in advance when entering the intersection.

[0030] S400: Establish a communication link between the target terminal and the Bluetooth device, and capture the target terminal in the video data. When the target terminal reaches a preset identification point, open the communication link and send a target response to the target terminal.

[0031] Using Bluetooth beacon signals, a communication link is established between the target terminal and the Bluetooth device. The position of the target terminal in the video image is determined through target recognition and tracking algorithms. When the target terminal is identified as reaching a preset identification point, which can be a zebra crossing or other point in front of an intersection, the communication link is opened to allow data to interact between the Bluetooth device and the target terminal. The target response is sent to the target terminal in real time through the Bluetooth device, guiding the autonomous driving vehicle to perform corresponding driving operations.

[0032] In Example 2, Figure 3 The implementation process of the dangerous behavior assessment method for an autonomous driving vehicle provided by an embodiment of the present invention is shown. The following details the steps of collecting video data, selecting traffic participants that affect each other, defining sample vehicles in motor vehicle lanes, and defining interference objects in non-motor vehicle lanes. S101: Constructing a behavior pattern recognition model. When a vehicle reaches a marking point, a snapshot of the non-motorized vehicle lane area is captured from the video data, and the snapshot is input into the behavior pattern recognition model to output a potential intention.

[0033] Based on a convolutional neural network, a behavioral pattern recognition model is constructed. The behavioral pattern recognition model is mainly used to identify the potential behavioral intentions of participants in non-motorized vehicle lanes. When a sample vehicle reaches a preset identification point, a snapshot of the current non-motorized vehicle lane area is captured from the video stream. This snapshot covers the real-time location, posture, movement direction, etc. of traffic participants such as electric bicycles and pedestrians. This snapshot is used as input to the trained behavioral pattern recognition model, and the output is the potential intention of the non-motorized vehicle or pedestrian, where the potential intention includes: whether to prepare to cross the road, turn right, accelerate, decelerate, or suddenly change direction, etc.

[0034] S102: Based on the potential intention, determine whether there are traffic participants in the motor vehicle lane and the non-motor vehicle lane that may affect each other.

[0035] Based on the potential intentions of non-motor vehicles and pedestrians, determine whether there are traffic participants in the non-motor vehicle lane that will affect the passage of vehicles in the motor vehicle lane.

[0036] In Example 3, Figure 3 The implementation process of the dangerous behavior assessment method for an autonomous driving vehicle provided by an embodiment of the present invention is shown. The steps of defining interference objects in the non-motorized vehicle lane are described in detail below: S103: Acquire driving data of the interference object, wherein the driving data at least includes: vehicle speed and driving position.

[0037] Determine the driving data of the interfering object in the non-motor vehicle lane.

[0038] S104: Determine the risk level of the target response based on the driving data.

[0039] Based on the driving data, the risk level of the target response is offset. The offset includes: increasing or decreasing the risk level. For example, if the driving speed of the interfering object is greater than the threshold, the risk level can be increased and the corresponding disposal plan can be activated to avoid traffic accidents.

[0040] In Example 4, Figure 4 The implementation process of the dangerous behavior assessment method for an autonomous driving vehicle provided by an embodiment of the present invention is shown. The following details the steps of collecting the behavioral characteristics of the interference object, reading the linkage response of the sample vehicle at a preset step time, integrating the behavioral characteristics and linkage response, generating a rule base, and inserting the risk level item. S201: Create a treatment plan that corresponds to each risk level. After the target response is determined, start the corresponding treatment plan.

[0041] Create a corresponding response plan for each risk level, where risk levels can be divided into high, medium and low. Once the target response is determined, the corresponding risk level is found and the corresponding response plan is initiated. The response plan may include continuous honking of the horn or early deceleration.

[0042] S202: Delete abnormal responses from the rule base, integrate the rule bases of all danger warning areas, build a management platform that coordinates all monitoring devices and Bluetooth devices, and upload the integrated rule base to the management platform.

[0043] In the rule base, abnormal responses are found, where abnormal responses refer to linkage responses that may cause traffic accidents or traffic accidents. For example, when the sample vehicle turns right, it does not slow down, and the interfering object does not slow down either, resulting in the relative distance between the two being too close. At this time, the linkage response corresponding to the sample vehicle is defined as an abnormal response. A management platform is constructed, where the management platform is mainly used to analyze and process all rule bases. The specific processing steps include: deleting identical linkage responses, counting the number of occurrences of linkage responses, etc.

