Auxiliary driving method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses an auxiliary driving method and device, electronic equipment and a storage medium. Obtaining vehicle positioning information sent by each target vehicle in the monitoring range of the vehicle-road interconnection equipment and roadside sensing information collected by a sensor; according to the vehicle positioning information and the roadside sensing information, performing vehicle positioning to obtain target positioning information; and inputting the target positioning information and the roadside sensing information into a traffic planning model, predicting the accident risk of each target vehicle, and sending an accident prediction result to the corresponding target vehicle, so that each target vehicle controls the vehicle motion state according to the accident prediction result. According to the embodiment of the invention, the foresight and accuracy of auxiliary driving are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to intelligent driving technology, and in particular to an assisted driving method, device, electronic device and storage medium. Background Art

[0002] Currently, intelligent driving technology is developing rapidly, and many driving assistance functions have been mass-produced and applied to provide drivers with auxiliary operations and improve driving safety.

[0003] In the prior art, assisted driving usually relies on the vehicle's own sensors to obtain various information and determines the assisted driving strategy based on the surrounding information obtained by the vehicle.

[0004] However, the information obtained by the sensors of the vehicle itself has a lag, and due to the characteristics of the sensors themselves, some sensors may be affected by the environment and cannot obtain effective information. Therefore, it is impossible to obtain comprehensive environmental information, resulting in lag and poor accuracy in assisted driving. Summary of the invention

[0005] The present application provides an assisted driving method, device, electronic device and storage medium to improve the foresight and accuracy of assisted driving.

[0006] In a first aspect, an embodiment of the present application provides an assisted driving method, which is applied to a roadside vehicle-road interconnection device, and the assisted driving method includes:

[0007] Obtain vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection equipment, and roadside perception information collected by sensors;

[0008] According to the vehicle positioning information and roadside sensing information, the vehicle is positioned to obtain the target positioning information;

[0009] The target positioning information and roadside perception information are input into the traffic planning model, the accident risk of each target vehicle is predicted, and the accident prediction results are sent to the corresponding target vehicles so that each target vehicle can control the vehicle motion state according to the accident prediction results.

[0010] In a second aspect, an embodiment of the present application provides an assisted driving method, which is applied to a target vehicle covered by a roadside vehicle-road interconnection device, and the assisted driving method includes:

[0011] Obtain the vehicle positioning information of the vehicle's sensors and the positioning information of external vehicles, and send the vehicle positioning information of the vehicle to the vehicle-road interconnection device on the roadside;

[0012] Receive accident prediction results sent by the roadside vehicle-road interconnection equipment;

[0013] The motion state of the vehicle is controlled according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction results.

[0014] In a third aspect, an embodiment of the present application further provides an auxiliary driving device, which is a vehicle-road interconnection device configured on the roadside, and the auxiliary driving device includes:

[0015] The information acquisition module is used to obtain the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and the roadside perception information collected by the sensor;

[0016] A target positioning information determination module is used to perform vehicle positioning according to the vehicle positioning information and roadside sensing information to obtain target positioning information;

[0017] The accident risk prediction module is used to input the target positioning information and roadside perception information into the traffic planning model, predict the accident risk of each target vehicle, and send the accident prediction results to the corresponding target vehicles so that each target vehicle can control the vehicle motion state according to the accident prediction results.

[0018] In a fourth aspect, an embodiment of the present application further provides an auxiliary driving device, which is configured on a target vehicle covered by a roadside vehicle-road interconnection device, and the auxiliary driving device includes:

[0019] The interconnection information acquisition module is used to obtain the vehicle positioning information of the vehicle sensor and the positioning information of external vehicles, and send the vehicle positioning information of the vehicle to the vehicle-road interconnection device on the road side;

[0020] An accident prediction result receiving module is used to receive the accident prediction result sent by the vehicle-road interconnection device on the road side;

[0021] The motion state control module is used to control the motion state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction results.

[0022] In a fifth aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising:

[0023] one or more processors;

[0024] A storage device for storing one or more programs;

[0025] When one or more programs are executed by one or more processors, the one or more processors implement any one of the assisted driving methods provided in the embodiments of the present application.

[0026] In a sixth aspect, an embodiment of the present application further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute any one of the assisted driving methods provided in the embodiments of the present application.

