Vehicle offset control method and electronic equipment

Abstract

The invention provides a vehicle deviation control method and electronic equipment, and the method comprises the steps: obtaining a reference driving path of a vehicle, obtaining object positions of detection objects in a plurality of nearby lanes, and obtaining a lane line position corresponding to the reference driving path, and responding to a detected lane change request; the reference driving path and the corresponding lane line position are updated, the object position is updated according to the relative transverse distance between the object position and the updated reference driving path, and the lane changing offset driving path of the vehicle is generated through the updated lane line position and the object position, so that the vehicle is controlled to drive along the lane changing offset driving path. The offset is completed in the lane changing process, numerous scenes do not need to be designed for lane changing offset in advance, and the problems of large computing power burden, abnormal exit and the like caused by numerous scene designs are solved.

Description

Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a vehicle deviation control method and electronic equipment. Background Art

[0002] Currently, intelligent assisted driving functions have begun to be highly praised by consumers, and the functions are more frequently turned on when driving on highways. For example, if there is an obstacle in the side lane when driving on the highway, the vehicle can be controlled to actively deviate.

[0003] Currently, many solutions are mainly aimed at side lanes. The common active offset method is to bind the offset vehicle or curb in the side lane, or to design many scenarios when changing lanes. The former is more dependent on accurate input from the front end, and the latter will increase the computing power burden. In the actual engineering application process, there will be abnormal exits and no action on objects that need to be offset in the lane adjacent to the lane changing lane when changing lanes. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, the present application aims to provide a vehicle offset control method and electronic device to solve the problems in the prior art such as heavy computing power burden, abnormal exit, and no action on objects that need to be offset in the lane adjacent to the lane changing lane when changing lanes.

[0005] The present application provides a vehicle deviation control method, the method comprising:

[0006] Acquire a reference driving path of a vehicle, and acquire an object position of each detection object in a plurality of lanes near the vehicle, and a lane line position corresponding to the reference driving path;

[0007] In response to detecting a lane change request of the vehicle, updating the reference driving path and the corresponding lane line position based on a target lane corresponding to the lane change request, and updating the object position according to a relative lateral distance between the object position and the updated reference driving path;

[0008] Based on the updated lane line position and the updated object position, determining an object to be avoided among the detected objects, and determining an offset of the vehicle based on the object to be avoided;

[0009] A lane-changing offset driving path is generated based on the offset and the target lane, and the vehicle is controlled to travel along the lane-changing offset driving path.

[0010] Optionally, generating a lane change deviation driving path based on the updated lane line position and the updated object position includes:

[0011] Based on the updated lane line position and the updated object position, determining an object to be avoided among the detected objects, and determining an offset of the vehicle based on the object to be avoided;

[0012] A lane change offset driving path is generated based on the offset and the target lane.

[0013] Optionally, the detected object includes a curb, and based on the updated lane line position and the updated object position, determining the object to be avoided from each detected object includes:

[0014] For each curb, determine a longitudinal distance between the curb and the vehicle based on the updated object position of the curb, and determine a lateral distance between the curb and the lane line based on the updated object position of the curb and the updated lane line position;

[0015] If the longitudinal distance is less than the curb longitudinal distance threshold, and the lateral distance is less than the curb lateral distance threshold, and the duration for which the lateral distance is less than the curb lateral distance threshold reaches a preset duration, the curb is determined as an object to be avoided.

[0016] Optionally, the detection object includes a target vehicle, and based on the updated lane line position and the updated object position, determining the object to be avoided from each detection object includes:

[0017] Acquire the status information of each target vehicle, remove the target vehicles with attributes of being traveling in the opposite direction or stationary in the status information, and remove the target vehicles located in the lane corresponding to the reference driving path;

[0018] For each target vehicle, based on the vehicle type of the target vehicle, the updated object position of the target vehicle and the updated lane line position, it is determined whether the target vehicle meets the preset avoidance conditions. If so, the target vehicle is determined as the object to be avoided.

[0019] Optionally, judging whether the target vehicle satisfies a preset avoidance condition based on the vehicle type of the target vehicle, the updated object position of the target vehicle, and the updated lane line position includes:

[0020] In response to determining that the vehicle type of the target vehicle is the first type, based on the updated object position and the updated lane line position, determining whether the target vehicle is located on the lane line, and if so, determining whether the target vehicle satisfies the corresponding lateral and longitudinal distance conditions according to the state information of the target vehicle and the updated object position, and if so, determining that the target vehicle satisfies the preset avoidance condition; or,

[0021] In response to determining that the vehicle type of the target vehicle is the second type, judging whether the target vehicle satisfies corresponding lateral and longitudinal distance conditions according to the state information of the target vehicle and the updated object position, and if so, determining that the target vehicle satisfies a preset avoidance condition.

[0022] Optionally, the method further includes:

[0023] Determining the safety risk level of the object to be avoided;

[0024] Determining the offset of the vehicle based on the object to be avoided includes:

[0025] In response to determining that there are multiple objects to be avoided, an offset direction of the vehicle is determined based on an updated position of an object to be avoided with a highest safety risk level, and an offset amount of the vehicle is determined based on the offset direction and a lane width of the target lane.

[0026] Optionally, before determining the offset direction of the vehicle based on the updated position of the object to be avoided having the highest safety risk level, the method further includes:

[0027] Based on the updated position of each of the objects to be avoided, it is determined whether there are objects to be avoided located on both sides of the target lane, and the longitudinal distance difference between the objects to be avoided located on both sides of the target lane is less than a preset threshold;

[0028] If so, a lane-changing driving path is generated based on the target lane, and the vehicle is controlled to travel along the lane-changing driving path.

