Vehicle path decision method and device, computer device and storage medium

Abstract

The application relates to a vehicle path decision method and device, computer equipment and a storage medium. The method comprises the following steps: collecting current road condition information in the driving process of a target vehicle according to a current driving path; identifying a driving influence factor contained in the current road condition information, so as to calculate a path safety parameter corresponding to the current driving path according to the driving influence factor; if the path safety parameter corresponding to the current driving path does not satisfy a preset safety condition, a candidate driving path is confirmed; a path safety parameter corresponding to each candidate driving path is calculated according to the current road condition information, and a lane-changing threat parameter corresponding to each candidate driving path is calculated according to a current driving parameter of the target vehicle; a target driving path is confirmed according to the path safety parameter and the lane-changing threat parameter corresponding to each candidate driving path, and the driving of the target vehicle is controlled according to the target driving path. The method can reduce the risk of automatic driving and improve the user experience.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle path decision-making method, apparatus, computer device, and storage medium. Background Technology

[0002] Autonomous vehicles, also known as driverless cars, computer-driven cars, or wheeled mobile robots, are a new generation of cars that rely on the collaborative efforts of artificial intelligence, computer vision, radar, monitoring devices, and global positioning systems to ultimately achieve autonomous driving. Advanced driver assistance systems are an important foundation for realizing autonomous driving.

[0003] During vehicle operation, some emergency scenarios may occur. In particular, when the autonomous driving system encounters an emergency, if the current speed is high, the autonomous vehicle may brake suddenly or turn sharply to change its route, which may easily cause danger and discomfort to the user. Summary of the Invention

[0004] Based on this, a vehicle path decision-making method, device, computer equipment, and storage medium are provided, which reduce the dangers of autonomous driving and improve the user experience by switching paths through path decision-making.

[0005] On the one hand, a vehicle routing decision method is provided, the method comprising:

[0006] While the target vehicle is traveling along its current route, collect current road condition information;

[0007] Identify the driving impact factors contained in the current road condition information, and calculate the path safety parameters corresponding to the current driving path based on the driving impact factors;

[0008] If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then the candidate driving path is confirmed.

[0009] Calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle;

[0010] Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, the target driving path is determined, and the driving of the target vehicle is controlled according to the target driving path.

[0011] In one embodiment, identifying driving influencing factors included in the current road condition information includes:

[0012] Based on the current road condition information, object recognition is performed to obtain the category information of each object;

[0013] Objects whose category information meets preset conditions are used as driving influence factors.

[0014] In one embodiment, identifying driving influencing factors included in the current road condition information includes:

[0015] Event identification is performed based on the current road condition information to obtain the event identification result;

[0016] The event identification results are used as driving impact factors.

[0017] In one embodiment, the current traffic information is composed of multiple current traffic sub-information, and each of the current traffic sub-information is collected by a different acquisition device;

[0018] The identification of driving influencing factors contained in the current road condition information includes:

[0019] Obtain the current road condition sub-information collected by each of the aforementioned acquisition devices;

[0020] Each of the current road condition sub-informations is identified to obtain the driving impact candidate factors contained in each of the current road condition sub-informations;

[0021] Calculate the confidence level of each driving impact candidate factor based on the driving impact candidate factors contained in each of the current road condition sub-information;

[0022] Candidate factors for driving impact that meet the preset confidence level are used as driving impact factors.

[0023] In one embodiment, calculating the path safety parameters corresponding to the current driving path based on the driving impact factor includes:

[0024] Confirm the distance of the target vehicle relative to the driving influence factor;

[0025] And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained;

[0026] Calculate the path safety parameters corresponding to the current driving path based on the impact level and the distance.

[0027] In one embodiment, if the path safety parameters corresponding to the current driving path do not meet preset safety conditions, then a candidate driving path is confirmed, including:

[0028] Obtain the historical driving path of the target vehicle within a preset time period;

[0029] The historical driving routes and the current driving routes are filtered to obtain candidate driving routes.

[0030] In one embodiment, the lane change threat parameter corresponding to each candidate driving path is calculated based on the current driving parameters of the target vehicle, including:

[0031] Identify the current driving parameters of other vehicles in the candidate driving path;

[0032] Lane change simulation is performed based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle;

[0033] Based on the results of the lane change simulation, the time parameters required for the target vehicle to change lanes to the candidate driving path and the speed change parameters of the target vehicle are confirmed.

