Cut-in Avoidance Assisted Driving Control Method, System, Electronic Device and Storage Medium

Abstract

The present invention provides a cut-in avoidance assisted driving control method, system, electronic device and storage medium. The method includes: when an adjacent vehicle has a cut-in intention, obtaining a plurality of avoidance behaviors that conform to the cut-in intention from a preset scenario library; obtaining the priorities of the plurality of avoidance behaviors, and calculating the avoidance results of each avoidance behavior according to the priorities; obtaining the avoidance behavior with the highest priority whose avoidance result is to avoid collision; outputting a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and updating the current avoidance scenario to the preset scenario library. By using the avoidance behavior with the highest priority to avoid collision to control the host vehicle to avoid the adjacent vehicle and updating the current avoidance scenario to the preset scenario library at the same time, the assisted driving system can better conform to the road traffic state through continuous update of the preset scenario library, and further improve the driving experience on the premise of ensuring driving safety.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive assisted driving, and more specifically, to a cut-in avoidance assisted driving control method, system, electronic device, and storage medium. Background Art

[0002] Currently, autonomous driving technology and assisted driving technology have become the most cutting-edge technologies in the automotive field. According to the J3016 classification standard of the SEA (Society of Automotive Engineer International) in June 2018, autonomous driving is defined into six levels from L0 to L5: L0 - no autonomous driving, L1 - assisted driving, L2 - partial autonomous driving, L3 - conditional autonomous driving, L4 - highly autonomous driving, and L5 - fully autonomous driving.

[0003] With the maturity of unmanned driving technology, although it still takes some time for unmanned driving technology to be popularized and applied, assisted driving technology, as a part of unmanned driving technology, has been widely used. In daily assisted driving applications, when the host vehicle encounters a lateral cut-in by another vehicle, in existing technical solutions, the avoidance strategy of the host vehicle is often formulated based on specific rules, resulting in the inability to further improve the driving experience. Summary of the Invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a cut-in avoidance assisted driving control method, system, electronic device, and storage medium to solve the problem that in existing technical solutions, the avoidance strategy of the host vehicle is often formulated based on specific rules, resulting in the inability to further improve the driving experience.

[0005] According to a first aspect of the present invention, there is provided a cut-in avoidance assisted driving control method, including:

[0006] When an adjacent vehicle has a cut-in intention, obtain a plurality of avoidance behaviors that match the cut-in intention from a preset scenario library;

[0007] Obtain the priorities of the plurality of avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities;

[0008] Obtain the avoidance behavior with the highest priority whose avoidance result is to avoid collision;

[0009] Output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the preset scenario library.

[0010] Based on the above technical solutions, the present invention can also be improved as follows.

[0011] Optionally, the preset scenario library is established and updated as follows:

[0012] Obtain the avoidance behaviors of vehicles in each avoidance scenario, and obtain the types of the avoidance behaviors;

[0013] Analyze the avoidance factors and vehicle control parameters in the avoidance behaviors, generate avoidance scenarios according to the avoidance factors, vehicle control parameters and the avoidance behaviors, and update the avoidance scenarios to the preset scenario library, where the type of the avoidance scenario is the type of the avoidance behavior.

[0014] Optionally, the types of the avoidance behaviors include longitudinal deceleration avoidance type, longitudinal acceleration avoidance type, in-lane lateral avoidance type, in-lane lateral avoidance and longitudinal deceleration type, in-lane lateral avoidance and longitudinal acceleration type, cross-lane lateral avoidance type, cross-lane lateral avoidance and longitudinal deceleration type, and cross-lane lateral avoidance and longitudinal acceleration type.

[0015] Optionally, after the step of updating the preset scenario library, it includes:

[0016] When the increment of avoidance scenarios in the preset scenario library reaches a preset number, obtain the percentile distribution of multiple vehicle control parameters in each avoidance scenario;

[0017] Push the percentile distribution of multiple vehicle control parameters of all avoidance scenarios to the host vehicle to determine the value of each vehicle control parameter;

[0018] Update the initial value of each vehicle control parameter according to the value of each vehicle control parameter.

[0019] Optionally, the step of outputting a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle further includes:

[0020] Calculate the minimum lateral and longitudinal acceleration corresponding to the avoidance behavior according to the vehicle control parameters corresponding to the avoidance behavior with the highest priority;

[0021] Calculate an avoidance trajectory according to the minimum lateral and longitudinal acceleration and the vehicle control parameters, and control the host vehicle to avoid the adjacent vehicle according to the avoidance trajectory.

[0022] Optionally, judge whether the adjacent vehicle has an intention to cut in through the following method:

[0023] When the lateral distance between the front wheels of the adjacent vehicle and the adjacent lane line is greater than a preset lateral distance, the lateral speed direction of the adjacent vehicle is towards the host vehicle, the lane-changing time of the adjacent vehicle is less than a preset lane-changing time, and the longitudinal distance by which the front of the adjacent vehicle exceeds the front of the host vehicle is greater than a preset longitudinal distance, or when the lateral distance between the front wheels of the adjacent vehicle and the adjacent lane line is less than the preset lateral distance, it is determined that the adjacent vehicle has an intention to cut in.

[0024] Optionally, the lane-changing avoidance assisted driving control method further includes:

[0025] If the avoidance result is that avoidance is not possible, control the host vehicle to longitudinally decelerate to avoid the adjacent vehicle.