[0044] In Example 5, Figure 5The implementation process of the dangerous behavior assessment method for an autonomous vehicle provided by an embodiment of the present invention is shown. The following details the steps of defining a target terminal and activating the monitoring device when a Bluetooth beacon signal of an autonomous vehicle is collected by a Bluetooth device deployed in a dangerous warning area, as follows: S301: Utilize the monitoring device to collect attribute characteristics of the autonomous driving vehicle, wherein the attribute characteristics include at least: license plate and appearance.

[0045] When the Bluetooth device receives the Bluetooth beacon signal of the autonomous vehicle, it uses the monitoring equipment to collect the license plate information of all vehicles and identify the autonomous vehicle among them.

[0046] S302: Determine whether the target terminal meets the attribute characteristics. If not, redefine the target terminal.

[0047] Determine whether the target terminal is an autonomous driving vehicle. If not, redetermine the target terminal. The advantage of this method is that by verifying the target terminal, the accuracy of target terminal identification can be improved, ensuring that the target response can be sent to the target terminal in a timely manner.

[0048] In Example 6, different from Example 1, in this embodiment of the present invention, the method further includes: With the monitoring device as the center and the preset distance as the radius, a data processing range is constructed to find the edge nodes; The video data is sent to an edge node, wherein each monitoring device corresponds to at least one edge node.

[0049] The data processing range is constructed with the monitoring equipment deployed in the danger warning area as the center and the preset distance as the radius. The preset distance is set by the traffic management personnel. The edge nodes within the data processing range are found, where the edge nodes are roadside shops or smart gateways, etc., and the video data is sent to the edge nodes for processing.

[0050] In Example 7, Figure 6 The implementation process of the dangerous behavior assessment method for an autonomous driving vehicle provided by an embodiment of the present invention is shown. The following details the steps of opening the communication link and sending the target response to the target terminal after the target terminal reaches the preset identification point. S401: defining abnormal events from video data, and counting the total number of abnormal events in each danger warning area.

[0051] In the video data, abnormal events are defined, where abnormal events refer to the state characteristics corresponding to when the sample vehicle or interference object suddenly brakes, has a traffic accident, or performs obvious dangerous actions. The total number of abnormal events in each danger warning area is calculated.

[0052] S402: Danger warning areas with a total number greater than a threshold are selected and defined as slow-moving sections. When the autonomous driving vehicle reaches the slow-moving section, a pre-configured deceleration control strategy is called and executed.

[0053] If the total number is greater than the threshold, the corresponding danger warning area is defined as a slow-moving section. When the autonomous driving vehicle is in the slow-moving section, the corresponding deceleration control strategy is executed, where the deceleration control strategy is: controlling the vehicle speed within a preset range.

[0054] Figure 7 The following is a block diagram showing the composition of a dangerous behavior assessment system for an autonomous driving vehicle provided by an embodiment of the present invention. The dangerous behavior assessment system 1 for an autonomous driving vehicle includes: The delineation module 11 is configured to delineate a danger warning area for the autonomous vehicle, where the danger warning area consists of a motor vehicle lane and a non-motor vehicle lane. Monitoring equipment pre-deployed in the danger warning area is used to collect video data, select traffic participants that affect each other, and define sample vehicles in the motor vehicle lane and interference objects in the non-motor vehicle lane. Insertion module 12 is used to collect behavioral characteristics of interference objects, and read the linkage response of sample vehicles at a preset step time, integrate the behavioral characteristics and linkage response, generate a rule base, and insert risk level items; The obtaining module 13 is used to define a target terminal when the Bluetooth beacon signal of the autonomous vehicle is collected by the Bluetooth device deployed in the danger warning area, and activate the monitoring device to collect the real-time behavior characteristics of traffic participants in the non-motorized vehicle lane, compare them with the rule library, and obtain a target response; The sending module 14 is used to establish a communication link between the target terminal and the Bluetooth device, and capture the target terminal in the video data. When the target terminal reaches a preset identification point, the communication link is opened and a target response is sent to the target terminal.