[0034] The lane change threat parameter corresponding to each candidate driving path is calculated based on the time parameter and the speed change parameter.

[0035] On the other hand, a vehicle routing decision device is provided, the device comprising:

[0036] The road condition data collection module is used to collect current road condition information as the target vehicle travels along its current route.

[0037] The route safety parameter calculation module is used to identify the driving influencing factors contained in the current road condition information, and to calculate the route safety parameters corresponding to the current driving route based on the driving influencing factors.

[0038] The candidate driving route confirmation module is used to confirm the candidate driving route if the path safety parameters corresponding to the current driving route do not meet the preset safety conditions.

[0039] The lane change threat parameter calculation module is used to calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and to calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle.

[0040] The target driving path confirmation module is used to confirm the target driving path based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, and control the driving of the target vehicle according to the target driving path.

[0041] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0042] While the target vehicle is traveling along its current route, collect current road condition information;

[0043] Identify the driving impact factors contained in the current road condition information, and calculate the path safety parameters corresponding to the current driving path based on the driving impact factors;

[0044] If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then the candidate driving path is confirmed.

[0045] Calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle;

[0046] Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, the target driving path is determined, and the driving of the target vehicle is controlled according to the target driving path.

[0047] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0048] While the target vehicle is traveling along its current route, collect current road condition information;

[0049] Identify the driving impact factors contained in the current road condition information, and calculate the path safety parameters corresponding to the current driving path based on the driving impact factors;

[0050] If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then the candidate driving path is confirmed.

[0051] Calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle;

[0052] Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, the target driving path is determined, and the driving of the target vehicle is controlled according to the target driving path.

[0053] The aforementioned vehicle routing decision-making method, device, computer equipment, and storage medium collect road condition information of the target vehicle's current driving path to identify influencing factors affecting the target vehicle's driving and path safety parameters of the target vehicle while driving on the current path. This allows for the determination of whether potential hazards exist on the current driving path and whether a lane change is necessary. If safety conditions are not met, candidate driving paths are selected, and lane change threat parameters generated by changing lanes to each candidate driving path are calculated. Based on the path safety parameters and lane change threat parameters, a target driving path that allows for a safe lane change is determined, thereby controlling the vehicle to change lanes to the target driving path. This vehicle routing decision-making method reduces the risks of autonomous driving and improves the user experience. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating a vehicle routing decision method in one embodiment;

[0055] Figure 2 This is a structural block diagram of a vehicle routing decision device in one embodiment;

[0056] Figure 3 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily need to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0059] The structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the implementation conditions of this application. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size should still fall within the scope of the technical content disclosed in this application, provided that they do not affect the effects and purposes that this application can produce.

[0060] The orientations or positional relationships indicated by terms such as "upper," "lower," "left," "right," "middle," "longitudinal," "lateral," "horizontal," "inner," "outer," "radial," and "circumferential" used in this specification are based on the orientations or positional relationships shown in the accompanying drawings and are used only for the purpose of simplifying the description. They do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0061] In one embodiment, such as Figure 1 As shown, a vehicle routing decision method is provided. Taking the application of this method to an autonomous vehicle as an example, the method includes the following steps:

[0062] Step 101: Collect current road condition information while the target vehicle is traveling along the current route.

[0063] The current road condition information includes road condition information on the target vehicle's current driving path, as well as road condition information on surrounding paths. Surrounding paths can be paths adjacent to the current driving path and / or paths that are a certain distance away from the current driving path.

[0064] It should be noted that there can be one or more methods for collecting current path information, including camera collection, radar collection, infrared collection, etc., which are not limited here.

[0065] Step 102: Identify the driving impact factors contained in the current road condition information, and calculate the path safety parameters corresponding to the current driving path based on the driving impact factors.

[0066] Among them, driving impact factors refer to one or more factors in road condition information that affect the driving of the target vehicle, including objects on the road, events occurring on the road, etc.; route safety parameters can be obtained from driving impact factors and are used to determine whether there are potential dangers on the road.

[0067] Step 103: If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then confirm the candidate driving path.

[0068] Among them, the security conditions can be preset thresholds and / or some preset rules.