[0029] Optionally, before determining the offset of the vehicle based on the object to be avoided, the method further includes:

[0030] For each of the objects to be avoided, determining whether the corresponding detected object has been determined as an object to be avoided in a plurality of consecutive historical moments before the current moment;

[0031] If not, the object to be avoided is eliminated.

[0032] Optionally, before determining the offset of the vehicle based on the object to be avoided, the method further includes:

[0033] Obtaining the speed of the vehicle and the curvature radius of the lane in which the vehicle is currently located;

[0034] In response to determining that the vehicle speed is greater than a preset speed threshold and the curvature radius is greater than a preset radius threshold, a step of determining an offset of the vehicle based on the object to be avoided is performed.

[0035] The present application also provides an electronic device, the electronic device comprising:

[0036] Processor and memory;

[0037] The processor is used to execute the steps of the vehicle deviation control method provided in any embodiment of the present application by calling the program or instruction stored in the memory.

[0038] An embodiment of the present application also provides a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute the steps of the vehicle deviation control method provided by any embodiment of the present application.

[0039] In summary, the present application proposes a vehicle offset control method, which obtains a reference driving path of a vehicle, and obtains the object position of each detection object in multiple nearby lanes, and the lane line position corresponding to the reference driving path, and then responds to the detection of a lane change request. Based on the target lane corresponding to the lane change request, the reference driving path and the corresponding lane line position are updated, and the object position is updated according to the relative lateral distance between the object position and the updated reference driving path. The vehicle's lane change offset driving path is generated through the updated lane line position and the updated object position, so as to control the vehicle to travel along the lane change offset driving path, and lane change offset can be achieved. The method can update the reference driving path according to the lane change request, update the position through the lateral distance of each object position relative to the reference driving path, and generate the lane change offset driving path based on the lateral distance, so as to complete the offset during the lane change process, avoid the object that needs to be offset, and ensure the driving safety of the vehicle. There is no need to design many scenarios for lane change offset in advance, which solves the problems of heavy computing power burden and abnormal exit caused by multiple scenario designs, and can also solve the problem of not taking action on the object that needs to be offset in the adjacent lane of the lane change lane. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 is a flow chart of a vehicle deviation control method provided by an embodiment of the present application;

[0042] Figure 2 is a schematic diagram of a translation process provided by an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of an offset for a large vehicle provided in an embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of an offset for a curb provided in an embodiment of the present application;

[0045] Figure 5 It is a schematic diagram of an offset of a wire crimping trolley provided in an embodiment of the present application;

[0046] Figure 6 This is a schematic diagram of an offset in a centering driving scenario provided by an embodiment of the present application;

[0047] Figure 7 is a structural schematic diagram of a vehicle deviation control device provided in an embodiment of the present application;

[0048] Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0050] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0051] As mentioned in the background technology, in order to solve the problems in the prior art, the present application proposes a vehicle deviation control method. Figure 1 is a flow chart of a vehicle deviation control method provided by an embodiment of the present application. Figure 1 , the vehicle deviation control method specifically includes:

[0052] S110, obtaining a reference driving path of the vehicle, and obtaining the object position of each detection object in a plurality of lanes near the vehicle, and the lane line position corresponding to the reference driving path.

[0053] The vehicle may be understood as the vehicle itself. The reference driving path may be a reference path that the vehicle is traveling at the current moment. Exemplarily, the reference driving path may be the center line of the lane where the vehicle is currently located.

[0054] In the embodiment of the present application, the detection object may be other set objects other than the vehicle, such as a curb, a target vehicle, etc. The detection objects in multiple lanes near the vehicle can be identified by sensors (visual sensors, radar sensors, etc.) carried on the vehicle. Among them, the multiple lanes near the vehicle include the lane where the vehicle is located, the adjacent lanes of the lane where the vehicle is located, and other lanes adjacent to the adjacent lanes. Taking the five-lane model as an example, the detection objects in the self-lane, left lane, left-left lane, right lane, and right-right lane can be sensed.

[0055] Specifically, based on the sensors mounted on the vehicle, each detection object in multiple lanes near the vehicle can be identified, and the object position of each detection object in the multiple lanes and the position of each lane line in the multiple lanes can be detected, and the lane line position corresponding to the reference driving path can be selected from each lane line position. The lane line position corresponding to the reference driving path can be the position of the left and right lane lines of the lane where the reference driving path is located.

[0056] It should be noted that the object positions of each detection object and the lane line positions obtained at this time are all positions obtained with the vehicle as the coordinate origin, that is, positions relative to the vehicle.

[0057] S120, in response to detecting a lane change request of the vehicle, updating a reference driving path and a corresponding lane line position based on a target lane corresponding to the lane change request, and updating an object position according to a relative lateral distance between the object position and the updated reference driving path.

[0058] The lane change request may be a request for controlling the vehicle to change lanes. Exemplarily, the lane change request may be generated based on a user's lane change operation with a lever, or may be generated by the vehicle's intelligent driving system when it detects that the vehicle needs to actively change lanes.

[0059] Specifically, if a lane change request of the vehicle is detected, the target lane corresponding to the lane change request can be determined, and then the reference driving path and the corresponding lane line position can be updated according to the target lane. For example, the reference driving path can be updated to the center line of the target lane, and the lane line position corresponding to the reference driving path can be updated to the position of the left and right lane lines of the target lane.