[0055] Figure 8 The following is a structural block diagram of a dangerous behavior assessment system for an autonomous driving vehicle according to an embodiment of the present invention. The delineation module 11 includes: A construction unit 111 is configured to construct a behavior pattern recognition model. When a sample vehicle arrives at a marked point, a snapshot of the non-motorized vehicle lane area is captured from the video data, and the snapshot is input into the behavior pattern recognition model to output a potential intention. A judgment unit 112 is configured to judge whether there are traffic participants that affect each other on the motor vehicle lane and the non-motor vehicle lane based on the potential intention; An acquiring unit 113 is configured to acquire driving data of the interfering object, wherein the driving data includes at least vehicle speed and driving position; The offset unit 114 is configured to offset the risk level of the target response based on the driving data.

[0056] Figure 9 The following is a structural block diagram of a dangerous behavior assessment system for an autonomous driving vehicle according to an embodiment of the present invention. The insertion module 12 includes: The activation unit 121 is used to create a treatment plan corresponding to each risk level, and activate the corresponding treatment plan after determining the target response; The uploading unit 122 is used to delete abnormal responses from the rule base, integrate the rule bases of all dangerous warning areas, build a management platform that coordinates all monitoring devices and Bluetooth devices, and upload the integrated rule base to the management platform.

[0057] Figure 10 The following is a structural block diagram of a dangerous behavior assessment system for an autonomous driving vehicle according to an embodiment of the present invention. The obtaining module 13 includes: The collecting unit 131 is configured to collect attribute characteristics of the autonomous driving vehicle using the monitoring device, wherein the attribute characteristics include at least: a license plate and an appearance; The defining unit 132 is configured to determine whether the target terminal meets the attribute characteristics, and if not, redefine the target terminal.

[0058] Figure 11 The following is a structural block diagram of a dangerous behavior assessment system for an autonomous driving vehicle according to an embodiment of the present invention. The issuing module 14 includes: A statistics unit 141 is used to define abnormal events from the video data and count the total number of abnormal events in each danger warning area; The calling unit 142 is used to select dangerous warning areas with a total number greater than a threshold and define them as slow-moving sections. When the autonomous driving vehicle reaches the slow-moving section, the pre-configured deceleration control strategy is called and executed.

[0059] The demarcation module 11 is mainly used to complete step S100, the insertion module 12 is mainly used to complete step S200, the acquisition module 13 is mainly used to complete step S300, and the delivery module 14 is mainly used to complete step S400; The construction unit 111 is mainly used to complete step S101, the judgment unit 112 is mainly used to complete step S102, the acquisition unit 113 is mainly used to complete step S103, and the offset unit 114 is mainly used to complete step S104; The starting unit 121 is mainly used to complete step S201, and the uploading unit 122 is mainly used to complete step S202; The collection unit 131 is mainly used to complete step S301, and the definition unit 132 is mainly used to complete step S302; The statistics unit 141 is mainly used to complete step S401, and the calling unit 142 is mainly used to complete step S402.

[0060] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0061] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for assessing dangerous behavior of an autonomous vehicle, characterized in that: The method comprises: Delineate a danger warning area for autonomous vehicles, where the danger warning area consists of motor vehicle lanes and non-motor vehicle lanes. Utilize monitoring equipment pre-deployed in the danger warning area to collect video data, select traffic participants that affect each other, and define sample vehicles in the motor vehicle lanes and interference objects in the non-motor vehicle lanes. Collect the behavioral characteristics of the interference object and read the linkage response of the sample vehicle at the preset step time. Integrate the behavioral characteristics and linkage response to generate a rule base and insert risk level items. When a Bluetooth beacon signal from an autonomous vehicle is collected using a Bluetooth device deployed in a danger warning area, a target terminal is defined and the monitoring device is activated to collect real-time behavioral characteristics of traffic participants in the non-motorized vehicle lane, compare them with a rule library, and obtain a target response; A communication link is established between the target terminal and the Bluetooth device, and the target terminal is captured in the video data. When the target terminal reaches a preset identification point, the communication link is opened and a target response is sent to the target terminal.

2. The method for assessing dangerous behavior of an autonomous driving vehicle according to claim 1, wherein: The steps of collecting video data, selecting traffic participants that affect each other, defining sample vehicles in motor vehicle lanes, and defining interference objects in non-motor vehicle lanes include: A behavior pattern recognition model is constructed. When a sample vehicle reaches a marked point, a snapshot of the non-motorized vehicle lane area is captured from the video data, and the snapshot is input into the behavior pattern recognition model to output a potential intention. Based on the potential intention, it is determined whether there are traffic participants that affect each other in the motor vehicle lane and the non-motor vehicle lane.

