Low-speed automatic piloting method and system, electronic device and storage medium

Abstract

The application relates to a low-speed automatic navigation method, a system, an electronic device and a storage medium, the automatic navigation method comprising the following steps: setting a sensing unit of a vehicle, the sensing unit comprising a camera, ultrasonic radar and an angular laser radar; determining a road scene and a front obstacle condition of the vehicle based on the sensing unit, and determining the width of a passable space in front of the vehicle excluding static obstacles; when the width of the passable space in front of the vehicle meets the passable requirement based on the sensing unit, the vehicle continues to move forward; when the width of the passable space in front of the vehicle does not meet the passable requirement, the vehicle is controlled to return along the original path or to turn around; the low-speed navigation function of the fusion of vision, ultrasonic wave and laser radar sensing is used to pass through a narrow road in a low-speed scene to avoid vehicle or personnel casualties and losses, and the probability of collision caused by narrow road passing and turning around in a low-speed scene is effectively reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic driving, in particular to a low-speed automatic navigation method and system, an electronic device and a storage medium. BACKGROUND

[0002] The current domestic and foreign household vehicle ownership rate is getting higher and higher, so the driving scene of automatic driving is getting more and more complex. In the city or narrow road of mountainous area, how to ensure the safe driving of vehicle in low-speed environment (vehicle speed ≤10kph), to use road elements to effectively perceive obstacles and road guide signs and control the vehicle to complete cruise and U-turn, is an important issue that needs to be considered in the field of automatic driving.

[0003] The technical scheme disclosed in the Chinese invention patent application with the title of "Method for autonomously driving vehicle in narrow road section (publication number: CN109416542A)" mainly describes the automatic driving method of the vehicle in the bidirectional narrow road scene. The control strategy of the vehicle is made according to the judgment of the opposite vehicle quantity and the driving acceleration, and the obstacle avoidance is also carried out according to the system storage of local traffic rules. However, when encountering a non-passable road section, the vehicle can only reverse to the original point of the vehicle starting function and cannot U-turn, and cannot perform road cruise according to the lane guide line. SUMMARY

[0004] The present application provides a low-speed automatic navigation method, system, electronic device and storage medium to assist the driver to safely pass or U-turn in the narrow road scene, and prevent the loss of wheels and personnel casualties caused by external complex environment.

[0005] According to the first aspect of the present application, a low-speed automatic navigation method is provided, comprising:

[0006] Step 1, setting the perception unit of the vehicle, the perception unit comprising: a camera, an ultrasonic radar and an angular laser radar;

[0007] Step 2, judging the road scene and the front obstacle situation of the vehicle based on the perception unit, and determining the width of the passable space in front of the vehicle excluding the static obstacles;

[0008] Step 3, when the width of the passable space in front of the vehicle meets the passing demand based on the perception unit, the vehicle continues to move forward; when the width of the passable space in front of the vehicle does not meet the passing demand, the vehicle is controlled to return to the original road or U-turn.

[0009] On the basis of the above technical scheme, the present application can also be improved as follows.

[0010] Optionally, before the step 2, the method further comprises: receiving a user manual triggering instruction of the low-speed piloting function, and executing the steps 2-4.

[0011] When the low-speed piloting function is started, the low-speed piloting function is exited immediately upon receiving an exit instruction from the user; the exit instruction comprises any one of the following: stepping on the brake, intervening the gear, and intervening the steering wheel.

[0012] Optionally, the process of determining the width of the passable space in the step 2 comprises:

[0013] Taking a center point of a rear axle of the vehicle as a starting coordinate origin, at least two images of the vehicle traveling at a speed v are acquired based on the camera;

[0014] The time interval between the two images is determined based on the camera, the distance difference between the two images in the traveling direction of the vehicle is calculated based on the time interval and the speed of the vehicle, and the oblique distance between the vehicle and the boundary of the passable space in front of the vehicle at the two images is detected based on the angular laser radar.

[0015] The width of the passable space of the vehicle is calculated based on the distance difference between the two images, the oblique distance, and the width of the vehicle.

[0016] Optionally, in the step 2, it is determined that the road scene is a single-lane narrow road scene, and in the step 3, when it is determined based on the perception unit that there is a moving obstacle in front of the vehicle, the vehicle continues to move forward after the moving obstacle disappears.