[0060] In the embodiment of the present application, the purpose of updating the reference driving path and the corresponding lane line position based on the target lane is: after detecting a lane change request, it can be determined that the vehicle is about to change lanes to the target lane. In order to realize the offset detection of the adjacent lanes of the target lane, the reference driving path can be updated to the center line of the target lane, which is convenient for the subsequent combination of the reference driving path and the object position of each detection object, to identify the detection object that needs to be offset, and complete the offset during the lane change process.

[0061] Specifically, after updating the reference driving path and the corresponding lane line position, the object position of each detection object can be updated according to the relative lateral distance between the object position of the detection object and the updated reference driving path. That is, the object position of the detection object is translated and converted from the original reference driving path (or can be understood as the vehicle coordinate system) to the updated reference driving path.

[0062] Exemplarily, for each detected object, a relative lateral distance between the object position of the detected object and the updated reference driving path may be calculated, and then the lateral position of the object position may be updated to the relative lateral distance, while the longitudinal position of the object position may remain unchanged.

[0063] like Figure 2 As shown, Figure 2 This is a schematic diagram of translation processing provided by an embodiment of the present application, taking the case where the vehicle is located in the middle lane of a five-lane road as an example. Assuming that the detection object is a target vehicle, the updated lateral position of the target vehicle is Y=Y0-C0, where Y0 is the lateral position of the target vehicle before the update, and C0 is the lateral position of the reference driving path after the update;

[0064] Assuming that the detection object is a curb, the updated lateral position of the left curb ILEC0=LEC0-C0, and the updated lateral position of the right curb IRIC0=RIC0-C0, wherein LEC0 is the lateral position of the left curb before updating, and RIC0 is the lateral position of the right curb before updating;

[0065] If the updated reference driving path is located to the left of the reference driving path before the update, C0 can be regarded as a positive value, then the lateral position of the left lane line corresponding to the updated reference driving path LC0 = SecLC0-C0, and the lateral position of the right lane line corresponding to the updated reference driving path RC0 = CLeC0-C0; if the updated reference driving path is located to the right of the reference driving path before the update, C0 can be regarded as a negative value, then the lateral position of the left lane line corresponding to the updated reference driving path LC0 = CRiC0-C0, and the lateral position of the right lane line corresponding to the updated reference driving path RC0 = SecRiC0-C0, wherein SecLC0 is the lateral position of the left-left lane line of the reference driving path before the update, SecRiC0 is the lateral position of the right-right lane line of the reference driving path before the update, CLeC0 is the lateral position of the left lane line of the reference driving path before the update, and CRiC0 is the lateral position of the right lane line of the reference driving path before the update.

[0066] In the embodiment of the present application, in order to achieve the completion of the offset during the lane change process and avoid the safety risks caused by the offset after the lane change is completed, it is also possible to determine that the vehicle has entered the target lane and completed the lane change when it is detected that the vehicle has crossed the lane line position corresponding to the updated reference driving path. At this time, there is a certain safety risk in controlling the vehicle to offset. Therefore, if it is detected that the vehicle has crossed the lane line position corresponding to the updated reference driving path, the object position of each detection object can be cleared, that is, the translated position is set, and then the object position of each detection object is re-detected, and then the offset control can be performed according to the offset control strategy in the vehicle center driving scenario. Among them, the offset control strategy in the vehicle center driving scenario can be referred to the description below.

[0067] S130: Generate a lane-changing offset driving path based on the updated lane line position and the updated object position, and control the vehicle to travel along the lane-changing offset driving path.

[0068] Specifically, after the reference driving path is updated and the object positions of each detected object and the lane line positions corresponding to the reference driving path are updated, the lane change offset driving path of the vehicle can be generated according to the updated lane line positions and object positions. For example, it can be determined whether each detected object needs to be avoided, and the object to be avoided can be determined therefrom, so as to generate a lane change offset driving path for the object to be avoided.

[0069] In a specific implementation, generating a lane change offset driving path based on an updated lane line position and an updated object position includes:

[0070] Based on the updated lane line position and the updated object position, the object to be avoided is determined among the detected objects, and the offset of the vehicle is determined based on the object to be avoided; and a lane change offset driving path is generated based on the offset and the target lane.

[0071] The detection objects may include curbs and target vehicles. For curbs and target vehicles, whether they need to be avoided can be determined based on the distance between them and the updated lane line position. In order to improve the reliability of vehicle deviation, different avoidance judgment conditions can be set for curbs and target vehicles respectively.

[0072] In some embodiments, the detected object includes a curb, and based on the updated lane line position and the updated object position, determining the object to be avoided from each detected object includes the following steps:

[0073] Step 11: for each curb, determine the longitudinal distance between the curb and the vehicle according to the updated object position of the curb, and determine the lateral distance between the curb and the lane line according to the updated object position of the curb and the updated lane line position;

[0074] Step 12: If the longitudinal distance is less than the curb longitudinal distance threshold, and the lateral distance is less than the curb lateral distance threshold, and the duration of the lateral distance being less than the curb lateral distance threshold reaches a preset duration, the curb is determined as an object to be avoided.

[0075] Among them, in step 11, the longitudinal distance between the curb and the vehicle can be obtained based on the longitudinal position of the object position after the curb is updated, and the lateral distance between the curb and the lane line (the lane line closest to the curb among the lane lines corresponding to the reference driving path) can be determined based on the lateral position in the updated object position and the updated lane line position.

[0076] Furthermore, in step 12, it can be determined whether the longitudinal distance is less than a preset curb longitudinal distance threshold, such as whether it is less than 17m, and whether the lateral distance is less than a preset curb lateral distance threshold, such as whether it is less than 0.15m, and whether the duration for which the lateral distance is less than the curb lateral distance threshold is greater than a preset duration, such as whether it is greater than 1s. If the above conditions are met, it can be determined that the vehicle needs to avoid the curb and the curb is determined to be the object to be avoided.