[0026] According to a second aspect of the present invention, there is provided a lane-changing avoidance assisted driving control system, including:

[0027] An intention judgment module, configured to obtain a plurality of avoidance behaviors that conform to the lane-changing intention from a preset scenario library when an adjacent vehicle has a lane-changing intention;

[0028] A result calculation module, configured to obtain the priorities of the plurality of avoidance behaviors and calculate the avoidance results of each avoidance behavior according to the priorities;

[0029] A behavior selection module, configured to obtain the avoidance behavior with the highest priority and an avoidance result of avoiding collision;

[0030] A vehicle control module, configured to output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the preset scenario library.

[0031] According to a third aspect of the present invention, there is provided an electronic device, including a memory and a processor, and when the processor executes a computer management program stored in the memory, the steps of any of the lane-changing avoidance assisted driving control system methods in the first aspect are implemented.

[0032] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium, on which a computer management program is stored, and when the computer management program is executed by a processor, the steps of any of the lane-changing avoidance assisted driving control system methods in the first aspect are implemented.

[0033] An auxiliary driving control method, system, electronic device and storage medium for cut-in avoidance provided by the present invention. The method includes: when an adjacent vehicle has a cut-in intention, obtaining multiple avoidance behaviors that match the above cut-in intention from a preset scenario library; obtaining the priorities of the above multiple avoidance behaviors, and calculating the avoidance results of each avoidance behavior according to the above priorities; obtaining the avoidance behavior with the highest priority whose avoidance result is to avoid collision; outputting a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and updating the current avoidance scenario to the above preset scenario library. By preset conditions, the present invention can obtain the cut-in intention of the adjacent vehicle in real time, so that it can monitor the cut-in intentions of other vehicles around the host vehicle in real time, and then can perform avoidance operations in advance, increasing the safety of the host vehicle itself. When it is determined that the adjacent vehicle has a cut-in intention, multiple avoidance behaviors that match the above cut-in intention are obtained from the preset scenario library, and the avoidance behavior with the highest priority among the avoidance results for avoiding collision is obtained. The avoidance behavior with the highest priority among the above avoidances is used to control the host vehicle to avoid the adjacent vehicle, and at the same time, the current avoidance scenario is updated to the above preset scenario library, so as to achieve the purpose of updating the preset scenario library, and further enable the auxiliary driving system to better conform to the road traffic state through continuous update of the preset scenario library, and further improve the driving experience on the premise of ensuring driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of an auxiliary driving control method for cut-in avoidance provided by the present invention;

[0035] Figure 2 It is a schematic diagram of a vehicle cut-in schematic diagram provided by the present invention;

[0036] Figure 3 It is a first flowchart of a possible application scenario control provided by the present invention;

[0037] Figure 4 It is a second flowchart of a possible application scenario control provided by the present invention;

[0038] Figure 5 It is a schematic diagram of the structure of an auxiliary driving control system for cut-in avoidance provided by the present invention;

[0039] Figure 6 It is a schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0040] Figure 7 It is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] The following will further describe in detail the specific implementation manners of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0042] Figure 1 It is a flowchart of an assisted driving control method for cut-in avoidance provided by the present invention. As Figure 1 shown, the method includes:

[0043] Step S100: When the adjacent vehicle has a cut-in intention, obtain multiple avoidance behaviors that match the cut-in intention from a preset scenario library;

[0044] It should be noted that the execution subject of the method in this embodiment can be a computer terminal device with data processing, network communication, and program running functions, such as: in-vehicle computer, computer, etc.; it can also be a server device with the same or similar functions, or a cloud server with similar functions. This embodiment does not limit this. For the sake of understanding, this embodiment and the following embodiments will be described by taking an in-vehicle computer as an example.

[0045] It can be understood that the above adjacent vehicle can be a vehicle driving in the adjacent lane of the host vehicle. The above vehicle can be a motor vehicle, a non-motor vehicle, or a pedestrian with a cut-in intention. This embodiment does not limit this.

[0046] It should be understood that the above cut-in intention can refer to the possibility that the above adjacent vehicle leaves its current driving lane and laterally enters the host vehicle's lane.

[0047] It can also be understood that the above preset condition can be a condition for judging whether the above adjacent vehicle will cut into the host vehicle's current lane. For example, when the lateral distance between the front wheels of the adjacent vehicle and the adjacent lane line is less than 0.1 meter, it is determined that the adjacent vehicle has a cut-in intention. The setting method can be set during the initialization of the assisted driving system, or obtained by learning the key control parameters in the cut-in scenario, or synchronously set by continuously updating the cut-in scenario in the cloud server. This embodiment does not limit this.

[0048] It should also be understood that the above preset scenario library can be used to store the avoidance scenarios when the host vehicle or other vehicles cut in. The above avoidance scenarios can be obtained by analyzing the key parameters of traffic participants during the lane-changing process based on the lane-changing behaviors of road traffic participants collected by on-vehicle sensors, or updated to the local by synchronizing the avoidance scenarios from the cloud server segment. This embodiment does not limit this.

[0049] It should also be noted that the above vehicle-mounted sensors include, but are not limited to, a perception system composed of cameras, millimeter-wave radars, lidars, and ultrasonic radars at the front, left front, left rear, right front, right rear, directly rear, roof, etc., which can cover the vehicle's surrounding environment.