[0017] Optionally, in the step 2, it is determined that the road scene is a single-lane narrow road scene, and in the step 3, when it is determined based on the perception unit that there is a stationary obstacle in front of the vehicle, the width of the passable space in front of the vehicle does not meet the passing requirement, and the vehicle is controlled to return to the original road or turn around according to the set priority.

[0018] Optionally, in the step 2, it is determined that the road scene is a double-lane narrow road scene, and in the step 3, when it is determined based on the perception unit that there is a moving obstacle coming from the opposite direction, the speed of the moving obstacle and the width of the passable space are monitored in real time, and the speed of the vehicle is reduced to a set value when the meeting distance is less than a set distance.

[0019] In the step 2, it is determined that the road scene is a double-lane narrow road scene, and in the step 3, when it is determined based on the perception unit that there is a stationary obstacle in front of the current lane, the opposite lane is determined to be a variable lane through the lane line identified by the perception unit, and it is determined that there is no obstacle in the opposite lane within a set range, and the vehicle returns to the original lane to continue driving after the tail ultrasonic radar fails to detect the obstacle after crossing the middle guide line.

[0020] Optionally, when it is judged in step 3 that the width of the passable space in front does not meet the passing requirement, it is judged whether the conditions for the vehicle to make a U-turn on a narrow road are met, and when the conditions are met, the vehicle is controlled to return along the original road or make a U-turn according to the priority setting;

[0021] The conditions for the vehicle to make a U-turn on a narrow road include that the current road width exceeds the vehicle length plus a set distance and there is no obstacle in the forward route;

[0022] The process of controlling the vehicle to make a U-turn includes repeatedly switching the driving direction of the vehicle when the vehicle judges that there is a collision risk.

[0023] According to a second aspect of the present application, a low-speed automatic piloting system is provided, comprising a perception unit and a low-speed piloting controller;

[0024] The perception unit comprises a camera, an ultrasonic radar and an angular laser radar, which are used to judge the road scene and the situation of the obstacle in front of the vehicle, and determine the width of the passable space in front of the vehicle excluding the static obstacle;

[0025] The low-speed piloting controller judges that the vehicle continues to move forward when the width of the passable space in front meets the passing requirement, and controls the vehicle to return along the original road or make a U-turn when the width of the passable space in front does not meet the passing requirement.

[0026] According to a third aspect of the present application, an electronic device is provided, comprising a memory and a processor, wherein the processor is configured to execute a computer management program stored in the memory to implement the steps of the low-speed automatic piloting method.

[0027] According to a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer management program, and the computer management program is executed by a processor to implement the steps of the low-speed automatic piloting method.

[0028] The low-speed automatic piloting method, system, electronic device and storage medium provided by the present application integrate the low-speed piloting function of the fusion of visual, ultrasonic and laser radar perception, which is used to pass through a narrow road in a low-speed scene to avoid vehicle or personnel casualties and losses. Different control strategies are made by identifying the road guide line to judge the current form scene, which increases the driving safety to a certain extent and effectively reduces the probability of collision when passing through a narrow road or making a U-turn in a low-speed scene. The function can also be used as a forward-looking function of high-level parking function (the parking process does not require the intervention of the driver), which plays a certain role in paving the way and inspiration for future high-level parking function. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 A flowchart of the low-speed automatic piloting method provided by the present application is provided;

[0030] Figure 2A schematic diagram of a one-way narrow road scene provided by an embodiment of the present application is shown.

[0031] Figure 3 A schematic diagram of a two-way narrow road scene provided by an embodiment of the present application is shown.

[0032] Figure 4 A schematic diagram of a one-way narrow road scene provided by an embodiment of the present application is shown.

[0033] Figure 5 A schematic diagram of a one-way narrow road scene provided by an embodiment of the present application is shown.

[0034] Figure 6 A structural block diagram of a low-speed automatic navigation system provided by the present application is shown.

[0035] Figure 7 A schematic diagram of a possible hardware structure of an electronic device provided by the present application is shown.

[0036] Figure 8 A schematic diagram of a possible hardware structure of a computer readable storage medium provided by the present application is shown. DETAILED DESCRIPTION

[0037] The principles and features of the present application are described below in conjunction with the accompanying drawings, which are only used to explain the present application and are not intended to limit the scope of the present application.