[0069] Specifically, if the path safety parameters of the current driving path do not meet the safety conditions, a candidate driving path needs to be selected so that the autonomous vehicle can switch to a safe driving path.

[0070] For example, safety conditions may include, but are not limited to, the absence of perceived driving influencing factors from intruding into the current driving path, the maintenance of a preset safe distance between other vehicles on the road and the target vehicle, and the stable driving trajectories of other vehicles on the road.

[0071] Step 104: Calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle.

[0072] Among them, the current driving parameters refer to the vehicle's operating data and driving environment when driving on the current road; the lane change threat parameters refer to the threats that may arise when the target vehicle switches from the current driving path to a candidate new path. Different lane change threat parameters may pose different degrees of threat when changing lanes.

[0073] Specifically, the path safety parameters corresponding to each candidate driving path are calculated based on the current road condition information, and the lane change threat parameters corresponding to each candidate driving path are calculated based on the current driving parameters of the target vehicle. The choice of which candidate driving path is optional is determined by the safety level of the candidate driving path and the potential threats when switching to the candidate driving path.

[0074] For example, in one possible implementation, preset threat conditions and corresponding threat parameters can be established based on traffic regulations, driving experience, etc. Threat conditions may include, but are not limited to: 1. If the candidate driving path has no drivable lanes or a sufficiently long dashed line to allow the target vehicle to change lanes, then the target vehicle is prohibited from changing lanes onto that candidate driving path; 2. Active lane changing away from the ramp entrance is prohibited when a certain distance is reached; 3. If changing lanes onto the candidate driving path would cause the target vehicle and / or other vehicles to brake suddenly, then changing lanes in that direction is prohibited; 4. If, after changing lanes to the candidate driving path, the difference between the target vehicle's speed and the current speed on the current driving path exceeds a certain threshold, then the target vehicle is prohibited from actively changing lanes in that direction, etc. If, based on the target vehicle's current operating data and driving environment parameters, the lane-changing threat parameters of one or more candidate driving paths match or exceed the preset threat conditions, then it is not recommended to change lanes onto that candidate driving path.

[0075] Step 105: Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, confirm the target driving path, and control the driving of the target vehicle according to the target driving path.

[0076] The target driving path refers to the path that, after screening, allows the target vehicle to safely change lanes and proceed.

[0077] Specifically, if there are one or more candidate driving paths, the candidate driving path that the target vehicle can safely change lanes and drive on is selected as the target driving path based on the corresponding path safety parameters and lane change threat parameters, and then the target vehicle is controlled to switch to the target driving path for driving.

[0078] It should be noted that, unless otherwise specified, this application does not limit the execution order of calculating the path safety parameters and the lane change threat parameters of the candidate driving path. For the candidate driving path, the path safety parameters can be calculated first and then the lane change threat parameters can be calculated; the lane change threat parameters can be calculated first and then the path safety parameters can be calculated; or the path safety parameters and lane change threat parameters of the candidate driving path can be calculated simultaneously.

[0079] Optionally, candidate driving paths can be filtered by calculating the path safety parameters or lane change threat parameters of the candidate driving paths to obtain variable driving paths, and then the lane change threat parameters or path safety parameters of the variable driving paths can be calculated accordingly to obtain the target driving path.

[0080] Optionally, if there are multiple target driving paths available for the target vehicle to select and switch between, a comprehensive analysis can be performed based on path safety parameters and lane change threat parameters to obtain path selection parameters. The target driving paths can then be sorted according to preset sorting rules based on the path selection parameters, and one of the sorted target driving paths can be selected.

[0081] For example, the path safety parameters and lane change threat parameters can be summed, or summed separately according to a preset ratio coefficient, to obtain the path selection parameters. The target driving paths are then sorted according to the sorting rules based on the path selection parameters, and the target driving path with the optimal path selection parameters after sorting is selected.

[0082] It should also be noted that when there are candidate driving paths with the same path selection parameters but conflicting lane change directions, if the path safety parameters of the current driving path do not meet the preset safety conditions, then a lane change will be performed according to the preset priority lane change direction or any other direction; if the path safety parameters of the current driving path meet the preset safety conditions, then a lane change will not be performed.