[0050] It should also be understood that the above avoidance behavior types include, but are not limited to: S001 longitudinal deceleration avoidance type, S002 longitudinal acceleration avoidance type, S003 in-lane lateral avoidance type, S004 in-lane lateral avoidance and longitudinal deceleration type, S005 in-lane lateral avoidance and longitudinal acceleration type, S006 cross-lane lateral avoidance type, S007 cross-lane lateral avoidance and longitudinal deceleration type, and S008 cross-lane lateral avoidance and longitudinal acceleration type.

[0051] In specific implementation, the in-vehicle computer of the host vehicle obtains the cut-in intention of the adjacent vehicle in real time through the vehicle-mounted sensors. When the above cut-in intention meets the preset conditions, an avoidance behavior similar to the scenario corresponding to the above cut-in intention is selected from the preset scenario library.

[0052] Step S200: Obtain the priorities of the multiple avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities;

[0053] It should be noted that the above priorities can be set during system initialization, can be generated according to the user's driving habits, or can be set according to the user's independent selection. This embodiment does not limit this.

[0054] It can be understood that the step of calculating the avoidance result through the avoidance behavior can be a process of substituting the relevant data in the current cut-in avoidance scenario into each avoidance behavior for solution. Among them,

[0055] S001 longitudinal deceleration avoidance solution: The auxiliary driving system presets the maximum deceleration A LonAcc , plan the trajectory of the host vehicle according to longitudinal deceleration avoidance, and judge whether there are still collision points. A LonAcc is the key control threshold;

[0056] S002 longitudinal acceleration avoidance solution: The auxiliary driving system presets the maximum acceleration A LonDCC , and at the same time sets the minimum following time interval T with the vehicle in front TimeGap , presets the maximum speed V max = 1.1*V limit , where V limit is the current road speed limit value, plan the trajectory of the host vehicle according to longitudinal acceleration, and judge whether there are still collision points with the cut-in target and the front target;

[0057] S003 in-lane lateral avoidance solution: The auxiliary driving system presets the maximum lateral offset S_horizontal and the maximum lateral acceleration ALatAcc , plan the trajectory of the host vehicle for lateral avoidance within the lane, and determine whether there are still collision points.

[0058] S004 Solve for lateral avoidance within the lane and longitudinal deceleration: The assisted driving system presets the maximum lateral offset S_hor and the maximum lateral acceleration A LatAcc , and the intelligent driving system presets the maximum deceleration A LonDCC , plan the trajectory of the host vehicle for lateral avoidance within the lane and longitudinal deceleration, and determine whether there are still collision points.

[0059] S005 Solve for lateral avoidance within the lane and longitudinal acceleration: The assisted driving system presets the maximum lateral offset S_hor and the maximum lateral acceleration A LatAcc , and the intelligent driving system presets the maximum longitudinal acceleration A LatAcc , and at the same time set the minimum following time interval T with the vehicle ahead TimeGap , preset the maximum speed V max = 1.1 * V limit , plan the trajectory of the host vehicle for lateral avoidance within the lane and longitudinal acceleration, and determine whether there are still collision points with the cut-in target and the vehicle ahead.

[0060] S006 Solve for lateral avoidance across lanes: The lane line on the avoidance side is a broken line, and the assisted driving system presets the lateral front safety space S on the avoidance side Front and S Rear , on the premise of meeting the conditions, with the maximum lateral acceleration A LatAcc , plan the trajectory of the host vehicle for lateral avoidance across lanes, and determine whether there are still collision points. The calculation formula is as follows:

[0061]

[0062] S Front = V ego *T timegap ;

[0063] Among them, V rear refers to the speed of the vehicle behind; V ego refers to the speed of the host vehicle; a = 3m / s 2 , refers to the deceleration of the vehicle behind; t B = 0.4s, the braking reaction time of the vehicle behind; t G = 1s, the following time interval of the vehicle behind after the host vehicle completes the lane change.

[0064] S007 Solve for lateral avoidance across lanes and longitudinal deceleration: The lane line on the avoidance side is a broken line, and the assisted driving system presets the lateral front safety space S on the avoidance side Front and S Rear , on the premise of meeting the conditions, with the maximum lateral acceleration A LatAcc, maximum deceleration A LonDCC , plan the trajectory of the host vehicle for cross-lane lateral avoidance and determine whether there are still collision points.

[0065] S008 Cross-lane lateral avoidance and longitudinal acceleration solution: The lane line on the avoidance side is a dotted line, and the ADAS presets the safe space S in the front side of the avoidance side Front and S Rear On the premise of meeting the conditions, with the maximum lateral acceleration A LatAcc , maximum acceleration A LonDCC , preset maximum speed V max = 1.1 * V limit , plan the trajectory of the host vehicle for cross-lane lateral avoidance and determine whether there are still collision points.

[0066] It should be understood that a preset priority ranking can be set for each of the above avoidance behaviors. For example, the preset priority ranking from high to low is: S001, S002, S003, S004, S005, S006, S007, and S008. The above initial priority can be adjusted and set by pushing the driving behavior data collected for the avoidance priority.