[0027] This application can obtain comprehensive traffic flow information of the monitored section by obtaining vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device and roadside perception information collected by sensors; based on the vehicle positioning information and roadside perception information, the vehicle is positioned to obtain target positioning information, thereby improving the accuracy of the positioning information; each target positioning information and roadside perception information are input into the traffic planning model, the accident risk of each target vehicle is predicted, and the accident prediction results are sent to the corresponding target vehicles, so that each target vehicle controls the vehicle motion state according to the accident prediction results, and the traffic planning model is used to predict accidents for the entire section of the road from a global perspective, thereby improving the foresight and accuracy of the prediction results. Therefore, the technical solution of this application solves the problem of being unable to obtain comprehensive environmental information, resulting in hysteresis and poor accuracy in assisted driving, and achieves the effect of improving the foresight and accuracy of assisted driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flow chart of an assisted driving method in Embodiment 1 of the present application;

[0029] Figure 2 is a flow chart of an assisted driving method in Embodiment 2 of the present application;

[0030] Figure 3 is a flow chart of an assisted driving method in Embodiment 3 of the present application;

[0031] Figure 4 is a structural schematic diagram of a driving assistance device in Embodiment 4 of the present application;

[0032] Figure 5 It is a structural schematic diagram of a driving assistance device in Embodiment 5 of the present application;

[0033] Figure 6 It is a structural diagram of an electronic device in Example 6 of the present application. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0035] It should be noted that the terms "first" and "second" etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Embodiment 1

[0037] Figure 1 This is a flow chart of an assisted driving method provided in Example 1 of the present application. This embodiment can be applicable to the situation where an assisted driving function is provided to a vehicle. The method can be executed by an assisted driving device, which can be implemented in software and / or hardware and specifically configured in a vehicle-road interconnection device on the roadside.

[0038] See also Figure 1 The assisted driving method shown is applied to a roadside vehicle-road interconnection device and specifically includes the following steps:

[0039] S110: Obtain vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and roadside perception information collected by the sensor.

[0040] The vehicle-road interconnection device can be a monitoring tower installed on one side of the road with integrated sensing, computing, receiving and transmission capabilities. It can be used to predict the accident risk of each target vehicle and send the accident prediction results to the corresponding target vehicle. The vehicle-road interconnection device can be arranged at intervals of 200-260 meters along the roadside, and its height can be determined by the detection field of view of each sensor selected. The vehicle-road interconnection device and the vehicle communicate with each other to form a perception network. The perception end of the vehicle-road interconnection device is equipped with a camera and a millimeter-wave radar, which can identify and classify targets within the detection range. Exemplarily, identifiable targets may include vehicles, two-wheeled vehicles, pedestrians, construction areas, obstacles, accumulated water and potholes on the road, etc., which are not specifically limited in this application. The roadside base station obtains various targets through the perception end, and combined with the road environment, it can identify collision risks in advance, or send navigation environment warning information to associated vehicles in advance. Since the vehicle-road interconnection equipment has a certain level of sophistication and obtains more comprehensive information, it can improve the accuracy of subsequent predictions of accident risks for each target vehicle, and can obtain information on vehicles traveling on the entire road section, so as to predict the probability of various accidents in advance and improve the foresight of accident risk prediction.

[0041] The target vehicle may be a vehicle traveling within the monitoring range of the vehicle-road interconnection device, and the target vehicle may communicate with the vehicle-road interconnection device. The target vehicle may send vehicle positioning information to the vehicle-road interconnection device at a certain communication frequency. The roadside sensing information may be information collected by cameras installed on the vehicle-road interconnection device and millimeter-wave radars. Exemplarily, the roadside sensing information may include the location information, speed information, and posture information of each target vehicle, which is not specifically limited in this application.

[0042] S120: Based on the vehicle positioning information and the roadside sensing information, the vehicle is positioned to obtain target positioning information.

[0043] The vehicle positioning information is the vehicle positioning information of each target vehicle determined based on the map, etc. Since it takes a certain amount of time to update and load the map, there may be a certain error in the vehicle positioning information. By fusing the vehicle positioning information with the roadside perception information collected by the camera of the vehicle-road interconnection device and the millimeter wave, more accurate positioning information, that is, target positioning information, can be obtained. The target positioning information is the positioning information after information fusion based on the vehicle positioning information and the roadside perception information. Exemplarily, the target positioning information can be coordinate information and posture information.

[0044] S130. Input the target positioning information and roadside perception information into the traffic planning model, predict the accident risk of each target vehicle, and send the accident prediction result to the corresponding target vehicle, so that each target vehicle can control the vehicle motion state according to the accident prediction result.