[0083] In the aforementioned vehicle routing decision-making method, road condition information of the target vehicle's current driving path is collected to identify influencing factors affecting the target vehicle's driving and path safety parameters while the target vehicle is traveling on the current path. This allows for the determination of potential hazards on the current driving path and whether a lane change is necessary. If safety conditions are not met, candidate driving paths are selected, and lane change threat parameters generated by changing lanes to each candidate driving path are calculated. Based on the path safety parameters and lane change threat parameters, a target driving path that allows for a safe lane change is determined, thereby controlling the vehicle to change lanes to the target driving path. This vehicle routing decision-making method reduces the risks of autonomous driving and improves the user experience.

[0084] In one embodiment, identifying driving influencing factors included in the current road condition information includes:

[0085] Based on the current road condition information, object recognition is performed to obtain the category information of each object;

[0086] Objects whose category information meets preset conditions are used as driving influence factors.

[0087] Among them, object recognition can be achieved through a preset object recognition model. The object recognition model can be trained based on pre-collected labeled data to identify the category of objects collected on the road.

[0088] Specifically, objects on the road are identified based on the trained object recognition model, including identifying the type of object or the type of vehicle.

[0089] The obtained category information is matched with preset threat conditions. If a threat condition that matches the category information exists, the object is identified as a driving impact factor.

[0090] For example, the preset threat conditions can be vehicle type, obstacle type, and warning signs. For instance, a water truck can spray water that affects radar point clouds and camera vision acquisition, which is a serious interference for autonomous vehicles. Or some cargo trailers can be used because the trailer is too long and wide, and the trailer cab and trailer are not rigid bodies, making it difficult for machine vision to accurately identify the position of the large vehicle and to maintain a safe distance from the large vehicle.

[0091] To further explain, in one embodiment, if it is detected that a vehicle on an adjacent path has a vehicle length, vehicle width, and vehicle height that exceed a preset safety threshold for any one or more of these parameters, then that vehicle may pose a threat to the target vehicle, and the vehicle will be used as a driving influence factor.

[0092] Optionally, in one implementation, if a warning sign such as a traffic cone or a triangle is detected in front of the target vehicle, it indicates that the road ahead may be impassable due to construction or an accident. Moreover, construction or accident areas are usually complex, and it is difficult for autonomous vehicles to make appropriate and timely judgments on such situations.

[0093] Therefore, by way of example, when an obstacle such as a cone or a triangle is detected, if the distance between the cone or triangle and the edge of the road where the target vehicle is located exceeds a certain threshold, and it is safe for the target vehicle to change lanes to other lanes, then it can change lanes to a safe lane.

[0094] Optionally, if the target vehicle collects three or more cones, the correlation coefficient of the cone positions is calculated. If these cone positions are strongly linearly correlated, it can be assumed that these cones are arranged in a long sequence, and the collected cones are part of the long cone arrangement. Linear regression is then performed on the cone positions to predict the possible locations of cones that have not yet been observed or collected. If one or more cones in the cone arrangement would encroach on the target vehicle's current lane, the target vehicle will choose to change lanes.

[0095] It should be noted that the object can be continuously identified in real time or periodically. If the category information obtained by the object recognition model changes and the frequency of change is greater than the preset recognition error threshold, it indicates that the object may pose a potential threat to the target vehicle, and the object will be used as a driving impact factor.

[0096] It should also be noted that the object categories perceived in real time or periodically can be compared frame by frame. If the number of mismatches (i.e., the frequency of change) in the category information of the same object recognized for multiple consecutive frames is greater than the preset recognition error threshold, then the object will be used as a driving influence factor.

[0097] If the recognition results of the same object by multiple acquisition devices on the vehicle do not match, and the number of mismatches exceeds the preset recognition error threshold, such as when the radar point cloud recognizes an object but the camera visual model cannot classify or segment the object, then the object may be an irregular vehicle or an unknown obstacle, and should also be considered as a driving influence factor.

[0098] In one embodiment, identifying driving influencing factors included in the current road condition information includes:

[0099] Event identification is performed based on the current road condition information to obtain the event identification result;

[0100] The event identification results are used as driving impact factors.

[0101] For ease of understanding and explanation, the above embodiments can be used as a reference. When collecting and identifying road condition information, in addition to identifying the category information of objects on the road, it is also necessary to perform event identification to obtain event identification results in order to perceive events that are happening on the road, especially events that may affect the normal driving of the target vehicle, and use the identified events as driving influencing factors, such as other vehicles merging into the lane, other vehicles being too close to the target vehicle, or other vehicles having unstable driving trajectories.