3. The method for assessing dangerous behavior of an autonomous driving vehicle according to claim 2, wherein: The step of defining an interference object in the non-motorized vehicle lane includes: Acquiring driving data of the interference object, wherein the driving data at least includes: vehicle speed and driving position; The risk level of the target response is shifted via the driving data.

4. The method for assessing dangerous behavior of an autonomous driving vehicle according to claim 3, wherein: The steps of collecting the behavioral characteristics of the interference object, reading the linkage response of the sample vehicle at a preset step time, integrating the behavioral characteristics and the linkage response, generating a rule base, and inserting the risk level item include: Create a corresponding treatment plan for each risk level, and once the target response is determined, initiate the corresponding treatment plan; Delete abnormal responses from the rule base, integrate the rule base of all dangerous warning areas, build a management platform that coordinates all monitoring devices and Bluetooth devices, and upload the integrated rule base to the management platform.

5. The method for assessing dangerous behavior of an autonomous driving vehicle according to claim 1, wherein: The steps of defining a target terminal and activating the monitoring device when a Bluetooth beacon signal of an autonomous driving vehicle is collected by a Bluetooth device deployed in a danger warning area include: Using the monitoring device, collecting attribute characteristics of the autonomous driving vehicle, wherein the attribute characteristics include at least: a license plate and an appearance; It is determined whether the target terminal meets the attribute characteristics. If not, the target terminal is redefined.

6. The method for assessing dangerous behavior of an autonomous driving vehicle according to claim 5, wherein: The method further comprises: With the monitoring device as the center and the preset distance as the radius, a data processing range is constructed to find the edge nodes; The video data is sent to an edge node, wherein each monitoring device corresponds to at least one edge node.

7. The method for assessing dangerous behavior of an autonomous driving vehicle according to claim 6, wherein: When the target terminal reaches the preset identification point, the step of opening the communication link and sending the target response to the target terminal includes: From the video data, abnormal events are defined and the total number of abnormal events in each danger warning area is counted; Danger warning areas with a total number greater than a threshold are selected and defined as slow-moving sections. When the autonomous vehicle reaches the slow-moving section, the pre-configured deceleration control strategy is called and executed.

8. A dangerous behavior assessment system for an autonomous driving vehicle, characterized in that: The system comprises: The delineation module is used to delineate a danger warning area for autonomous vehicles, where the danger warning area consists of motor vehicle lanes and non-motor vehicle lanes. Monitoring equipment pre-deployed in the danger warning area is used to collect video data, select traffic participants that affect each other, and define sample vehicles in the motor vehicle lanes and interference objects in the non-motor vehicle lanes. Insertion module, used to collect behavioral characteristics of interference objects, and read the linkage response of sample vehicles at a preset step time, integrate behavioral characteristics and linkage response, generate a rule base, and insert risk level items; The obtaining module is used to define a target terminal when a Bluetooth beacon signal of an autonomous vehicle is collected by a Bluetooth device deployed in a danger warning area, and activate the monitoring device to collect real-time behavioral characteristics of traffic participants in the non-motorized vehicle lane, compare them with the rule library, and obtain a target response; The sending module is used to establish a communication link between the target terminal and the Bluetooth device, and capture the target terminal in the video data. When the target terminal reaches a preset identification point, the communication link is opened and the target response is sent to the target terminal.

9. The dangerous behavior assessment system for an autonomous driving vehicle according to claim 8, characterized in that: The delineation module includes: a construction unit for constructing a behavior pattern recognition model, wherein when a sample vehicle arrives at a marked point, a snapshot of the non-motor vehicle lane area is captured from the video data, and the snapshot is input into the behavior pattern recognition model to output a potential intention; a judgment unit, configured to judge whether there are traffic participants that affect each other on the motor vehicle lane and the non-motor vehicle lane according to the potential intention; An acquisition unit, configured to acquire driving data of an interfering object, wherein the driving data includes at least vehicle speed and driving position; An offset unit is configured to offset the risk level of the target response based on the driving data.

10. The dangerous behavior assessment system for an autonomous driving vehicle according to claim 9, characterized in that: The insertion module comprises: The startup unit is used to create a treatment plan that corresponds to the risk level. When the target response is determined, the corresponding treatment plan is started; The upload unit is used to delete abnormal responses from the rule base, integrate the rule base of all dangerous warning areas, build a management platform that coordinates all monitoring devices and Bluetooth devices, and upload the integrated rule base to the management platform.

Images