[0045] The traffic planning model can be a model trained based on the traffic data of the current road section, used to predict the accident risk based on the current vehicle positioning information and traffic status, and send the accident prediction results to the corresponding target vehicle. The corresponding target vehicle can receive the accident prediction results and prompt the driver according to its own auxiliary driving system or control the driving status of the vehicle to avoid risks. For example, the traffic planning model can be a neural network model

[0046] The target positioning information and roadside perception information are input into the traffic planning model, which can predict the accident risk of each target vehicle and send the accident prediction results to the corresponding target vehicle. The traffic planning model can obtain traffic condition information of the entire monitored section through roadside perception information, and can perform global planning processing, which can identify possible accidents in advance and improve the foresight and accuracy of accident prediction results.

[0047] By uploading the target positioning information and roadside perception information to the traffic planning model, each target vehicle is tracked and predicted through scenarios such as longitudinal acceleration and deceleration, lateral lane changes, intersection turns, roundabouts, merging into and out of ramps, etc., and combined with global traffic participation elements for calculation, the participation status of each target vehicle participating in the traffic in the road network can be monitored in real time. Through the traffic planning model, the risk of accidents can be predicted, and possible traffic danger scenarios can be predicted and warned in advance.

[0048] In an optional embodiment, the traffic planning model is trained in the following manner: obtaining historical traffic flow data, and corresponding historical road condition information, time type and geographic information; using the historical traffic flow data, and corresponding historical road condition information, time type and geographic information as training data, and training the initial traffic planning model to obtain a trained traffic planning model.

[0049] Historical traffic flow data may include the number of vehicles, speed, and direction of travel during a certain period of time in the past. Historical road condition information may include road congestion, accident information, weather, and construction conditions. Time types may include date, time period, and holiday information. Geographic location information may include the geographical location of the road and nearby important facilities. Different historical road condition information, time types, and geographic information will affect the prediction results. Therefore, historical traffic flow data, historical road condition information, time types, and geographic information are used as training data to train the initial traffic planning model to obtain a trained traffic planning model, thereby improving the accuracy of the traffic planning model.

[0050] By obtaining historical traffic flow data, historical road condition information, time type and geographic information; using historical traffic flow data, historical road condition information, time type and geographic information as training data, the initial traffic planning model is trained to obtain a trained traffic planning model. The traffic planning model can predict accidents according to different time types, road conditions and traffic conditions, thereby improving the accuracy of the prediction.

[0051] Many cities have begun to fully promote vehicle-road cooperative systems, such as smart traffic lights, and networking of vehicles and infrastructure. Currently, intelligent driving technology is developing rapidly, and many driving assistance functions have been mass-produced and applied. Based on the current main on-board sensor solutions, the vehicle's perception of the surrounding environment mainly relies on cameras, millimeter-wave radars, high-precision maps, and lidars, etc. There are scenarios where the function is limited when the detection distance is exceeded or there are obstacles blocking the vehicle. For the prior perception of high-precision maps, there are problems such as slow update frequency. All of the above may cause safety issues for driving assistance functions in boundary scenarios.

[0052] The technical solution of this embodiment can fully obtain the traffic flow information of the monitored section by obtaining the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device and the roadside perception information collected by the sensor; based on the vehicle positioning information and the roadside perception information, the vehicle is positioned to obtain the target positioning information, thereby improving the accuracy of the positioning information; the positioning information of each target and the roadside perception information are input into the traffic planning model, the accident risk of each target vehicle is predicted, and the accident prediction results are sent to the corresponding target vehicles, so that each target vehicle controls the vehicle motion state according to the accident prediction results, and the traffic planning model is used to predict accidents for the entire road section from a global perspective, thereby improving the foresight and accuracy of the prediction results. Therefore, the technical solution of this application solves the problem that it is impossible to obtain comprehensive environmental information, resulting in hysteresis and poor accuracy in assisted driving, and achieves the effect of improving the foresight and accuracy of assisted driving.

[0053] Embodiment 2

[0054] Figure 2 This is a flow chart of an assisted driving method provided in Example 2 of the present application. The technical solution of this embodiment is further refined on the basis of the above technical solution.

[0055] Furthermore, after “obtaining the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and the perception information of the sensor”, add: “Based on the perception information, determine whether there are fixed obstacles; fixed obstacles include at least one of accumulated water, potholes, obstacles and construction guardrails; based on the vehicle positioning information and the vehicle's movement information, predict whether there is a risk of fixed collision with the fixed obstacle, and send the fixed collision prediction result to each target vehicle” to predict the risk of fixed collision.

[0056] See also Figure 2 An assisted driving method shown includes:

[0057] S210: Obtain vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and roadside perception information collected by the sensor.

[0058] S220: Based on the vehicle positioning information and the roadside sensing information, the vehicle is positioned to obtain target positioning information.