[0038] Figure 1 A flowchart of a low-speed automatic navigation method provided by the present application is shown. Figure 1 The automatic navigation method includes:

[0039] Step 1, setting a perception unit of the vehicle, the perception unit including: a camera, ultrasonic radars and corner laser radars.

[0040] In an embodiment provided by the present application, a low-speed navigation controller with 1 front camera, 12 ultrasonic radars and 4 corner laser radars as the perception unit is used to perceive narrow road conditions by using the camera and ultrasonic radar sensors to perceive elements, and to identify road guide lines, vehicles, pedestrians and road edges in narrow road conditions, so as to plan the vehicle route in advance.

[0041] Step 2, determining the road scene and the front obstacle situation of the vehicle based on the perception unit, and determining the width of the passable space in front of the vehicle after excluding static obstacles.

[0042] Step 3, when the width of the passable space in front of the vehicle meets the traffic demand based on the perception unit, the vehicle continues to move forward; when the width of the passable space in front of the vehicle does not meet the traffic demand, the vehicle is controlled to return or turn around.

[0043] Due to the hardware environment limitation of the current vehicle, few mass-produced vehicles are equipped with laser radar, so there is precision loss and error in identifying personnel, road edge, roadside parked vehicles and other obstacles at a long distance, especially for low obstacles such as road edge and ground lock, there is a large error in the existing visual and ultrasonic fusion scheme, which leads to the inability of the vehicle to judge whether the road width can be passed during automatic driving. In order to solve the above problems, in addition to the traditional visual and ultrasonic perception, laser radar must be assisted to judge the width between obstacles in advance on the route and then make route decision.

[0044] In order to assist the driver to safely pass or turn around in the narrow road scene (such as narrow door, two-way single lane, single lane, community road scene), prevent wheel loss and personnel injury loss caused by external complex environment, the low-speed automatic navigation method provided by the application combines visual perception guide line vehicle and traffic sign to identify the current scene traffic strategy and obstacle, and is assisted by ultrasonic radar perception to perform vehicle automatic cruise control. In the case where the rules allow, the user can choose to reverse or turn around. This function can also be used as an extension and forward-looking technology of high-level parking function. The narrow road navigation function is integrated into the high-level parking function, which can cope with more complex driving scenes.

[0045] Embodiment 1

[0046] The embodiment 1 provided by the application is an embodiment of the low-speed automatic navigation method provided by the application, which combines Figure 1 It can be seen that the embodiment of the automatic navigation method includes:

[0047] Step 1, setting the perception unit of the vehicle, the perception unit includes: camera, ultrasonic radar and angle laser radar.

[0048] After receiving the user's manual trigger instruction low-speed navigation function, steps 2-4 are executed.

[0049] After the low-speed navigation function is started, the low-speed navigation function is immediately exited when the user sends an exit instruction; the exit instruction includes any one of the following modes: stepping on the brake, intervening the gear and intervening the steering wheel.

[0050] The automatic navigation method provided by the application is suitable for narrow road environment with ground marking or road edge, the user can manually trigger the low-speed road navigation function when encountering a narrow road scene and the vehicle is stationary. After triggering the low-speed road navigation function, the vehicle automatically drives according to the driving road width and ground marking and avoids obstacles in advance according to the obstacle moving speed and distance, the user can exit the function by stepping on the brake, intervening the gear and the steering wheel, in addition, if a narrow dead-end road scene is encountered, the user can choose the turn around function to be controlled by the vehicle.

[0051] Step 2: Based on the perception unit, determine the road scene and obstacles in front of the vehicle, and determine the width of the passable space in front of the vehicle after removing stationary obstacles.

[0052] In one possible embodiment, the process of determining the width of the passable space in step 2 includes:

[0053] When a user activates the low-speed navigation function and passes through this narrow path, the vehicle must be stopped. At this time, the corner lidar detector scans the roadside and vehicles, taking the center point of the vehicle's rear axle as the origin of the coordinate system, and uses the camera to acquire at least two frames of images of the vehicle traveling at speed v.

[0054] The time interval between two frames of images is determined by the camera, and the distance difference between the two frames of images in the direction of vehicle travel is calculated based on the time interval and the vehicle speed. The diagonal distance between the vehicle and the boundary of the passable space ahead is obtained by the angular lidar detection.

[0055] The width of the passable space for the vehicle is calculated based on the distance difference between two frames, the diagonal distance, and the vehicle width.