[0067] It can also be understood that the above avoidance behavior can be the behavior of the host vehicle avoiding the adjacent vehicle in the scenario where the adjacent vehicle cuts into the host vehicle's lane. The above avoidance behavior can also include the key parameters of traffic participants during the avoidance process, including but not limited to: the head-to-tail distance at the start of lane change, speed, acceleration, acceleration change rate, lane change completion time, and headway after lane change completion, etc.

[0068] It should also be understood that the above avoidance result can be calculated based on the set values of each vehicle control parameter in the above avoidance behavior to determine whether each avoidance behavior will ultimately successfully avoid the adjacent vehicle by itself. The above avoidance result can include: cannot avoid, avoid collision, etc., and this embodiment does not limit this.

[0069] In a specific implementation, the in-vehicle computer first obtains the priorities of the above multiple avoidance behaviors, and then calculates the final avoidance results of each avoidance behavior according to the priorities.

[0070] Step S300: Obtain the avoidance behavior with the highest priority and the avoidance result of avoiding collision;

[0071] Step S400: Output a control command according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the preset scenario library.

[0072] In a specific implementation, the in-vehicle computer generates a control instruction based on the control parameters in the avoidance behavior with the highest priority, and controls the host vehicle to avoid the adjacent vehicle according to the above control instruction. Meanwhile, the avoidance behavior, control parameters, and scenario factors in the current avoidance scenario are combined and updated to the above-mentioned preset scenario library.

[0073] It can be understood that, due to the deficiencies in the background technology, the embodiments of the present invention propose a lane-cutting avoidance assisted driving control method. When an adjacent vehicle has a lane-cutting intention, multiple avoidance behaviors that match the above lane-cutting intention are obtained from the preset scenario library; the priorities of the above multiple avoidance behaviors are obtained, and the avoidance results of each avoidance behavior are calculated according to the above priorities; the avoidance behavior with the highest priority whose avoidance result is to avoid collision is obtained; a control instruction is output according to the avoidance behavior with the highest priority to control the host vehicle to avoid the above adjacent vehicle, and the current avoidance scenario is updated to the above-mentioned preset scenario library. The present invention obtains the lane-cutting intention of the adjacent vehicle in real time through preset conditions, so that it can monitor the lane-cutting intentions of other vehicles around the host vehicle in real time, and then can perform avoidance operations in advance, increasing the safety of the host vehicle itself. When it is determined that the adjacent vehicle has a lane-cutting intention, multiple avoidance behaviors that match the above lane-cutting intention are obtained from the preset scenario library, and the avoidance behavior with the highest priority among the avoidance results to avoid collision is obtained, and the avoidance behavior with the highest priority among the above avoidance results to avoid collision is used to control the host vehicle to avoid the above adjacent vehicle. At the same time, through the vehicle-mounted sensing device and the V2X vehicle-to-vehicle communication device, the scenarios of the host vehicle and other vehicles dealing with lane-cutting behaviors can be dynamically obtained, enriching the scenario library and further achieving the purpose of updating the preset scenario library, so that the assisted driving system can better conform to the road traffic conditions through continuous updating of the preset scenario library, and further improve the driving experience on the premise of ensuring driving safety.

[0074] In a possible embodiment, the preset scenario library is established and updated in the following manner:

[0075] Step S010: Obtain the avoidance behaviors of the vehicle in each avoidance scenario, and obtain the types of the avoidance behaviors;

[0076] It should be noted that the above avoidance scenarios can be obtained by sensors to obtain the avoidance behaviors of the host vehicle or adjacent vehicles, or can be obtained by synchronizing the avoidance scenario library in the cloud server. This embodiment does not limit this.

[0077] Step S020: Analyze the avoidance factors and vehicle control parameters in the avoidance behavior, generate an avoidance scenario according to the avoidance factors, vehicle control parameters, and the avoidance behavior, and update the avoidance scenario to the preset scenario library. The type of the avoidance scenario is the type of the avoidance behavior.

[0078] It should be noted that the above avoidance factors may include: the type of the cut-in target, the lane where the host vehicle is located, the types of lane lines of the left and right adjacent lanes, traffic signs on the current road, weather conditions, and the types and motion states of targets within the nine-square grid range around the host vehicle. This embodiment places no restrictions on this.

[0079] It can be understood that the types and motion states of targets within the nine-square grid range around the host vehicle may be to divide a nine-square grid centered on the host vehicle and obtain information such as the types, positions, speeds, and accelerations of vehicles in the other eight grids.

[0080] In the method of this embodiment, by obtaining avoidance scenarios in the adjacent vehicle, the host vehicle, and / or the cloud server, the continuous update of the avoidance scenarios is realized. Furthermore, the above preset scenario library can be continuously filled, enabling the host vehicle to obtain control parameters in the avoidance behavior that more conform to the current scenario of the host vehicle, thereby greatly improving the avoidance success rate and reducing traffic risks during vehicle avoidance.

[0081] In a possible embodiment, the types of the avoidance behaviors include longitudinal deceleration avoidance type, longitudinal acceleration avoidance type, in-lane lateral avoidance type, in-lane lateral avoidance and longitudinal deceleration type, in-lane lateral avoidance and longitudinal acceleration type, cross-lane lateral avoidance type, cross-lane lateral avoidance and longitudinal deceleration type, and cross-lane lateral avoidance and longitudinal acceleration type.