[0059] S230, input each target positioning information and roadside perception information into the traffic planning model, predict the accident risk of each target vehicle, and send the accident prediction result to the corresponding target vehicle, so that each target vehicle can control the vehicle motion state according to the accident prediction result.

[0060] S240. Determine whether there are fixed obstacles based on roadside sensing information; fixed obstacles include at least one of accumulated water, potholes, obstacles and construction guardrails.

[0061] Fixed obstacles include at least one of puddles, potholes, obstacles and construction guardrails. Fixed obstacles may affect driving safety, so it is necessary to identify fixed obstacles to improve driving safety. Roadside perception information may include photographed road images. Fixed obstacles in road images can be identified through target recognition algorithms to determine whether there are fixed obstacles.

[0062] S250: Predict whether there is a risk of fixed collision with a fixed obstacle based on the vehicle positioning information and the vehicle movement information, and send the fixed collision prediction result to each target vehicle.

[0063] The vehicle's driving trajectory can be predicted based on the vehicle's positioning information and the vehicle's motion information. If there is a fixed obstacle in the predicted driving trajectory, it is determined that there is a risk of a fixed collision with the fixed obstacle, and the prediction result is sent to the corresponding target vehicle. After receiving the fixed collision prediction result, the target vehicle prompts the driver or controls the vehicle to change its motion state based on the fixed collision prediction result, such as changing lanes or slowing down.

[0064] In some scenarios with limited vision, such as when there are tall buildings at a turn, the vehicle's own sensors cannot obtain road condition information after the turn. At this time, obtaining fixed collision prediction results based on the roadside vehicle-road interconnection equipment can avoid collisions with fixed obstacles and improve driving safety.

[0065] In an optional embodiment, the method further includes: identifying the emergency vehicle based on the perception information, and sending the emergency vehicle identification result to each target vehicle, so that each target vehicle determines the avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of the external vehicle.

[0066] Emergency vehicles include special vehicles such as ambulances, fire trucks and police cars. When an emergency vehicle appears behind a vehicle, it is necessary to give way to the emergency vehicle. However, due to the influence of the road environment, the vehicle may not be able to detect the emergency vehicle in time, or cannot quickly determine the avoidance method, which affects the passage of the emergency vehicle and even causes road congestion.

[0067] The camera is used to shoot the traffic participating vehicles in the monitored road section and identify the emergency vehicle. When an emergency vehicle is identified, the emergency vehicle identification result is sent to each target vehicle, so that each target vehicle can determine the avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of the external vehicle. Exemplarily, the target vehicle can determine the avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of the external vehicle based on the deep learning model.

[0068] Optionally, the roadside vehicle-road interconnection equipment can plan the emergency vehicle avoidance method based on the positioning and posture information of each target vehicle, and send the emergency vehicle avoidance method to the target vehicle in front of the emergency vehicle, so that the target vehicle can quickly give way to the emergency vehicle without causing traffic congestion.

[0069] By identifying emergency vehicles based on perception information and sending the emergency vehicle identification results to each target vehicle, each target vehicle can determine its own avoidance method based on its own vehicle positioning information and the positioning information of external vehicles. Each target vehicle can be notified in time to give way to the emergency vehicle and ensure the rapid passage of the emergency vehicle.

[0070] The technical solution of this embodiment determines whether there are fixed obstacles based on perception information; the fixed obstacles include at least one of accumulated water, potholes, obstacles and construction guardrails; based on the vehicle positioning information and the vehicle's motion information, predicts whether there is a risk of fixed collision with the fixed obstacle, and sends the fixed collision prediction results to each target vehicle, which can avoid the collision between the target vehicle and the fixed obstacle from a global perspective and improve driving safety.

[0071] Embodiment 3

[0072] Figure 3 This is a flow chart of an assisted driving method provided in Example 3 of the present application. This embodiment can be applicable to the situation where an assisted driving function is provided to a vehicle. The method can be executed by an assisted driving device, which can be implemented using software and / or hardware and is specifically configured in a target vehicle covered by a roadside vehicle-road interconnection device.

[0073] See also Figure 3 The assisted driving method shown is applied to a target vehicle covered by a roadside vehicle-road interconnection device, and specifically includes the following steps:

[0074] S310: Obtain vehicle positioning information of the vehicle and positioning information of external vehicles, and send the vehicle positioning information of the vehicle to a vehicle-road interconnection device on the road side.