[0077] For example, for the right side curb, if the longitudinal distance between the starting point of the right side curb and the vehicle is less than 17m, and the lateral distance between the right side curb and the right lane line of the target lane is less than 0.15m, and lasts for more than 1s, then the right side curb can be determined as an object to be avoided.

[0078] In the embodiment of the present application, it is considered that there may be a situation where the lane line on one side corresponding to the reference driving path does not exist. If the lane line on the side close to the curb does not exist among the lane lines corresponding to the reference driving path, the lateral distance between the curb and the vehicle can be determined based on the updated object position of the curb. If the longitudinal distance is less than the curb longitudinal distance threshold, and the lateral distance is less than a preset threshold (such as 2m), and the duration of the lateral distance being less than the preset threshold reaches a preset duration, the curb is determined as the object to be avoided.

[0079] In addition, for a roadside object that has been determined to be an object to be avoided, if it is detected that the lateral distance between it and the lane line is greater than a set value (such as 0.5m) and the duration is greater than a set time (such as 200ms), or if it is detected that the longitudinal distance between it and the vehicle is greater than a set value, the object to be avoided can be eliminated.

[0080] Through the above steps 11 and 12, it is possible to determine whether the curb needs to be avoided based on the longitudinal distance between the curb and the vehicle and the lateral distance between the curb and the nearest lane line in the target lane. This can avoid avoiding the curb that is too far away from the vehicle in the longitudinal direction. At the same time, it can avoid avoiding the curb that is too far away from the target lane in the lateral direction, thereby ensuring the reliability of vehicle deviation.

[0081] In some other embodiments, the detection object includes a target vehicle, and based on the updated lane line position and the updated object position, determining the object to be avoided among the detection objects includes the following steps:

[0082] Step 21, obtaining the status information of each target vehicle, removing the target vehicles with the attributes of being traveling in the opposite direction or stationary in the status information, and removing the target vehicles located in the lane corresponding to the reference driving path;

[0083] Step 22: for each target vehicle, based on the vehicle type of the target vehicle, the updated object position of the target vehicle, and the updated lane line position, determine whether the target vehicle meets the preset avoidance conditions. If so, determine the target vehicle as the object to be avoided.

[0084] In step 21, the state information of each target vehicle may be obtained, and the state information may include properties of the target vehicle, such as speed, whether it is stationary, whether it is traveling in the opposite direction, whether it is located in a lane corresponding to the reference driving path, etc. Exemplarily, a state matrix may be used to describe the state information of all target vehicles, and the state information of each target vehicle may be obtained through the state matrix.

[0085] In step 21, considering that there is a certain delay from the sensor collecting information to receiving and processing the information, the lateral and longitudinal distance compensation can be performed on all target vehicles first, which can further improve the accuracy of the avoidance judgment. For example, a preset delay time can be obtained, and the lateral distance compensation value and the longitudinal distance compensation value can be determined based on the preset delay time and the speed information of the vehicle, and then the object position of each target vehicle is updated according to the lateral distance compensation value and the longitudinal distance compensation value.

[0086] Furthermore, the target vehicles detected by the radar and invalid target vehicles can be eliminated to ensure the reliability of the target vehicles, and the target vehicles with the attributes of being traveling in the opposite direction or stationary can be eliminated, and the target vehicles located in the lane corresponding to the reference driving path can be eliminated. For example, if it is a lane change scenario, the target vehicles in the target lane will be eliminated, and if it is a center driving scenario, the target vehicles in the lane where the vehicle is currently located will be eliminated.

[0087] Furthermore, in step 22, the target vehicle can be divided into different types, and combined with the vehicle type of the target vehicle, as well as the updated position information and lane line position, it is determined whether the target vehicle meets the preset avoidance conditions, that is, whether the vehicle needs to avoid the target vehicle.

[0088] Through the above steps 21 and 22, oncoming or stationary target vehicles can be eliminated first, and target vehicles in the target lane can be eliminated. Targets that do not need to be avoided can be filtered out first, thereby improving the overall judgment efficiency. Then, based on information such as vehicle type and position, it is determined whether it is necessary to avoid them. The vehicle type can be taken into consideration to ensure the rationality of vehicle avoidance and avoid invalid vehicle avoidance.

[0089] With respect to the above step 22, in one example, judging whether the target vehicle meets the preset avoidance condition based on the vehicle type of the target vehicle, the updated object position of the target vehicle, and the updated lane line position includes:

[0090] In response to determining that the vehicle type of the target vehicle is the first type, based on the updated object position and the updated lane line position, determining whether the target vehicle is located on the lane line, and if so, determining whether the target vehicle satisfies corresponding lateral and longitudinal distance conditions according to the state information of the target vehicle and the updated object position, and if so, determining that the target vehicle satisfies a preset avoidance condition;

[0091] Alternatively, in response to determining that the vehicle type of the target vehicle is the second type, it is determined whether the target vehicle meets the corresponding lateral and longitudinal distance conditions based on the state information of the target vehicle and the updated object position. If so, it is determined that the target vehicle meets the preset avoidance conditions.

[0092] The first type may be a family passenger car, and the second type may be a truck or trailer. Specifically, if the vehicle type of the target vehicle is the first type, it means that the target vehicle is small in size. At this time, it can be determined whether the target vehicle is located on the lane line close to the vehicle side corresponding to the reference driving path, that is, whether the target vehicle presses the lane line close to the vehicle side in the target lane. If so, the relative longitudinal speed between the target vehicle and the vehicle can be further determined based on the state information of the target vehicle, and the minimum longitudinal distance can be calculated according to the relative longitudinal speed and the preset collision time.