[0082] In a possible embodiment, after the step of updating the preset scenario library, it includes:

[0083] Step S030: When the increment of avoidance scenarios in the preset scenario library reaches a preset quantity, obtain the percentile distribution of multiple vehicle control parameters in each avoidance scenario;

[0084] It should be noted that the above increment of avoidance scenarios may be the cumulative increase amount of avoidance scenarios in the above preset scenario library, and the above preset quantity may be a set threshold, which can generally be set to 70 - 80. This embodiment places no restrictions on this.

[0085] It can be understood that there is a corresponding avoidance behavior in each of the above avoidance scenarios, and the above avoidance behavior contains multiple vehicle control parameters. The above vehicle control parameters include but are not limited to: TTLC (time to line crossing), D (distance between the front wheel of the adjacent vehicle and the adjacent lane), S (preset maximum lateral offset), A LonDCC (preset maximum longitudinal acceleration), A LonAcc (preset maximum longitudinal deceleration), A LatAcc (maximum lateral acceleration), T TimeGap (minimum following time), a (deceleration of the vehicle behind), tB (Braking reaction time of the vehicle behind), t G (The following-distance between the following vehicle and the ego vehicle after the ego vehicle completes lane change).

[0086] It should be understood that the above percentile distribution can be obtained by sorting the actual values of the vehicle control parameters in all avoidance scenarios in the above preset scenario library in ascending order, dividing the sorted values into 100 equal parts, and the percentile is the actual value corresponding to the percentile.

[0087] Step S040: Push the percentile distribution of multiple vehicle control parameters of all avoidance scenarios to the ego vehicle to determine the value of each vehicle control parameter;

[0088] It should be noted that pushing the percentile distribution of vehicle control parameters to the ego vehicle as described above can be to push the percentile distribution of control parameters to the driver of the vehicle, so that the driver can select the control parameter threshold of each control parameter, thereby determining the value of each measured control parameter.

[0089] Step S050: Update the initial value of each vehicle control parameter according to the value of each vehicle control parameter.

[0090] It should be noted that the above initial value can be a default value set for each vehicle control parameter during system initialization.

[0091] In this embodiment, by allowing the driver to select the threshold of the vehicle control parameter during the avoidance process and updating the initial threshold of the vehicle control parameter after the driver's selection, the method of this embodiment becomes more anthropomorphic, achieving the effect of improving the driving experience, and further achieving the purpose of enhancing the user experience and lane-changing efficiency.

[0092] In a possible embodiment, the step of outputting a control instruction according to the avoidance behavior with the highest priority to control the ego vehicle to avoid the adjacent vehicle further includes:

[0093] Step S401: Calculate the minimum lateral and longitudinal acceleration corresponding to the avoidance behavior according to the vehicle control parameter corresponding to the avoidance behavior with the highest priority;

[0094] Step S402: Calculate an avoidance trajectory according to the minimum lateral and longitudinal acceleration and the vehicle control parameter, and control the ego vehicle to avoid the adjacent vehicle according to the avoidance trajectory.

[0095] In the embodiment of the present invention, by calculating the minimum lateral and longitudinal acceleration control parameter that can avoid collision based on the avoidance behavior with the highest priority, and calculating the avoidance trajectory according to the above vehicle control parameter and the minimum lateral and longitudinal acceleration control parameter, the success rate of the ego vehicle's avoidance is further improved, and the risk of traffic safety accidents is reduced.

[0096] In a possible embodiment, it is determined whether the adjacent vehicle has an intention to cut in by the following method: when the lateral distance between the front wheels of the adjacent vehicle and the adjacent lane line is greater than a preset lateral distance, the lateral speed direction of the adjacent vehicle is towards the host vehicle, the lane-changing time of the adjacent vehicle is less than a preset lane-changing time, and the longitudinal distance by which the front of the adjacent vehicle exceeds the front of the host vehicle is greater than a preset longitudinal distance, or when the lateral distance between the front wheels of the adjacent vehicle and the adjacent lane line is less than the preset lateral distance, it is determined that the adjacent vehicle has an intention to cut in.

[0097] It should be noted that the above preset lateral distance can be an initial value set during system initialization, or a set value after providing the avoidance behavior parameters in the preset scenario library for the driver to select. The initial value of the above preset lateral distance can usually be set to 0.1 meter.

[0098] It can be understood that the above preset lane-changing time can be an initial value set during system initialization, or a set value after providing the avoidance behavior parameters in the preset scenario library for the driver to select. The initial value of the above preset lane-changing time can usually be set to 1 second.

[0099] It should be understood that the above preset longitudinal distance can be an initial value set during system initialization, or a set value after providing the avoidance behavior parameters in the preset scenario library for the driver to select. The initial value of the above preset longitudinal distance can usually be set to 1 meter.

[0100] In a possible embodiment, the above-mentioned cut-in avoidance assisted driving control method further includes: if the avoidance result is that avoidance cannot be achieved, controlling the host vehicle to decelerate longitudinally to avoid the adjacent vehicle.

[0101] It should be noted that when the above avoidance result is that avoidance cannot be achieved, it can be a situation where in the method of this embodiment, through calculation, none of the above avoidance behaviors can complete the avoidance of the adjacent vehicle without causing a traffic safety accident.