[0075] The vehicle obtains information about the surrounding environment of the vehicle through the vehicle-side perception unit. Exemplarily, the perception unit may include a front-view camera, a rear-view camera, a forward millimeter-wave radar, and a rear-angle millimeter-wave radar. The perception level can be significantly improved by fusing the perception information of the vehicle and the perception information of external vehicles. The position of the vehicle can be located in real time by combining the inertial navigation unit to obtain vehicle positioning information. According to the vehicle positioning information collected by the vehicle's sensors and the external vehicle's own positioning information sent by external vehicles, assisted driving planning decisions can be made to realize driving assistance functions. Exemplarily, assisted driving can be realized by sending control information to the lateral and longitudinal execution units and the central control unit respectively. The lateral and longitudinal execution units can realize the lateral and longitudinal motion control of the vehicle, and the central control unit can realize the alarm prompts such as sound and light in the vehicle.

[0076] External vehicles may be other vehicles around the vehicle. For example, external vehicles may be vehicles within 200 meters in front of the vehicle's lane, 120 meters behind the vehicle, 180 meters in front of the adjacent lane, and 100 meters behind the vehicle. The vehicle and external vehicles communicate and interconnect through the vehicle-mounted communication unit to obtain the positioning information of external vehicles in real time. The vehicle may also send the vehicle positioning information of the vehicle to the vehicle-road interconnection device on the road side through the vehicle-mounted communication unit.

[0077] S320: Receive accident prediction results sent by the roadside vehicle-road interconnection device.

[0078] After receiving the vehicle positioning information of the vehicle, the roadside vehicle-road interconnection device performs vehicle positioning based on the vehicle positioning information and roadside perception information to obtain target positioning information; each target positioning information and roadside perception information are input into the traffic planning model, the accident risk of each target vehicle is predicted, and the accident prediction result is sent to the corresponding target vehicle. The vehicle receives the accident prediction result sent by the roadside vehicle-road interconnection device.

[0079] S330: Control the motion state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction result.

[0080] After obtaining the vehicle positioning information of the vehicle, the positioning information of the external vehicles and the accident prediction results, the vehicle positioning information of the vehicle, the positioning information of the external vehicles and the accident prediction results are sent to the driving assistance controller through the vehicle communication unit, and the driving assistance controller determines the auxiliary driving strategy. For example, the driving assistance controller can determine whether to send a warning signal to the central control unit, or send a control command to the horizontal and vertical execution units to assist the driver in avoiding risks.

[0081] Exemplarily, the judgment of warning signals can be based on avoiding collisions, introducing coefficient variables, setting warning signal thresholds, and determining whether to send warning signals. Exemplarily, control instructions can be judged based on the RSS responsibility-sensitive model (a professional term, a model), assuming that the "worst case" means that the front vehicle starts braking at the maximum deceleration, and the rear vehicle has a certain reaction time after discovering it, and still moves forward at the maximum acceleration during the reaction time, and then changes to braking at the minimum deceleration. If collisions can be avoided in this case, then there is no possibility of rear-ending the front vehicle for the autonomous driving vehicle. The minimum safe distance calculation formula is as follows:

[0082] Dmin=V r ρ+1 / 2α max ρ 2 +(V r +ρα max ) 2 / 2β min -V f 2 / 2β max ;

[0083] Among them, Dmin is the minimum safety distance, V f is the speed of the front vehicle, V r is the speed of the following vehicle, ρ is the reaction time, α min is the minimum braking acceleration of the rear vehicle, β min is the minimum braking acceleration of the front vehicle, α max is the maximum braking acceleration of the rear vehicle and β max is the maximum braking acceleration of the vehicle in front.

[0084] By obtaining the positioning information and accident prediction results of external vehicles, it is possible to change from single-vehicle intelligence to vehicle-road collaborative intelligence. The target vehicle can receive messages from various information sources such as roadside equipment, other vehicles and traffic lights, making up for the low accuracy and lag of assisted driving caused by the limited sensor perception range, or the obstruction of obstacles, or the influence of extreme weather such as heavy fog and snow. The roadside detection equipment and other vehicles continuously enhance the perception ability of the vehicle, and form a perception group with a wider overall detection distance and range and a smaller detection blind spot.

[0085] For example, by obtaining the positioning information and accident prediction results of external vehicles, the intersection collision warning function can be improved. When the vehicle is approaching an intersection and there is a risk of collision with a distant vehicle traveling sideways, the roadside vehicle-road interconnection device will send a warning message to the vehicle, and the vehicle's central control unit will warn the driver. This function is applicable to the warning of collision hazards at intersections such as intersections of ordinary roads and highways in cities and suburbs, entrances to ring roads, and entrances to highways. It assists drivers in avoiding or reducing lateral collisions and improves traffic safety at intersections.