[0102] In one embodiment, the current traffic information is composed of multiple current traffic sub-information, and each of the current traffic sub-information is collected by a different acquisition device;

[0103] The identification of driving influencing factors contained in the current road condition information includes:

[0104] Obtain the current road condition sub-information collected by each of the aforementioned acquisition devices;

[0105] Each of the current road condition sub-informations is identified to obtain the driving impact candidate factors contained in each of the current road condition sub-informations;

[0106] Calculate the confidence level of each driving impact candidate factor based on the driving impact candidate factors contained in each of the current road condition sub-information;

[0107] Candidate factors for driving impact that meet the preset confidence level are used as driving impact factors.

[0108] Different data acquisition devices refer to, but are not limited to, different types of data acquisition devices, different data acquisition methods, and different locations where data acquisition devices are set. For example, data acquisition devices may be, but are not limited to, radar data acquisition devices, camera data acquisition devices, infrared data acquisition devices, etc. The location of the data acquisition devices may be, but is not limited to, the "up", "down", "left", "right", "inside", "outside" directions of the car. The current sub-road condition information corresponds to each data acquisition device and is collected by the corresponding data acquisition device.

[0109] Because the collection effect of one or more collection devices may be affected under certain special circumstances, resulting in inaccurate identification results, the current road condition sub-information collected by each device is identified separately to obtain driving influence candidate factors. The corresponding confidence level is calculated by means of regression analysis, and the driving influence candidate factors with confidence levels within the preset confidence interval are selected as driving influence factors.

[0110] In one embodiment, the path safety parameters corresponding to the current driving path are calculated based on the driving impact factor, including:

[0111] Confirm the distance of the target vehicle relative to the driving influence factor;

[0112] And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained;

[0113] Calculate the path safety parameters corresponding to the current driving path based on the impact level and the distance.

[0114] The impact level can be preset according to various possible driving impact factors.

[0115] Specifically, based on the confidence level of the driving impact factor, the category and corresponding impact level of the driving impact factor are derived to determine the possibility that the driving impact factor poses a threat to the target vehicle. Then, based on the change in the distance between the target vehicle and the driving impact factor, the path safety parameters of the target vehicle on the current path are determined to decide whether the target vehicle needs to change lanes.

[0116] For example, if other vehicles in the lane or adjacent lane where the target vehicle is currently traveling are judged to have a high level of influence based on their type or mode of travel, and the distance between the other vehicle and the target vehicle is too close (less than the preset safe distance threshold), then it is considered that the other vehicle is highly likely to pose a threat to the target vehicle. Furthermore, the safety parameters of the target vehicle's current travel path do not meet the preset conditions, so the target vehicle needs to switch routes.

[0117] To further explain, in one possible implementation, for the adjacent vehicles perceived by the target vehicle and the corresponding collected data, the mean and standard deviation of the distribution of the lateral distance between the adjacent vehicles and the target vehicle in each historical data collection are calculated. If the mean of the lateral distance between one or more adjacent vehicles and the target vehicle is less than a preset safe distance threshold and the standard deviation exceeds a preset stability threshold, then the driving trajectory of the one or more adjacent vehicles is considered unstable, and the event is considered to be of a high impact level. If the target vehicle changes lanes in a direction away from the unstable adjacent vehicles, it meets the safety conditions, and then the target vehicle changes lanes in that direction.

[0118] In one embodiment, if the path safety parameters corresponding to the current driving path do not meet preset safety conditions, then a candidate driving path is confirmed, including:

[0119] Obtain the historical driving path of the target vehicle within a preset time period;

[0120] The historical driving routes and the current driving routes are filtered to obtain candidate driving routes.

[0121] Understandably, in order to avoid the target vehicle frequently changing lanes and causing safety hazards to itself and other vehicles on the road, historical driving routes traveled within a preset time period can also be considered when determining candidate driving routes.

[0122] Specifically, the historical driving routes and the current driving routes are filtered based on the route safety parameters to obtain candidate driving routes. If the historical driving routes and the current driving routes within a preset time are on the same road, the backtracking time for querying the historical driving routes is extended and historical driving routes with different roads are obtained. Alternatively, the acquisition of historical driving routes is paused, and candidate driving routes are filtered based on the current driving route and adjacent routes.