[0102] In the method of this embodiment, by selecting longitudinal retrieval to avoid the adjacent vehicle when it is impossible to avoid the adjacent vehicle, the traffic safety risk is minimized, and the safety of the host vehicle is greatly improved.

[0103] In a possible application scenario, it is not excluded that in the case of manual driving, when faced with the cut-in of another vehicle, due to the host vehicle having the priority right of way in the current lane, the driver may not avoid subjectively. Optionally, the present invention can also establish a non-avoidance behavior, collect data, establish scenarios, arrange priorities, etc. for this behavior, and the assisted driving system can also schedule and execute it accordingly.

[0104] In a possible application scenario, the above control parameters take into account traffic regulations. When changing lanes to avoid, it is required to be a dotted line and the upper limit is 1.1 times the speed limit. However, in some emergency situations, changing lanes to avoid or exceeding the speed limit threshold is required to avoid collisions. Then, optionally, on the premise of avoiding collisions, the preset limit conditions such as the type of road boundary line and speed limit in extreme cases can also be designed as parameters. If a sufficient number of driving behavior samples can be accumulated in the establishment of the scenario library, such avoidance behaviors can be scheduled in the scenario selection of the avoidance behavior, and emergency avoidance actions can be executed to further improve the avoidance success rate of the assisted driving system.

[0105] In a possible application scenario, to further illustrate the situation of judging whether the adjacent vehicle has an intention to cut in, this embodiment will be described with reference to the accompanying drawings. See Figure 2 , Figure 2 FIG. is a schematic diagram of a vehicle cutting-in provided by the present invention; Figure 2 In the figure, vehicle A is the host vehicle and vehicle B is the adjacent vehicle. l A is the original driving path of the host vehicle, and l B is the predicted cutting-in trajectory of the adjacent vehicle. D is the lateral distance between the front wheel of the adjacent vehicle and the adjacent lane line, S is the longitudinal distance by which the front of the adjacent vehicle exceeds the front of the host vehicle, C is the predicted collision point of vehicles A and B, T0 is the initial moment, T1 is the collision moment, and T is the collision time interval.

[0106] In the above application scenario, when the lateral distance D between the front wheel of the adjacent vehicle and the adjacent lane line is greater than 0.1 meter, the lateral speed direction of the adjacent vehicle is towards the host vehicle, the lane-changing time of the adjacent vehicle is less than 1 second, and the longitudinal distance S by which the front of the adjacent vehicle exceeds the front of the host vehicle is greater than 1 meter, or when the lateral distance D between the front wheel of the adjacent vehicle and the adjacent lane line is less than 0.1 meter, it is determined that the adjacent vehicle has an intention to cut in.

[0107] In the above application scenario, starting from the moment when it is determined that the adjacent vehicle has an intention to cut in, the cutting-in trajectory of the adjacent vehicle can be predicted according to the motion state of the adjacent vehicle, and it is determined whether there will be an intersection with the host vehicle trajectory and a collision will occur after a certain time T according to the predicted cutting-in trajectory. When there is a collision risk, the method of the present invention needs to be executed for avoidance.

[0108] In a possible application scenario, to further introduce the possible control flow of the invention embodiment in detail, see Figure 3 , Figure 3 FIG. is a first flowchart of possible application scenario control provided by the present invention.

[0109] In this application scenario, the steps in the above flowchart include:

[0110] The assisted driving system collects driving behaviors and road traffic information during cut-in avoidance. Among them, the above-mentioned road traffic information includes, but is not limited to: cut-in target type, the lane where the host vehicle is located, the lane line types of the left and right adjacent lanes, traffic signs (speed limits, etc.) on the current road, weather conditions, target types within the nine-square grid range around the host vehicle, and the motion state of the host vehicle, etc.

[0111] Classify the avoidance driving behaviors, where the avoidance driving behaviors include: longitudinal deceleration avoidance, longitudinal acceleration avoidance, lateral avoidance within the lane, lateral avoidance within the lane and longitudinal deceleration, lateral avoidance within the lane and longitudinal acceleration, cross-lane lateral avoidance, cross-lane lateral avoidance and longitudinal deceleration, and cross-lane lateral avoidance and longitudinal acceleration.

[0112] Further analyze the correlation between the cut-in target type and the avoidance behavior. Among them, the analysis of the correlation between the cut-in target type and the avoidance behavior can be to analyze and obtain the correlation between the cut-in target type, the lane where the host vehicle is located, the target types of the front and rear doors, weather, traffic information, etc. and the avoidance behavior.

[0113] Component scenario library, which contains the priorities of different avoidance behaviors in specific scenarios.

[0114] Analyze the driving behavior, mainly used to calculate specific driving control parameters such as the judgment cut-in timing, longitudinal and lateral accelerations, lateral offset distance, following time interval, etc. of all avoidance behaviors.

[0115] Build a control parameter library, and the parameters in the control parameter library are distributed according to percentiles for the calculated driving parameters.

[0116] Push the percentile values to the driver for selection. Among them, after a certain number of scenarios are added to the scenario library, the control parameter thresholds are pushed to the driver according to the percentile distribution, so that the driver can select the control parameter thresholds that conform to their own driving habits and update the initial control parameter thresholds.

[0117] The cut-in intention of the adjacent vehicle is established. Among them, it is judged whether the adjacent vehicle has a cut-in intention according to the control parameter thresholds selected by the driver.