[0086] For vehicles that do not obtain the positioning information and accident prediction results of external vehicles, the existing implementation solution is to use the front corner millimeter wave radar of the vehicle to realize the recognition of the front and side traffic targets. The detection of this solution is easily blocked, and the recognition may be late due to the blockage of roadbed guardrails, etc. By introducing the acquisition of the positioning information and accident prediction results of external vehicles, the collision risk can be identified early, assisting vehicle driving and reducing the collision risk.

[0087] For example, when the host vehicle and a distant vehicle are about to merge at an intersection, the detection capability of the host vehicle, such as the front-view camera and the front-angle millimeter-wave radar, is limited by obstacles such as guardrails and trees on the road, as well as weather conditions such as heavy fog and snow, and it is impossible to accurately capture and track the distant vehicle target. The roadside vehicle-road interconnection equipment built on the roadside can accurately identify the coordinate position, movement direction, movement speed and other information of the target vehicle participating in the road traffic from a high altitude through the camera, and can quickly calculate and predict whether there is a collision risk for the relevant target based on the current driving status. If there is a risk, the roadside equipment will send prompt information to the corresponding host vehicle and distant vehicle in real time to remind the driver to slow down in time and improve the safety of crossing the intersection.

[0088] The technical solution of this embodiment obtains the vehicle positioning information of the vehicle and the positioning information of external vehicles, and sends the vehicle positioning information of the vehicle to the roadside vehicle-road interconnection device; receives the accident prediction results sent by the roadside vehicle-road interconnection device; controls the movement state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction results. By obtaining the accident prediction results sent by the roadside vehicle-road interconnection device, the accident prediction results of the traffic accident prediction of the entire road section from a global perspective can be obtained, and the movement state of the vehicle can be controlled in time to improve the foresight and accuracy of assisted driving. Therefore, the technical solution of this application solves the problem that the comprehensive environmental information cannot be obtained, resulting in the lag and poor accuracy of assisted driving, and achieves the effect of improving the foresight and accuracy of assisted driving.

[0089] In an optional embodiment, the method further includes: receiving an emergency vehicle identification result sent by a roadside vehicle-road interconnection device; and determining an avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of external vehicles.

[0090] By receiving the emergency vehicle identification results sent by the roadside vehicle-road interconnection device, it is possible to obtain timely information on whether it is necessary to give way to the emergency vehicle. The central control unit of the vehicle can plan the route based on the vehicle positioning information of the vehicle and the positioning information of the external vehicle, and determine the avoidance method of the vehicle. For example, the avoidance method of the vehicle can be determined based on the vehicle positioning information of the vehicle and the positioning information of the external vehicle based on the deep learning model.

[0091] By receiving the emergency vehicle identification results sent by the roadside vehicle-road interconnection equipment and determining the avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of external vehicles, emergency vehicles can be discovered in time and quickly given way to them.

[0092] Embodiment 4

[0093] Figure 4 The figure shows a schematic diagram of the structure of an auxiliary driving device provided in the fourth embodiment of the present application. This embodiment can be applied to the case of providing an auxiliary driving function for a vehicle, and is configured on the roadside of a vehicle-road interconnection device. The specific structure of the auxiliary driving device is as follows:

[0094] The information acquisition module 410 is used to acquire the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and the roadside perception information collected by the sensor;

[0095] The target positioning information determination module 420 is used to perform vehicle positioning according to the vehicle positioning information and the roadside sensing information to obtain the target positioning information;

[0096] The accident risk prediction module 430 is used to input the target positioning information and roadside perception information into the traffic planning model, predict the accident risk of each target vehicle, and send the accident prediction result to the corresponding target vehicle so that each target vehicle can control the vehicle motion state according to the accident prediction result.

[0097] The technical solution of this embodiment can fully obtain the traffic flow information of the monitored section by obtaining the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device and the roadside perception information collected by the sensor; based on the vehicle positioning information and the roadside perception information, the vehicle is positioned to obtain the target positioning information, thereby improving the accuracy of the positioning information; the positioning information of each target and the roadside perception information are input into the traffic planning model, the accident risk of each target vehicle is predicted, and the accident prediction results are sent to the corresponding target vehicles, so that each target vehicle controls the vehicle motion state according to the accident prediction results, and the traffic planning model is used to predict accidents for the entire road section from a global perspective, thereby improving the foresight and accuracy of the prediction results. Therefore, the technical solution of this application solves the problem that it is impossible to obtain comprehensive environmental information, resulting in hysteresis and poor accuracy in assisted driving, and achieves the effect of improving the foresight and accuracy of assisted driving.

[0098] Optionally, the traffic planning model is trained using the following modules:

[0099] A historical data acquisition module is used to acquire historical traffic flow data, as well as corresponding historical road condition information, time type and geographic information;

[0100] The traffic planning model training module is used to use historical traffic flow data, as well as corresponding historical road condition information, time type and geographical information as training data to train the initial traffic planning model to obtain a trained traffic planning model.