[0056] Step 3: If the width of the passable space ahead meets the passage requirements based on the perception unit, the vehicle continues to move forward; if the width of the passable space ahead does not meet the passage requirements, the vehicle is controlled to return along the original route or turn around.

[0057] In one possible embodiment, in step 2, it is determined that the road scene is a single-lane narrow road scene. In step 3, when it is determined that there is a moving obstacle ahead based on the perception unit, the vehicle continues to move forward after the moving obstacle disappears.

[0058] In one possible embodiment, in step 2, it is determined that the road scene is a single-lane narrow road scene. In step 3, if it is determined by the perception unit that there is a stationary obstacle in front that makes the width of the passable space in front insufficient for passage, the vehicle is controlled to return or turn around according to the set priority.

[0059] like Figure 2 The diagram illustrates a one-way narrow road scenario according to an embodiment of the present invention. The single-lane narrow road scenario involves a single lane where stationary obstacles, such as vehicles, parked on the roadside occupy part of the road, leaving a narrow passageway. In practice, the system determines that the road ahead is passable and vehicles can pass normally. If moving obstacles, such as pedestrians or non-motorized vehicles, exist on the vehicle's path, the vehicle will wait for the obstacles to disappear before continuing. If obstacles consistently occupy the path, preventing the vehicle from moving forward, the vehicle will prompt the user to return to the starting point. Under conditional statements, where the LiDAR detects space for a U-turn on both sides of the road, the user can also choose to make a U-turn.

[0060] In a possible implementation, in step 2, it is determined that the road scene is a two-lane narrow road scene, and in step 3, when it is determined by the perception unit that there is a moving obstacle coming from the opposite direction, the speed of the moving obstacle and the width of the passable space are monitored in real time, and when the meeting distance is less than a set distance, the vehicle speed is reduced to a set value.

[0061] As shown in Figure 3 Fig. 1 is a schematic diagram of a two-way narrow road scene provided by an embodiment of the present application, in a specific implementation, when the two-lane narrow road scene exists in the meeting scene, the vehicle will monitor the speed of the oncoming vehicle and the route in real time under the condition that there is no obstacle in the front route, judge whether there is enough space to pass, and control the driving speed according to the distance of the oncoming vehicle, when the meeting distance of the two vehicles is less than ten meters, the vehicle speed is controlled to be 3kph.

[0062] As shown in Figure 4 Fig. 2 is a schematic diagram of a one-way narrow road scene provided by an embodiment of the present application, in a possible implementation, in step 2, it is determined that the road scene is a two-lane narrow road scene, and in step 3, when it is determined by the perception unit that there is a static obstacle in front of the current lane, the vehicle can perform obstacle avoidance processing, that is, after crossing the middle guide line, when the tail ultrasonic radar cannot detect the obstacle, the vehicle returns to the original lane and continues to drive, when the perception unit determines that the opposite lane is a variable lane and there is no obstacle in the set range.

[0063] In a possible implementation, in step 3, when it is determined that the width of the passable space in front does not meet the passing demand, it is determined whether the conditions for the vehicle to turn around on the narrow road are met, and when the conditions are met, the vehicle is controlled to return to the original road or turn around according to the priority setting.

[0064] The conditions for the vehicle to turn around on the narrow road include that the current road width exceeds the length of the vehicle plus a set distance, and there is no obstacle in the front route, in a specific implementation, the set distance can be 0.4 meters, and the passable width of the current road can be calculated by the laser radar.

[0065] As shown in Figure 5 Fig. 3 is a schematic diagram of a narrow road turn provided by an embodiment of the present application, the process of controlling the vehicle to turn around includes repeatedly switching the driving direction of the vehicle when the vehicle determines that there is a collision risk.

[0066] The vehicle controls the gear switching and driving direction switching of the vehicle according to the route between the front route and the target parking point. When the vehicle determines that there is a collision risk, the driving direction of the vehicle is repeatedly switched.

[0067] In an embodiment of the present application, the narrow road U-turn travel optimal route reference requirements are:

[0068] Ensure that the target parking point vehicle body posture and the initial vehicle body posture are 180 degrees;

[0069] Ensure that the number of gear shifting is less than 5 times;

[0070] According to the vehicle preset tracking path, the maximum distance is traveled under the condition of meeting the lateral corner control, that is, the vehicle can travel the maximum distance when switching the driving direction each time.