[0123] It should be noted that if the path safety parameters of historical driving routes and adjacent routes do not meet the safety conditions, the selection can be expanded to include more drivable routes on the road.

[0124] In one embodiment, the lane change threat parameter corresponding to each candidate driving path is calculated based on the current driving parameters of the target vehicle, including:

[0125] Identify the current driving parameters of other vehicles in the candidate driving path;

[0126] Lane change simulation is performed based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle;

[0127] Based on the results of the lane change simulation, the time parameters required for the target vehicle to change lanes to the candidate driving path and the speed change parameters of the target vehicle are confirmed.

[0128] The lane change threat parameter corresponding to each candidate driving path is calculated based on the time parameter and the speed change parameter.

[0129] Among them, driving parameters refer to the operating data of the vehicle while it is in motion.

[0130] It should be noted that before the target vehicle changes lanes, a lane change simulation can be performed by combining the driving parameters of the target vehicle and other vehicles to calculate the time and speed changes required for the target vehicle to change lanes to each candidate driving path. In this way, the lane change threat parameters corresponding to each candidate driving path can be calculated to reflect the risks in the process of the target vehicle changing lanes to each candidate driving path.

[0131] In one embodiment, for each route decision of the target vehicle, including whether to perform a lane change or not, the decision and reason can also be broadcast to the driver and / or passengers through the human-machine interface in the vehicle.

[0132] In one embodiment, such as Figure 2As shown, a vehicle route decision-making device is provided, including: a road condition acquisition module, a route safety parameter calculation module, a candidate driving route confirmation module, a lane change threat parameter calculation module, and a target driving route confirmation module, wherein:

[0133] The road condition data collection module is used to collect current road condition information as the target vehicle travels along its current route.

[0134] The route safety parameter calculation module is used to identify the driving influencing factors contained in the current road condition information, and to calculate the route safety parameters corresponding to the current driving route based on the driving influencing factors.

[0135] The candidate driving route confirmation module is used to confirm the candidate driving route if the path safety parameters corresponding to the current driving route do not meet the preset safety conditions.

[0136] The lane change threat parameter calculation module is used to calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and to calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle.

[0137] The target driving path confirmation module is used to confirm the target driving path based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, and control the driving of the target vehicle according to the target driving path.

[0138] In one embodiment, identifying driving influencing factors included in the current road condition information includes:

[0139] The object recognition module is used to identify objects based on the current road condition information and obtain the category information of each object.

[0140] Objects whose category information meets preset conditions are used as driving influence factors.

[0141] In one embodiment, identifying driving influencing factors included in the current road condition information includes:

[0142] The event recognition module is used to recognize events based on the current road condition information and obtain event recognition results.

[0143] The event identification results are used as driving impact factors.

[0144] In one embodiment, the current traffic information is composed of multiple current traffic sub-information, and each of the current traffic sub-information is collected by a different acquisition device;

[0145] The identification of driving influencing factors contained in the current road condition information includes:

[0146] The road condition acquisition module is also used to acquire the current road condition sub-information collected by each of the acquisition devices;

[0147] Each of the current road condition sub-informations is identified to obtain the driving impact candidate factors contained in each of the current road condition sub-informations;

[0148] Calculate the confidence level of each driving impact candidate factor based on the driving impact candidate factors contained in each of the current road condition sub-information;

[0149] Candidate factors for driving impact that meet the preset confidence level are used as driving impact factors.

[0150] In one embodiment, the path safety parameters corresponding to the current driving path are calculated based on the driving impact factor, including:

[0151] The distance control module confirms the distance of the target vehicle relative to the driving influence factor;

[0152] And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained;

[0153] Calculate the path safety parameters corresponding to the current driving path based on the impact level and the distance.

[0154] In one embodiment, if the path safety parameters corresponding to the current driving path do not meet preset safety conditions, then a candidate driving path is confirmed, including:

[0155] The path filtering module is used to obtain the historical driving path of the target vehicle within a preset time period;

[0156] The historical driving routes and the current driving routes are filtered to obtain candidate driving routes.