[0101] Optional auxiliary driving devices also include:

[0102] A fixed obstacle recognition module, used to determine whether there are fixed obstacles based on roadside sensing information; fixed obstacles include at least one of accumulated water, pits, obstacles and construction guardrails;

[0103] The fixed collision risk prediction module is used to predict whether there is a risk of fixed collision with a fixed obstacle based on the vehicle positioning information and the vehicle movement information, and send the fixed collision prediction result to each target vehicle.

[0104] Optional auxiliary driving devices also include:

[0105] The emergency vehicle identification module is used to identify the emergency vehicle based on the roadside perception information and send the emergency vehicle identification result to each target vehicle so that each target vehicle can determine the avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of the external vehicles.

[0106] The assisted driving device provided in the embodiments of the present application can execute the assisted driving method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the assisted driving method.

[0107] Embodiment 5

[0108] Figure 5 The figure shows a schematic diagram of the structure of an auxiliary driving device provided in the fifth embodiment of the present application. The present embodiment can be applied to the case where an auxiliary driving function is provided to a vehicle, and the target vehicle covered by the vehicle-road interconnection device disposed on the roadside. The specific structure of the auxiliary driving device is as follows:

[0109] The interconnection information acquisition module 510 is used to obtain the vehicle positioning information of the vehicle and the positioning information of external vehicles, and send the vehicle positioning information of the vehicle to the vehicle-road interconnection device on the road side;

[0110] The accident prediction result receiving module 520 is used to receive the accident prediction result sent by the vehicle-road interconnection device on the road side;

[0111] The motion state control module 530 is used to control the motion state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction result.

[0112] The technical solution of this embodiment obtains the vehicle positioning information of the vehicle and the positioning information of external vehicles, and sends the vehicle positioning information of the vehicle to the roadside vehicle-road interconnection device; receives the accident prediction results sent by the roadside vehicle-road interconnection device; controls the movement state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction results. By obtaining the accident prediction results sent by the roadside vehicle-road interconnection device, the accident prediction results of the traffic accident prediction of the entire road section from a global perspective can be obtained, and the movement state of the vehicle can be controlled in time to improve the foresight and accuracy of assisted driving. Therefore, the technical solution of this application solves the problem that the comprehensive environmental information cannot be obtained, resulting in the lag and poor accuracy of assisted driving, and achieves the effect of improving the foresight and accuracy of assisted driving.

[0113] Optional auxiliary driving devices also include:

[0114] An emergency vehicle identification result receiving module is used to receive the emergency vehicle identification result sent by the roadside vehicle-road interconnection device;

[0115] The avoidance mode determination module is used to determine the avoidance mode of the vehicle according to the vehicle positioning information of the vehicle and the positioning information of the external vehicle.

[0116] The assisted driving device provided in the embodiments of the present application can execute the assisted driving method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the assisted driving method.

[0117] Embodiment 6

[0118] Figure 6 A schematic diagram of the structure of an electronic device provided in Example 6 of the present application is shown in FIG. Figure 6 As shown, the electronic device includes a processor 610, a memory 620, an input device 630, and an output device 640; the number of the processor 610 in the electronic device can be one or more. Figure 6 A processor 610 is taken as an example; the processor 610, memory 620, input device 630 and output device 640 in the electronic device can be connected via a bus or other methods, and Figure 640 takes the connection via a bus as an example.

[0119] The memory 620, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the assisted driving method in the embodiment of the present application (for example, the information acquisition module 410, the target positioning information determination module 420 and the accident risk prediction module 430). The processor 610 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 620, that is, realizing the above-mentioned assisted driving method.

[0120] The memory 620 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 620 may further include a memory remotely arranged relative to the processor 610, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0121] The input device 630 may be used to receive input character information and generate key signal input related to user settings and function control of the electronic device. The output device 640 may include a display device such as a display screen.

[0122] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0123] Embodiment 7

[0124] Embodiment 7 of the present application also provides a storage medium containing computer executable instructions, which is applied to a roadside vehicle-road interconnection device. When the computer executable instructions are executed by a computer processor, they are used to execute an assisted driving method, which includes: obtaining vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and roadside perception information collected by a sensor; performing vehicle positioning according to the vehicle positioning information and the roadside perception information to obtain target positioning information; inputting each target positioning information and roadside perception information into a traffic planning model, predicting the accident risk of each target vehicle, and sending the accident prediction result to the corresponding target vehicle, so that each target vehicle controls the vehicle motion state according to the accident prediction result.