[0071] Embodiment 2

[0072] The embodiment 2 provided by the present application is an embodiment of a low-speed automatic navigation system provided by the present application, Figure 6 The structure diagram of the low-speed automatic navigation system provided for the embodiment of the present application, combined with Figure 1 Figure 6 It can be known that the embodiment of the automatic navigation system includes a perception unit and a low-speed navigation controller; at the same time, the GNSS / RTK is externally connected to provide the global position of the vehicle, which is used to determine the initial position of the vehicle, and the inertial navigation device IMU is used to provide acceleration and swing angle information.

[0073] The perception unit includes a camera, an ultrasonic radar and an angle laser radar, which are used to judge the road scene and the front obstacle condition of the vehicle, and determine the width of the passable space in front of the vehicle after excluding the static obstacles.

[0074] In an embodiment of the present application, one front camera, 12 ultrasonic radars and 4 angle laser radars are used as the low-speed navigation controller of the perception unit, and the vehicle-mounted central control is used for human-computer interaction, the camera and the ultrasonic radar sensor are used to perceive the narrow road condition perception elements, the road guide line, the vehicle, the pedestrian and the road edge and other perception elements in the narrow road condition can be recognized, so that the vehicle travel route is planned in advance, and the narrow road U-turn function is also provided, the driver starts the low-speed navigation function through the vehicle-mounted central control to pass through the narrow road.

[0075] When the low-speed navigation function is started, the low-speed navigation function is immediately exited when the exit instruction issued by the user is received; the exit instruction includes any one of the following modes: stepping on the brake, intervening the gear and intervening the steering wheel.

[0076] The automatic navigation method provided by the application is suitable for narrow road environment with ground marks or road edges, and the low-speed road navigation function can be manually triggered when the user encounters a narrow road scene and the vehicle is stationary. After triggering the low-speed road navigation function, the vehicle automatically travels according to the width of the driving road and the ground marks, and avoids obstacles in advance according to the moving speed and distance of the obstacles. The user can exit the function by pressing the brake, intervening the gear and the steering wheel, etc. In addition, if the user encounters a narrow dead-end road scene, the user can choose the U-turn function to control the vehicle to U-turn.

[0077] In a possible implementation manner, the process in which the perception unit determines the width of the passable space includes:

[0078] When the user starts the low-speed navigation function, the vehicle needs to be stopped to pass through the narrow path. At this time, the corner laser radar detects the road edge and the roadside vehicle for scanning. The center point of the rear axle of the vehicle is taken as the starting coordinate origin, and at least two frames of images of the vehicle traveling at a speed v are obtained based on the camera.

[0079] The time interval between the two frames of images is determined based on the camera, the distance difference in the traveling direction of the vehicle between the two frames of images is calculated based on the time interval and the speed of the vehicle, and the oblique distance between the vehicle and the boundary of the passable space in front of the vehicle at the two frames of images is obtained based on the corner laser radar detection.

[0080] The width of the passable space of the vehicle is calculated based on the distance difference between the two frames of images, the oblique distance and the width of the vehicle.

[0081] The low-speed navigation controller determines that the width of the passable space in front of the vehicle meets the passing requirement, and the vehicle continues to travel forward. When the width of the passable space in front of the vehicle does not meet the passing requirement, the low-speed navigation controller controls the vehicle to return along the original road or to U-turn.

[0082] In a possible implementation manner, the perception unit determines that the road scene is a single-lane narrow road scene, and the low-speed navigation controller controls the vehicle to continue to travel forward after the moving obstacle disappears when the perception unit determines that there is a moving obstacle in front of the vehicle.

[0083] In a possible implementation manner, the perception unit determines that the road scene is a single-lane narrow road scene, and the low-speed navigation controller controls the vehicle to return along the original road or to U-turn according to the set priority when the perception unit determines that there is a static obstacle in front of the vehicle, so that the width of the passable space in front of the vehicle does not meet the passing requirement.