[0093] Furthermore, the lateral distance between the target vehicle and the reference driving path can be determined by the lateral position in the object position of the target vehicle, and the longitudinal distance between the target vehicle and the vehicle can be determined by the longitudinal position in the object position of the target vehicle. If the lateral distance is less than the preset first distance, and the longitudinal distance is less than the minimum longitudinal distance, it can be determined that the target vehicle meets the corresponding lateral and longitudinal distance conditions, and then it is determined that the target vehicle meets the preset avoidance conditions and is the object to be avoided.

[0094] If the target vehicle is of the second type, it means that the target vehicle is larger in size. In this case, there is no need to determine whether the target vehicle crosses the line. The relative longitudinal speed between the target vehicle and the vehicle can be directly determined based on the target vehicle's status information, and the minimum longitudinal distance can be calculated based on the relative longitudinal speed and the preset collision time.

[0095] Furthermore, the lateral distance between the target vehicle and the reference driving path can be determined by the lateral position in the object position of the target vehicle, and the longitudinal distance between the target vehicle and the vehicle can be determined by the longitudinal position in the object position of the target vehicle. If the lateral distance is less than the preset second distance, and the longitudinal distance is less than the minimum longitudinal distance, it can be determined that the target vehicle meets the corresponding lateral and longitudinal distance conditions, and then it is determined that the target vehicle meets the preset avoidance conditions and is the object to be avoided. The preset second distance is less than the preset first distance.

[0096] Through the above example, for a small car, we can first determine whether it crosses the line, and then determine whether it meets the corresponding horizontal and vertical distance conditions. For a large vehicle, we can directly determine whether it meets the corresponding horizontal and vertical distance conditions. This can achieve reasonable avoidance of small cars that cross the line and reasonable avoidance of large vehicles, ensuring the reliability of vehicle offset.

[0097] In the embodiment of the present application, after determining whether each detected object needs to be avoided, that is, after determining the object to be avoided, the offset of the vehicle can be determined to avoid the object to be avoided.

[0098] Considering that before controlling the vehicle to perform the offset, in order to ensure the safety of the offset control, it is also possible to determine whether the vehicle meets certain conditions. In one example, before determining the offset of the vehicle based on the object to be avoided, it also includes:

[0099] The vehicle speed and the curvature radius of the lane in which the vehicle is currently located are obtained; in response to determining that the vehicle speed is greater than a preset speed threshold and the curvature radius is greater than a preset radius threshold, a step of determining an offset of the vehicle based on an object to be avoided is performed.

[0100] The preset speed threshold may be a preset speed critical value representing high-speed driving of the vehicle; and the preset radius threshold may be a preset curvature radius critical value representing that the current lane is safe to deviate from.

[0101] Specifically, if the vehicle speed is greater than a preset speed threshold, it means that the vehicle is traveling at high speed. If the curvature radius of the current lane is greater than the preset radius threshold, it means that the curvature of the current lane is relatively small. If the vehicle is traveling at high speed and the curvature of the lane currently in which the vehicle is located is relatively small, the vehicle can be offset controlled, that is, the subsequent steps of determining the offset of the vehicle based on the object to be avoided are executed.

[0102] Through the above examples, considering that the states of traffic participants change greatly when driving at low speeds, it is possible to avoid controlling the vehicle deviation when the vehicle is driving at low speeds to ensure the safety of vehicle driving. In addition, considering that there are safety risks in controlling the vehicle deviation when the road is very curved, it is possible to avoid controlling the vehicle deviation when the road is curved to further ensure the safety of vehicle driving.

[0103] In the embodiment of the present application, considering that there may be situations where a vehicle that crosses the line briefly crosses the line and immediately returns to its original position, in order to avoid controlling the vehicle to deviate in such situations, the avoidance judgment results of multiple consecutive moments before can also be combined. In one example, before determining the offset of the vehicle based on the object to be avoided, it also includes:

[0104] For each object to be avoided, determine whether the corresponding detected object has been determined as an object to be avoided in multiple consecutive historical moments before the current moment; if not, the object to be avoided is eliminated.

[0105] Specifically, for each object to be avoided, if the object to be avoided has been judged to need to be avoided in multiple consecutive historical moments before the current moment, that is, the detected object has been determined as an object to be avoided in multiple consecutive historical moments, then the object to be avoided can be retained; otherwise, the object to be avoided can be eliminated to avoid subsequent avoidance by controlling the vehicle offset.

[0106] Through the above examples, it is possible to avoid the object to be avoided when there is a short-term collision risk with the object to be avoided. For example, a car that crosses the line immediately returns to the center of the lane 100ms after crossing the line, a truck slows down and increases the longitudinal distance from the vehicle, and the lateral distance between the curb and the vehicle increases, thereby ensuring the reliability of vehicle avoidance.

[0107] In the embodiment of the present application, considering that the number of objects to be avoided that are finally determined at the same time may be multiple, and the vehicle needs to perform offset avoidance based on one of the objects to be avoided. Therefore, in some embodiments, the method provided in the embodiment of the present application further includes: determining the safety risk level of the object to be avoided;

[0108] Determining the offset of the vehicle based on the object to be avoided includes:

[0109] In response to determining that there are multiple objects to be avoided, a vehicle offset direction is determined based on an updated object position of an object to be avoided with a highest safety risk level, and an offset amount of the vehicle is determined based on the offset direction and a lane width of a target lane.