[0118] Perform scenario scheduling in the scenario library, and find the scenario that conforms to the current cut-in intention of the adjacent vehicle by matching in the preset scenario library.

[0119] Solve the self-vehicle avoidance behavior according to the updated threshold value to determine whether there is a solution that can avoid the collision. If there is no solution, the default S001 longitudinal deceleration avoidance is selected, and the control parameter selects the maximum deceleration to perform the avoidance behavior. If it is determined that there are multiple solutions, the avoidance behavior with the highest priority is selected, the control parameters in the above avoidance behavior are obtained for calculation and selection, and then the control instructions are generated, and the avoidance behavior is executed according to the above control instructions. If it is determined that there is only one solution, the corresponding avoidance behavior is directly obtained, and the control parameters in the above avoidance behavior are obtained for calculation and selection, and then the control instructions are generated, and the avoidance behavior is executed according to the above control instructions.

[0120] In another possible implementation scenario, in order to avoid traffic accidents as much as possible, the vehicle can also perform evasive behavior beyond the factors stipulated by the traffic law while ensuring its own safety as much as possible. Figure 4 , Figure 4 A possible application scenario control second flow chart provided by the present invention, since the steps before the collision avoidance solution are all the same as Figure 3 The steps before solving the problem are consistent with those in the previous scenario, and will not be repeated in this implementation scenario.

[0121] In the scenario of this embodiment, when the existing avoidance behavior solution is found to be unsolvable, the self-driving assisted driving system releases the speed limit threshold and the dashed line lane change restrictions and solves again. If a solution is found, the avoidance behavior is selected according to the priority, the control parameters in the avoidance behavior are obtained for calculation and selection, and then a control instruction is generated, and the avoidance behavior is executed according to the control instruction. If there is still no solution, S001 longitudinal deceleration avoidance is selected by default, and the control parameter selects the maximum deceleration to execute the avoidance behavior.

[0122] In the scenario of this embodiment, considering that some emergency situations require cross-lane avoidance or exceeding the speed limit threshold to avoid collision, it is optional to take avoiding collision as a prerequisite, and in extreme cases, preset limit conditions such as road boundary line type and speed limit can also be designed as parameters. If a sufficient number of driving behavior samples can be accumulated in the establishment of the scenario library, such avoidance behavior can be scheduled in the scene when the avoidance behavior is selected, and emergency avoidance actions can be executed, thereby further improving the avoidance success rate of the assisted driving system.

[0123] Figure 5 A schematic diagram of a structure of a cut-in avoidance assisted driving control system provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, a cut-in avoidance assisted driving control system includes an intention judgment module 100, a result calculation module 200, a behavior selection module 300 and a vehicle control module 400, wherein:

[0124] An intention judgment module 100, when there is an intention of the adjacent vehicle to cut in, obtains a plurality of avoidance behaviors that conform to the cut-in intention from a preset scenario library; a result calculation module 200, configured to obtain the priorities of the plurality of avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities; a behavior selection module 300, configured to obtain the avoidance behavior with the highest priority whose avoidance result is to avoid collision; a vehicle control module 400, configured to output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle.

[0125] It can be understood that an assisted driving control system for cut-in avoidance provided by the present invention corresponds to the assisted driving control method for cut-in avoidance provided in the foregoing embodiments. The relevant technical features of the assisted driving control system for cut-in avoidance can refer to the relevant technical features of the assisted driving control method for cut-in avoidance, which will not be elaborated here.

[0126] Please refer to Figure 6 , Figure 6 which is a schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. As Figure 6 shown, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are implemented:

[0127] When there is an intention of the adjacent vehicle to cut in, obtain a plurality of avoidance behaviors that conform to the above cut-in intention from a preset scenario library; obtain the priorities of the plurality of avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities; obtain the avoidance behavior with the highest priority whose avoidance result is to avoid collision; output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the above preset scenario library.

[0128] Please refer to Figure 7 , Figure 7 which is a schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. As Figure 7 shown, this embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, the following steps are implemented:

[0129] When there is an intention of the adjacent vehicle to cut in, obtain a plurality of avoidance behaviors that conform to the above cut-in intention from a preset scenario library; obtain the priorities of the plurality of avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities; obtain the avoidance behavior with the highest priority whose avoidance result is to avoid collision; output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the above preset scenario library.

[0130] An assisted driving control method, system and storage medium for cut-in avoidance provided by an embodiment of the present invention. The method includes: when a neighboring vehicle has a cut-in intention, obtaining multiple avoidance behaviors that match the above cut-in intention from a preset scenario library; obtaining the priorities of the above multiple avoidance behaviors, and calculating the avoidance results of each avoidance behavior according to the above priorities; obtaining the avoidance behavior with the highest priority whose avoidance result is to avoid collision; outputting a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the neighboring vehicle, and updating the current avoidance scenario to the above preset scenario library. The present invention obtains the cut-in intention of the neighboring vehicle in real time through preset conditions, so that it can monitor the cut-in intentions of other vehicles around the host vehicle in real time, and then can perform avoidance operations in advance, increasing the safety of the host vehicle itself. When it is determined that the neighboring vehicle has a cut-in intention, multiple avoidance behaviors that match the above cut-in intention are obtained from the preset scenario library, and the avoidance behavior with the highest priority among the avoidance results for avoiding collision is obtained. The avoidance behavior with the highest priority among the above avoidance of collision is used to control the host vehicle to avoid the neighboring vehicle, and at the same time, the current avoidance scenario is updated to the above preset scenario library, so as to achieve the purpose of updating the preset scenario library, and further enable the assisted driving system to be more in line with the road traffic conditions through continuous updating of the preset scenario library, and further improve the driving experience on the premise of ensuring driving safety.