[0084] The single-lane narrow road scene is a one-way lane, and the roadside parked static obstacles such as vehicles and the like occupy part of the road, leaving a part of the narrow path. In the specific implementation process, it is judged that the road scene in front is in a passable state, and the vehicle can pass normally. If there is a moving obstacle such as a pedestrian or a non-motor vehicle on the vehicle's route, the vehicle will wait for the obstacle to disappear and then continue. If the obstacle always occupies the route, the vehicle cannot continue to move forward, and the vehicle will prompt the user to return to the original route, that is, to return to the starting coordinate origin. In the conditional sequence, that is, when the laser radar detects that there is a U-turn space on both sides of the road, the user can also choose to turn around.

[0085] In a possible embodiment, the perception unit judges that the road scene is a double-lane narrow road scene, and the low-speed navigation controller monitors the speed of the moving obstacle and the width of the passable space in real time when the perception unit judges that there is a moving obstacle in the opposite direction in front. When the meeting distance is less than a set distance, the vehicle speed is reduced to a set value.

[0086] In the specific implementation, when the double-lane narrow road scene exists in the meeting scene, the vehicle will monitor the speed of the oncoming vehicle and the route in front of the vehicle in real time, judge whether there is enough space to pass, and control the driving speed according to the distance of the oncoming vehicle. When the meeting distance of the two vehicles is less than ten meters, the vehicle speed is controlled to be 3kph.

[0087] In a possible embodiment, the perception unit judges that the road scene is a double-lane narrow road scene, and the low-speed navigation controller judges that there is a static obstacle in front of the current lane based on the perception unit. When the perception unit identifies the lane line and judges that the opposite lane is a variable lane and that there is no obstacle in the opposite lane within a set range, the vehicle can perform obstacle avoidance processing, that is, after crossing the middle guide line, the vehicle returns to the original lane to continue driving when the tail ultrasonic radar cannot detect the obstacle. In the specific implementation process, the set range can be the detection range, for example, 100 meters.

[0088] In a possible embodiment, when the low-speed navigation controller judges that the width of the passable space in front does not meet the passing requirement, it judges whether the conditions for the vehicle to turn around in a narrow road are met. When the conditions are met, the vehicle is controlled to return to the original route or turn around according to the priority setting.

[0089] The conditions for the vehicle to turn around in a narrow road include that the current road width exceeds the vehicle length plus a set distance, and there is no obstacle in front of the route. In the specific implementation, the set distance can be 0.4 meters, and the passable width of the current road can be calculated by the laser radar.

[0090] The process of controlling the vehicle to turn around includes repeatedly switching the driving direction of the vehicle when the vehicle judges that there is a collision risk.

[0091] The vehicle controls the gear switching and the driving direction switching of the vehicle according to the route between the front route to the target parking point. When the vehicle judges that there is a collision risk, the driving direction of the vehicle is repeatedly switched.

[0092] In an embodiment of the present application, the narrow road U-turn traveling optimal route reference requirements are:

[0093] The target parking point vehicle body posture and the initial vehicle body posture are ensured to be 180°.

[0094] The number of gear switching is ensured to be less than 5 times.

[0095] According to the vehicle preset tracking path, the maximum distance is traveled under the condition of meeting the lateral corner control, that is, the vehicle can travel the maximum distance when the driving direction is switched each time.

[0096] Please refer to Figure 7 , Figure 7 The embodiment of the electronic device provided by the present application is shown in the figure. As shown in Figure 7 , the present application provides an electronic device, which comprises a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are realized: setting a perception unit of a vehicle, the perception unit comprising a camera, an ultrasonic radar, and an angular laser radar; determining the road scene and the front obstacle situation of the vehicle based on the perception unit, and determining the width of the passable space in front of the vehicle excluding static obstacles; when the width of the passable space in front of the vehicle meets the traffic demand based on the perception unit, the vehicle continues to move forward; when the width of the passable space in front of the vehicle does not meet the traffic demand, the vehicle is controlled to return along the original route or to make a U-turn.

[0097] Please refer to Figure 8 , Figure 8 The embodiment of the computer readable storage medium provided by the present application is shown in the figure. As shown in Figure 8 , the present embodiment provides a computer readable storage medium 1400, which stores a computer program 1411. When the computer program 1411 is executed by a processor, the following steps are realized: setting a perception unit of a vehicle, the perception unit comprising a camera, an ultrasonic radar, and an angular laser radar; determining the road scene and the front obstacle situation of the vehicle based on the perception unit, and determining the width of the passable space in front of the vehicle excluding static obstacles; when the width of the passable space in front of the vehicle meets the traffic demand based on the perception unit, the vehicle continues to move forward; when the width of the passable space in front of the vehicle does not meet the traffic demand, the vehicle is controlled to return along the original route or to make a U-turn.