[0157] In one embodiment, the lane change threat parameter corresponding to each candidate driving path is calculated based on the current driving parameters of the target vehicle, including:

[0158] The lane change simulation module identifies the current driving parameters of other vehicles in the candidate driving path;

[0159] Lane change simulation is performed based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle;

[0160] Based on the results of the lane change simulation, the time parameters required for the target vehicle to change lanes to the candidate driving path and the speed change parameters of the target vehicle are confirmed.

[0161] The lane change threat parameter corresponding to each candidate driving path is calculated based on the time parameter and the speed change parameter.

[0162] In one embodiment, it further includes:

[0163] The human-computer interaction module is used to announce to the driver and / or passengers each route decision and reason made by the target vehicle.

[0164] Specific limitations regarding the vehicle routing decision-making device can be found in the limitations of the vehicle routing decision-making method described above, and will not be repeated here. Each module in the aforementioned vehicle routing decision-making device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0165] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle routing decision method. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0166] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0167] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0168] While the target vehicle is traveling along its current route, collect current road condition information;

[0169] Identify the driving impact factors contained in the current road condition information, and calculate the path safety parameters corresponding to the current driving path based on the driving impact factors;

[0170] If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then the candidate driving path is confirmed.

[0171] Calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle;

[0172] Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, the target driving path is determined, and the driving of the target vehicle is controlled according to the target driving path.

[0173] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0174] Based on the current road condition information, object recognition is performed to obtain the category information of each object;

[0175] Objects whose category information meets preset conditions are used as driving influence factors.

[0176] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0177] Event identification is performed based on the current road condition information to obtain the event identification result;

[0178] The event identification results are used as driving impact factors.

[0179] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0180] Obtain the current road condition sub-information collected by each of the aforementioned acquisition devices;

[0181] Each of the current road condition sub-informations is identified to obtain the driving impact candidate factors contained in each of the current road condition sub-informations;

[0182] Calculate the confidence level of each driving impact candidate factor based on the driving impact candidate factors contained in each of the current road condition sub-information;

[0183] Candidate factors for driving impact that meet the preset confidence level are used as driving impact factors.

[0184] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0185] Confirm the distance of the target vehicle relative to the driving influence factor;

[0186] And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained;

[0187] Calculate the path safety parameters corresponding to the current driving path based on the impact level and the distance.

[0188] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0189] Obtain the historical driving path of the target vehicle within a preset time period;

[0190] The historical driving routes and the current driving routes are filtered to obtain candidate driving routes.

[0191] In one embodiment, when the processor executes the computer program, it further performs the following steps: identifying the current driving parameters of other vehicles in the candidate driving path;

[0192] Lane change simulation is performed based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle;

[0193] Based on the results of the lane change simulation, the time parameters required for the target vehicle to change lanes to the candidate driving path and the speed change parameters of the target vehicle are confirmed.

[0194] The lane change threat parameter corresponding to each candidate driving path is calculated based on the time parameter and the speed change parameter.

[0195] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0196] While the target vehicle is traveling along its current route, collect current road condition information;

[0197] Identify the driving impact factors contained in the current road condition information, and calculate the path safety parameters corresponding to the current driving path based on the driving impact factors;

[0198] If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then the candidate driving path is confirmed.

[0199] Calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, and calculate the lane change threat parameters corresponding to each candidate driving path based on the current driving parameters of the target vehicle;

[0200] Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, the target driving path is determined, and the driving of the target vehicle is controlled according to the target driving path.

[0201] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0202] Based on the current road condition information, object recognition is performed to obtain the category information of each object;

[0203] Objects whose category information meets preset conditions are used as driving influence factors.

[0204] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0205] Event identification is performed based on the current road condition information to obtain the event identification result;

[0206] The event identification results are used as driving impact factors.

[0207] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0208] The identification of driving influencing factors contained in the current road condition information includes:

[0209] Obtain the current road condition sub-information collected by each of the aforementioned acquisition devices;

[0210] Each of the current road condition sub-informations is identified to obtain the driving impact candidate factors contained in each of the current road condition sub-informations;

[0211] Calculate the confidence level of each driving impact candidate factor based on the driving impact candidate factors contained in each of the current road condition sub-information;

[0212] Candidate factors for driving impact that meet the preset confidence level are used as driving impact factors.

[0213] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0214] Confirm the distance of the target vehicle relative to the driving influence factor;

[0215] And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained;

[0216] Calculate the path safety parameters corresponding to the current driving path based on the impact level and the distance.