[0125] Embodiment 7 of the present application also provides a storage medium containing computer executable instructions, which is applied to a target vehicle covered by a roadside vehicle-road interconnection device. When the computer executable instructions are executed by a computer processor, they are used to execute an assisted driving method, which includes: obtaining vehicle positioning information of the vehicle's sensor and positioning information of external vehicles, and sending the vehicle positioning information of the vehicle to the roadside vehicle-road interconnection device; receiving an accident prediction result sent by the roadside vehicle-road interconnection device; and controlling the motion state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of external vehicles and the accident prediction result.

[0126] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present application, whose computer executable instructions are not limited to the method operations described above, can also execute related operations in the assisted driving method provided in any embodiment of the present application.

[0127] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0128] It is worth noting that in the embodiment of the above-mentioned assisted driving device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0129] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A driving assistance method, characterized in that: Vehicle-road interconnection equipment used on the roadside includes: Obtain vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection equipment, and roadside perception information collected by sensors; Performing vehicle positioning according to the vehicle positioning information and the roadside sensing information to obtain target positioning information; The target positioning information and the roadside perception information are input into the traffic planning model, the accident risk of each target vehicle is predicted, and the accident prediction result is sent to the corresponding target vehicle, so that each target vehicle can control the vehicle motion state according to the accident prediction result.

2. The method according to claim 1, characterized in that The traffic planning model is trained in the following way: Obtain historical traffic flow data, as well as corresponding historical road condition information, time type and geographic information; The historical traffic flow data, and the corresponding historical road condition information, the time type and the geographic information are used as training data to train the initial traffic planning model to obtain a trained traffic planning model.

3. The method according to claim 1, characterized in that After obtaining the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device and the perception information of the sensor, the method further includes: Determine whether there is a fixed obstacle according to the roadside sensing information; the fixed obstacle includes at least one of accumulated water, a pit, an obstacle and a construction guardrail; Based on the vehicle positioning information and the vehicle movement information, it is predicted whether there is a risk of fixed collision with the fixed obstacle, and the fixed collision prediction result is sent to each of the target vehicles.

4. The method according to claim 1, characterized in that: The method further comprises: The emergency vehicle is identified based on the roadside sensing information, and the emergency vehicle identification result is sent to each of the target vehicles, so that each of the target vehicles determines the avoidance method of the vehicle based on the vehicle positioning information of the vehicle and the positioning information of external vehicles.

5. A driving assistance method, characterized in that: The target vehicles covered by the roadside vehicle-road interconnection equipment include: Acquire vehicle positioning information of the vehicle and positioning information of external vehicles, and send the vehicle positioning information of the vehicle to the vehicle-road interconnection device on the roadside; Receive accident prediction results sent by the roadside vehicle-road interconnection equipment; The motion state of the vehicle is controlled according to the vehicle positioning information of the vehicle, the positioning information of the external vehicle and the accident prediction result.

6. The method according to claim 5, characterized in that The method further comprises: Receive emergency vehicle identification results sent by roadside vehicle-road interconnection equipment; The avoidance method of the vehicle is determined according to the vehicle positioning information of the vehicle and the positioning information of the external vehicle.

7. A driving assistance device, characterized in that: The vehicle-road interconnection equipment configured on the roadside includes: The information acquisition module is used to obtain the vehicle positioning information sent by each target vehicle within the monitoring range of the vehicle-road interconnection device, and the roadside perception information collected by the sensor; A target positioning information determination module, used to perform vehicle positioning according to the vehicle positioning information and the roadside sensing information to obtain target positioning information; The accident risk prediction module is used to input the target positioning information and the roadside perception information into the traffic planning model, predict the accident risk of each target vehicle, and send the accident prediction result to the corresponding target vehicle so that each target vehicle can control the vehicle motion state according to the accident prediction result.

8. A driving assistance device, characterized in that: The target vehicles covered by the roadside vehicle-road interconnection equipment include: The interconnection information acquisition module is used to obtain the vehicle positioning information of the vehicle and the positioning information of external vehicles, and send the vehicle positioning information of the vehicle to the vehicle-road interconnection device on the road side; An accident prediction result receiving module is used to receive the accident prediction result sent by the vehicle-road interconnection device on the road side; The motion state control module is used to control the motion state of the vehicle according to the vehicle positioning information of the vehicle, the positioning information of the external vehicle and the accident prediction result.

9. An electronic 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 program, the assisted driving method as described in any one of claims 1-4 and / or 5-6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the assisted driving method as described in any one of claims 1-4 and / or 5-6 is implemented.

Images