[0110] Specifically, after determining the object to be avoided from the detected objects, the safety risk level of the object to be avoided can also be determined based on the object position of the object to be avoided. The safety risk level can reflect the collision risk between the vehicle and the object to be avoided, and the higher the safety risk level, the greater the collision risk.

[0111] For example, if the object to be avoided is located in front of the vehicle, the safety risk level of the object to be avoided can be increased, and if the object to be avoided is located behind the vehicle, the safety risk level of the object to be avoided can be reduced. Furthermore, if the horizontal distance between the object to be avoided and the lane line corresponding to the reference driving path is closer, the safety risk level is greater, and if the longitudinal distance between the object to be avoided and the vehicle is closer, the safety risk level is greater. Furthermore, if the object to be avoided is located in front of the vehicle and the speed of the object to be avoided is lower than the speed of the vehicle, the safety risk level of the object to be avoided can be further increased.

[0112] Furthermore, when there are multiple objects to be avoided, the object to be avoided with the highest safety risk level can be selected, and the offset direction of the vehicle can be determined based on the object position of the object to be avoided. For example, if the object to be avoided is located on the left side of the vehicle, the offset direction is right; and if the object to be avoided is located on the right side of the vehicle, the offset direction is left.

[0113] After obtaining the offset direction, the corresponding vehicle offset distance can be queried in combination with the lane width of the target lane, and the vehicle offset amount can be obtained in combination with the offset direction.

[0114] Through the above implementation, when there are multiple objects to be avoided, the offset amount can be determined based on the safety risk level of each object to be avoided, which can ensure that objects to be avoided with high risks are offset first, further ensuring the safety of vehicle driving.

[0115] In the embodiment of the present application, considering that there may be a situation where there are objects that need to be avoided on both sides, for such a situation, there is no need to control the vehicle to offset in order to ensure the safety of the vehicle.

[0116] In an optional implementation, before determining the offset direction of the vehicle based on the updated position of the object to be avoided having the highest safety risk level, the method further includes:

[0117] Based on the updated position of each object to be avoided, determine whether there are objects to be avoided located on both sides of the target lane, and whether the longitudinal distance difference between the objects to be avoided located on both sides of the target lane is less than a preset threshold; if so, generate a lane change driving path based on the target lane, and control the vehicle to drive along the lane change driving path.

[0118] Specifically, it can be determined based on the position of each object to be avoided whether there are objects to be avoided located on both sides of the target lane, and whether the longitudinal distance difference between the objects to be avoided on both sides is less than a preset threshold.

[0119] If the above conditions are met, it means that there are objects that need to be avoided on both sides of the target lane, and avoiding one of the objects may cause the vehicle to collide with the other object. Therefore, a lane change driving path can be generated at this time to control the vehicle to drive along the lane change driving path, so as to achieve only controlling the vehicle to change lanes without completing the offset during the lane change process.

[0120] Through the above implementation, when there are objects that need to be avoided on both sides of the target lane, the vehicle can be controlled to only complete the lane change, avoiding the risk of collision caused by lane change deviation, thereby further improving the vehicle driving safety.

[0121] Furthermore, a lane change offset driving path may be generated according to the offset and the target lane, and the vehicle may be controlled to travel along the lane change offset driving path, so as to control the vehicle to complete the offset during the lane change process. For example, a lane change driving path may be generated according to the target lane, and then a portion of the lane change driving path located in the target lane may be updated according to the offset to obtain the lane change offset driving path.

[0122] For example, Figure 3 is a schematic diagram of an offset for a large vehicle provided in an embodiment of the present application, such as Figure 3 As shown, before receiving a lane change request, the vehicle can travel according to the original reference driving path. After receiving the lane change request, the reference driving path can be updated, and after determining that the target vehicle (large vehicle) needs to be avoided, a lane change offset driving path can be generated according to the offset and the target lane. Of course, after the offset is completed, the reference driving path can also be updated.

[0123] Figure 4 is a schematic diagram of an offset for a curb provided in an embodiment of the present application, such as Figure 4 As shown, the vehicle can travel according to the original reference driving path before receiving a lane change request, and after receiving the lane change request, the reference driving path can be updated, and after determining that the curb needs to be avoided, a lane change offset driving path can be generated according to the offset and the target lane.

[0124] Figure 5 is a schematic diagram of an offset of a wire pressing trolley provided in an embodiment of the present application, such as Figure 5As shown, the vehicle can travel according to the original reference driving path before receiving a lane change request. After receiving the lane change request, the reference driving path can be updated. After determining that the target vehicle (the car crossing the line) needs to be avoided, a lane change offset driving path can be generated according to the offset and the target lane. After the offset is completed, the reference driving path can also be updated.

[0125] In addition to realizing the offset control in the lane change scenario (active lane change or lever lane change), the embodiment of the present application can also provide the offset control in the center driving scenario. Specifically, in the case of the vehicle's lane change request not being detected, it can be considered that the vehicle is driving in the center, and there is no need to update the reference driving path, nor the object position of the detection object. The object to be avoided can be directly determined in each detection object based on the lane line position and object position corresponding to the reference driving path, and then the offset of the vehicle is determined according to the object to be avoided, and the offset driving path is generated based on the offset, and the vehicle is controlled to drive along the offset driving path. After the offset is completed, the reference driving path can also be updated.

[0126] For example, Figure 6 is a schematic diagram of an offset in a centering driving scenario provided by an embodiment of the present application, such as Figure 6 As shown, the vehicle can travel according to the initial reference driving path. After determining that the target vehicle needs to be avoided, an offset driving path can be generated according to the offset, and after the offset is completed, the reference driving path is updated.