[0131] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0132] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, system, or computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocksFigure 1 means for the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one Figure 1 or more processes and / or boxes Figure 1 or more boxes.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one Figure 1 or more processes and / or boxes Figure 1 or more boxes.

[0136] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0137] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A cut-in avoidance assisted driving control method, characterized in that The method includes: When the adjacent vehicle has an intention to cut in, obtain multiple avoidance behaviors that match the cut-in intention from a preset scenario library; Obtain the priorities of the multiple avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities; Obtain the avoidance behavior with the highest priority whose avoidance result is to avoid collision; Output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the preset scenario library; Establish and update the preset scenario library in the following manner: Obtain the avoidance behaviors of the vehicle in each avoidance scenario, and obtain the types of the avoidance behaviors; Analyze the avoidance factors and vehicle control parameters in the avoidance behavior, generate an avoidance scenario according to the avoidance factors, vehicle control parameters and the avoidance behavior, and update the avoidance scenario to the preset scenario library, and the type of the avoidance scenario is the type of the avoidance behavior.

2. The cut-in avoidance assisted driving control method according to claim 1, wherein The types of the avoidance behaviors include longitudinal deceleration avoidance type, longitudinal acceleration avoidance type, lateral avoidance type within the lane, lateral avoidance and longitudinal deceleration type within the lane, lateral avoidance and longitudinal acceleration type within the lane, cross-lane lateral avoidance type, cross-lane lateral avoidance and longitudinal deceleration type, and cross-lane lateral avoidance and longitudinal acceleration type.

3. The cut-in avoidance assisted driving control method according to claim 1, wherein After the step of updating the preset scenario library, it includes: When the increment of avoidance scenarios in the preset scenario library reaches a preset number, obtain the percentile distribution of multiple vehicle control parameters in each avoidance scenario; Push the percentile distribution of multiple vehicle control parameters of all avoidance scenarios to the host vehicle to determine the value of each vehicle control parameter; Update the initial value of each vehicle control parameter according to the value of each vehicle control parameter.

4. The cut-in avoidance assisted driving control method according to claim 1, characterized in that The step of outputting a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle further includes: Calculate the minimum transverse and longitudinal accelerations corresponding to the avoidance behavior according to the vehicle control parameters corresponding to the avoidance behavior with the highest priority; Calculate an avoidance trajectory according to the minimum transverse and longitudinal accelerations and the vehicle control parameters, and control the host vehicle to avoid the adjacent vehicle according to the avoidance trajectory.

5. The cut-in avoidance assisted driving control method according to claim 1, characterized in that Judge whether the adjacent vehicle has an intention to cut in by the following method: When the lateral distance between the front wheel of the adjacent vehicle and the adjacent lane line is greater than a preset lateral distance, the lateral speed direction of the adjacent vehicle is towards the host vehicle, the lane-changing time of the adjacent vehicle is less than a preset lane-changing time, and the longitudinal distance by which the front of the adjacent vehicle exceeds the front of the host vehicle is greater than a preset longitudinal distance, or when the lateral distance between the front wheel of the adjacent vehicle and the adjacent lane line is less than the preset lateral distance, it is determined that the adjacent vehicle has an intention to cut in.

6. The cut-in avoidance assisted driving control method according to claim 1, further includes: If the avoidance result is that it cannot avoid, control the host vehicle to longitudinally decelerate to avoid the adjacent vehicle.

7. An auxiliary driving control system for cutting-in avoidance, characterized in that, It includes An intention judgment module, configured to, when the adjacent vehicle has an intention to cut in, obtain multiple avoidance behaviors that match the cut-in intention from a preset scenario library; A result calculation module, configured to obtain the priorities of the multiple avoidance behaviors, and calculate the avoidance results of each avoidance behavior according to the priorities; A behavior selection module, configured to obtain the avoidance behavior with the highest priority whose avoidance result is to avoid collision; A vehicle control module, configured to output a control instruction according to the avoidance behavior with the highest priority to control the host vehicle to avoid the adjacent vehicle, and update the current avoidance scenario to the preset scenario library; The preset scenario library is established and updated in the following manner: Obtain the avoidance behaviors of vehicles in each avoidance scenario, and obtain the types of the avoidance behaviors; Analyze the avoidance factors and vehicle control parameters in the avoidance behavior, generate an avoidance scenario according to the avoidance factors, vehicle control parameters and the avoidance behavior, and update the avoidance scenario to the preset scenario library, where the type of the avoidance scenario is the type of the avoidance behavior.

8. An electronic device, characterized in that, It includes a memory and a processor, and the processor is configured to implement the steps of the cut-in avoidance assisted driving control method according to any one of claims 1-6 when executing a computer management program stored in the memory.

9. A computer-readable storage medium, characterized in that, A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the cut-in avoidance assisted driving control method according to any one of claims 1-6 are implemented.

Images