[0217] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0218] Obtain the historical driving path of the target vehicle within a preset time period;

[0219] The historical driving routes and the current driving routes are filtered to obtain candidate driving routes.

[0220] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0221] Identify the current driving parameters of other vehicles in the candidate driving path;

[0222] Lane change simulation is performed based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle;

[0223] Based on the results of the lane change simulation, the time parameters required for the target vehicle to change lanes to the candidate driving path and the speed change parameters of the target vehicle are confirmed.

[0224] The lane change threat parameter corresponding to each candidate driving path is calculated based on the time parameter and the speed change parameter.

[0225] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0226] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0227] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A vehicle routing decision method, characterized in that, include: While the target vehicle is traveling along its current route, collect current road condition information; Identify the driving influence factors contained in the current road condition information, and confirm the distance of the target vehicle relative to the driving influence factors; And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained; based on the influence level and the distance, the path safety parameters corresponding to the current driving path are calculated; If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then the candidate driving path is confirmed. Calculate path safety parameters corresponding to each candidate driving path based on the current road condition information, and identify the current driving parameters of other vehicles in the candidate driving paths; perform lane change simulation based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle; based on the results of the lane change simulation, determine the time parameter required for the target vehicle to change lanes to the candidate driving path and the speed change parameter of the target vehicle; calculate the lane change threat parameter corresponding to each candidate driving path based on the time parameter and the speed change parameter. Based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, the target driving path is determined, and the driving of the target vehicle is controlled according to the target driving path.

2. The method according to claim 1, characterized in that, The identification of driving influencing factors contained in the current road condition information includes: Based on the current road condition information, object recognition is performed to obtain the category information of each object; Objects whose category information meets preset conditions are used as driving influence factors.

3. The method according to claim 1, characterized in that, The identification of driving influencing factors contained in the current road condition information includes: Event identification is performed based on the current road condition information to obtain the event identification result; The event identification results are used as driving impact factors.

4. The method according to any one of claims 1 to 3, characterized in that, The current traffic information is composed of multiple current traffic information sub-informations, and each current traffic information sub-information is collected by a different data acquisition device; The identification of driving influencing factors contained in the current road condition information includes: Obtain the current road condition sub-information collected by each of the aforementioned acquisition devices; Each of the current road condition sub-informations is identified to obtain the driving impact candidate factors contained in each of the current road condition sub-informations; Calculate the confidence level of each driving impact candidate factor based on the driving impact candidate factors contained in each of the current road condition sub-information; Candidate factors for driving impact that meet the preset confidence level are used as driving impact factors.

5. The method according to claim 1, characterized in that, If the path safety parameters corresponding to the current driving path do not meet the preset safety conditions, then confirming the candidate driving path includes: Obtain the historical driving path of the target vehicle within a preset time period; The historical driving routes and the current driving routes are filtered to obtain candidate driving routes.

6. A vehicle routing decision-making device, characterized in that, include: The road condition data collection module is used to collect current road condition information as the target vehicle travels along its current route. The route safety parameter calculation module is used to identify the driving influence factors contained in the current road condition information and confirm the distance of the target vehicle relative to the driving influence factors. And based on the confidence level corresponding to the driving influence factor, the influence level corresponding to the driving influence factor is obtained; Calculate the path safety parameters corresponding to the current driving path based on the impact level and the distance; The candidate driving route confirmation module is used to confirm the candidate driving route if the path safety parameters corresponding to the current driving route do not meet the preset safety conditions. The lane change threat parameter calculation module is used to calculate the path safety parameters corresponding to each candidate driving path based on the current road condition information, identify the current driving parameters of other vehicles in the candidate driving paths, perform lane change simulation based on the current driving parameters of the other vehicles and the current driving parameters of the target vehicle, determine the time parameter required for the target vehicle to change lanes to the candidate driving path and the speed change parameter of the target vehicle based on the results of the lane change simulation, and calculate the lane change threat parameters corresponding to each candidate driving path based on the time parameter and the speed change parameter. The target driving path confirmation module is used to confirm the target driving path based on the path safety parameters and lane change threat parameters corresponding to each candidate driving path, and control the driving of the target vehicle according to the target driving path.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the vehicle routing decision method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the vehicle routing decision method according to any one of claims 1 to 5.

Images