[0127] The vehicle offset control method provided in the embodiment of the present application obtains the reference driving path of the vehicle, obtains the object position of each detection object in multiple lanes nearby, and the lane line position corresponding to the reference driving path, and then responds to the detection of a lane change request, based on the target lane corresponding to the lane change request, updates the reference driving path and the corresponding lane line position, and updates the object position according to the relative lateral distance between the object position and the updated reference driving path, and generates the lane change offset driving path of the vehicle through the updated lane line position and the updated object position, thereby controlling the vehicle to travel along the lane change offset driving path, and can achieve lane change offset. The method can update the reference driving path according to the lane change request, update the position according to the lateral distance of each object position relative to the reference driving path, and generate the lane change offset driving path based on the lateral distance, so as to complete the offset during the lane change process, avoid the object that needs to be offset, and ensure the driving safety of the vehicle, without having to design many scenarios for lane change offset in advance, solving the problems of heavy computing power burden and abnormal exit caused by multiple scenario designs, and can also solve the problem of not taking action on the object that needs to be offset in the adjacent lane of the lane change lane. In response to the lane change request, by performing a translation transformation, the same effect as the active offset of the side lane can be achieved.

[0128] Figure 7 7 is a schematic diagram of the structure of a vehicle offset control device provided in an embodiment of the present application. The device includes an acquisition module 710, a position update module 720 and an offset execution module 730, wherein:

[0129] An acquisition module 710 is used to acquire a reference driving path of a vehicle, and acquire an object position of each detection object in a plurality of lanes near the vehicle, and a lane line position corresponding to the reference driving path;

[0130] a position updating module 720, configured to update the reference driving path and the corresponding lane line position based on the target lane corresponding to the lane change request in response to detecting the lane change request of the vehicle, and update the object position according to the relative lateral distance between the object position and the updated reference driving path;

[0131] The offset execution module 730 is used to generate a lane change offset driving path based on the updated lane line position and the updated object position, and control the vehicle to travel along the lane change offset driving path.

[0132] On the basis of the above-mentioned embodiments, optionally, the offset execution module 730 is specifically used to determine the object to be avoided among the detected objects based on the updated lane line position and the updated object position, and determine the offset of the vehicle based on the object to be avoided; and generate a lane change offset driving path based on the offset and the target lane.

[0133] On the basis of the above-mentioned embodiments, optionally, the offset execution module 730 includes an offset unit, which is used to determine, for each curb, the longitudinal distance between the curb and the vehicle based on the updated object position of the curb, and to determine the lateral distance between the curb and the lane line based on the updated object position of the curb and the updated lane line position; if the longitudinal distance is less than a curb longitudinal distance threshold, and the lateral distance is less than a curb lateral distance threshold, and the duration for which the lateral distance is less than the curb lateral distance threshold reaches a preset duration, the curb is determined as an object to be avoided.

[0134] On the basis of the above embodiments, optionally, the offset unit is further used to obtain the state information of each target vehicle, remove the target vehicles with attributes of opposite-direction driving or stationary in the state information, and remove the target vehicles located in the lane corresponding to the reference driving path;

[0135] For each target vehicle, based on the vehicle type of the target vehicle, the updated object position of the target vehicle and the updated lane line position, it is determined whether the target vehicle meets the preset avoidance conditions. If so, the target vehicle is determined as the object to be avoided.

[0136] On the basis of the above-mentioned embodiments, optionally, the offset unit is further used to, in response to determining that the vehicle type of the target vehicle is the first type, determine whether the target vehicle is located on the lane line based on the updated object position and the updated lane line position; if so, determine whether the target vehicle meets the corresponding horizontal and vertical distance conditions according to the state information of the target vehicle and the updated object position; if so, determine that the target vehicle meets the preset avoidance condition; or

[0137] In response to determining that the vehicle type of the target vehicle is the second type, judging whether the target vehicle satisfies corresponding lateral and longitudinal distance conditions according to the state information of the target vehicle and the updated object position, and if so, determining that the target vehicle satisfies a preset avoidance condition.

[0138] Based on the above embodiments, optionally, the offset unit is also used to determine the safety risk level of the object to be avoided; in response to determining that the number of the objects to be avoided is multiple, based on the updated object position of the object to be avoided with the highest safety risk level, the offset direction of the vehicle is determined, and based on the offset direction and the lane width of the target lane, the offset amount of the vehicle is determined.

[0139] On the basis of the above-mentioned embodiments, optionally, the offset unit is also used to determine whether there are objects to be avoided located on both sides of the target lane respectively based on the updated object positions of each object to be avoided, and the longitudinal distance difference between the objects to be avoided located on both sides of the target lane is less than a preset threshold; if so, a lane change driving path is generated based on the target lane, and the vehicle is controlled to travel along the lane change driving path.

[0140] On the basis of the above-mentioned implementation modes, optionally, the offset unit is also used to determine, for each of the objects to be avoided, whether the corresponding detected object has been determined as the object to be avoided in multiple consecutive historical moments before the current moment; if not, the object to be avoided is eliminated.

[0141] Based on the above embodiments, optionally, the offset unit is also used to obtain the vehicle speed and the curvature radius of the lane in which the vehicle is currently located; in response to determining that the vehicle speed is greater than a preset speed threshold and the curvature radius is greater than a preset radius threshold, executing the step of determining the offset of the vehicle based on the object to be avoided.

[0142] The vehicle deviation control device provided in the embodiment of the present application can execute the steps of the vehicle deviation control method provided in the method embodiment of the present application, and the execution steps and beneficial effects are no longer repeated here.

[0143] Figure 8Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 400 includes one or more processors 401 and a memory 402 .

[0144] The processor 401 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0145] The memory 402 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement the vehicle offset control method of any embodiment of the present application described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0146] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including early warning information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0147] Of course, to simplify, Figure 8 Only some of the components related to the present application in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 400 may also include any other appropriate components.

[0148] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the vehicle deviation control method provided by any embodiment of the present application.

[0149] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0150] In addition, the embodiments of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the vehicle deviation control method provided by any embodiment of the present application.

[0151] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0152] It should be noted that the terms used in this application are only for describing specific embodiments, rather than limiting the scope of this application. As shown in the specification and claims of this application, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0153] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0154] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and its core ideas of this application. The above is only the preferred implementation method of this application. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, ordinary technicians in this technical field can make several improvements, modifications or changes without departing from the principles of this application, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the concept and technical solution of the invention to other occasions without improvement, should be regarded as the scope of protection of this application.

Claims

1. A vehicle deviation control method, characterized in that: include: Acquire a reference driving path of a vehicle, and acquire an object position of each detection object in a plurality of lanes near the vehicle, and a lane line position corresponding to the reference driving path; In response to detecting a lane change request of the vehicle, updating the reference driving path and the corresponding lane line position based on a target lane corresponding to the lane change request, and updating the object position according to a relative lateral distance between the object position and the updated reference driving path; A lane-changing deviation driving path is generated based on the updated lane line position and the updated object position, and the vehicle is controlled to travel along the lane-changing deviation driving path.

2. The method according to claim 1, characterized in that The generating of the lane change deviation driving path based on the updated lane line position and the updated object position includes: Based on the updated lane line position and the updated object position, determining an object to be avoided among the detected objects, and determining an offset of the vehicle based on the object to be avoided; A lane change offset driving path is generated based on the offset and the target lane.

3. The method according to claim 2, characterized in that The detection object includes a curb, and based on the updated lane line position and the updated object position, determining the object to be avoided from each detection object includes: For each curb, determine a longitudinal distance between the curb and the vehicle based on the updated object position of the curb, and determine a lateral distance between the curb and the lane line based on the updated object position of the curb and the updated lane line position; If the longitudinal distance is less than the curb longitudinal distance threshold, and the lateral distance is less than the curb lateral distance threshold, and the duration for which the lateral distance is less than the curb lateral distance threshold reaches a preset duration, the curb is determined as an object to be avoided.

4. The method according to claim 2, characterized in that: The detection object includes a target vehicle, and based on the updated lane line position and the updated object position, determining an object to be avoided among the detection objects includes: Acquire the status information of each target vehicle, remove the target vehicles with attributes of being traveling in the opposite direction or stationary in the status information, and remove the target vehicles located in the lane corresponding to the reference driving path; For each target vehicle, based on the vehicle type of the target vehicle, the updated object position of the target vehicle and the updated lane line position, it is determined whether the target vehicle meets the preset avoidance conditions. If so, the target vehicle is determined as the object to be avoided.

5. The method according to claim 4, characterized in that Based on the vehicle type of the target vehicle, the updated object position of the target vehicle, and the updated lane line position, determining whether the target vehicle meets a preset avoidance condition includes: In response to determining that the vehicle type of the target vehicle is the first type, based on the updated object position and the updated lane line position, determining whether the target vehicle is located on the lane line, and if so, determining whether the target vehicle satisfies the corresponding lateral and longitudinal distance conditions according to the state information of the target vehicle and the updated object position, and if so, determining that the target vehicle satisfies the preset avoidance condition; or, In response to determining that the vehicle type of the target vehicle is the second type, judging whether the target vehicle satisfies corresponding lateral and longitudinal distance conditions according to the state information of the target vehicle and the updated object position, and if so, determining that the target vehicle satisfies a preset avoidance condition.

6. The method according to claim 2, characterized in that The method further comprises: Determining the safety risk level of the object to be avoided; Determining the offset of the vehicle based on the object to be avoided includes: In response to determining that there are multiple objects to be avoided, an offset direction of the vehicle is determined based on an updated position of an object to be avoided with a highest safety risk level, and an offset amount of the vehicle is determined based on the offset direction and a lane width of the target lane.

7. The method according to claim 6, characterized in that Before determining the offset direction of the vehicle based on the updated position of the object to be avoided with the highest safety risk level, the method further includes: Based on the updated position of each of the objects to be avoided, it is determined whether there are objects to be avoided located on both sides of the target lane, and the longitudinal distance difference between the objects to be avoided located on both sides of the target lane is less than a preset threshold; If so, a lane-changing driving path is generated based on the target lane, and the vehicle is controlled to travel along the lane-changing driving path.

8. The method according to claim 2, characterized in that: Before determining the offset of the vehicle based on the object to be avoided, the method further includes: For each of the objects to be avoided, determining whether the corresponding detected object has been determined as an object to be avoided in a plurality of consecutive historical moments before the current moment; If not, the object to be avoided is eliminated.

9. The method according to claim 2, characterized in that: Before determining the offset of the vehicle based on the object to be avoided, the method further includes: Obtaining the speed of the vehicle and the curvature radius of the lane in which the vehicle is currently located; In response to determining that the vehicle speed is greater than a preset speed threshold and the curvature radius is greater than a preset radius threshold, a step of determining an offset of the vehicle based on the object to be avoided is performed.

10. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The processor is used to execute the steps of the vehicle deviation control method as claimed in any one of claims 1 to 9 by calling the program or instruction stored in the memory.

Images