[0098] The low-speed automatic navigation method and system, the electronic device and the storage medium provided by the embodiment of the present application can realize low-speed navigation function by fusing vision, ultrasonic wave and laser radar sensing, and can be used to pass through narrow roads in a low-speed scene to avoid vehicle or personnel casualties and losses. Different control strategies are made by identifying road guide lines to determine the current scene, which increases the driving safety to a certain extent, effectively reduces the probability of collision when passing through narrow roads or turning around in a low-speed scene, and the function can also be used as a forward-looking function of high-level parking function (the driver does not need to intervene in the parking process), and plays a certain role in paving the way and inspiration for future high-level parking function.

[0099] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0100] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0101] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus for performing the functions specified in one or more flows and / or blocks.

[0102] These computer program instructions can also be stored in a computer readable storage medium which can guide the computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable storage medium produce a product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus for performing the functions specified in one or more flows and / or blocks.

[0103] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0104] While the preferred embodiments of the application have been described, it should be apparent that a little thought and experimentation can lead to the development of other techniques and approaches that are widely equivalent to those described above. Accordingly, no limitation is intended to the scope of the protection granted to the application that can encompass all techniques and approaches comparable to those described and falling within the scope of the claims below and the scope of equivalents thereof.

[0105] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A low-speed automatic homing method, characterized by, The automatic navigation method comprises: Step 1, setting a perception unit of the vehicle, wherein the perception unit comprises a camera, an ultrasonic radar and an angular laser radar; Step 2, determining a road scene and a front obstacle condition of the vehicle based on the perception unit, and determining a width of a passable space in front of the vehicle excluding a stationary obstacle; Step 3, when the width of the passable space in front of the vehicle meets the passable requirement based on the perception unit, the vehicle continues to move forward; when the width of the passable space in front of the vehicle does not meet the passable requirement based on the perception unit, the vehicle is controlled to return along the original route or to turn around; The process of determining the width of the passable space in step 2 comprises: taking a center point of a rear axle of the vehicle as a starting coordinate origin, and acquiring at least two images of the vehicle moving at a speed v based on the camera; determining a time interval between the two images based on the camera, calculating a distance difference of a moving direction of the vehicle between the two images based on the time interval and the speed of the vehicle, and detecting a slant distance between the vehicle and a boundary of the passable space in front of the vehicle based on the angular laser radar; calculating the width of the passable space of the vehicle based on the distance difference, the slant distance and the width of the vehicle between the two images.

2. The automatic homing method according to claim 1, characterized in that, Before step 2, after receiving a manual triggering instruction of a user, the low-speed navigation function is executed from step 2 to step 4; After the low-speed navigation function is started, the low-speed navigation function is exited immediately when a user sends an exit instruction; the exit instruction comprises any one of the following: stepping on a brake, interfering with a gear position and interfering with a steering wheel.

3. The automatic homing method of claim 1, wherein In step 2, when the road scene is determined to be a single-lane narrow road scene, and when a moving obstacle exists in front of the vehicle based on the perception unit in step 3, the vehicle continues to move forward after the moving obstacle disappears.

4. The automatic homing method of claim 1, wherein In step 2, when the road scene is determined to be a single-lane narrow road scene, and when a stationary obstacle exists in front of the vehicle based on the perception unit in step 3, the width of the passable space in front of the vehicle does not meet the passable requirement, and the vehicle is controlled to return along the original route or to turn around according to a priority setting.

5. The automatic homing method of claim 1, wherein In step 2, when the road scene is determined to be a double-lane narrow road scene, and when a moving obstacle exists in front of the vehicle based on the perception unit in step 3, the speed of the moving obstacle and the width of the passable space are monitored in real time, and the vehicle speed is reduced to a set value when a meeting distance is less than a set distance. In step 2, when the road scene is determined to be a double-lane narrow road scene, and when a stationary obstacle exists in front of the current lane based on the perception unit in step 3, the opposite lane is determined to be a variable lane based on the perception unit, and when the opposite lane does not exist within a set range, the vehicle crosses an intermediate guide line and returns to the original lane to continue driving after the rear ultrasonic radar detects no obstacle.

6. The automatic homing method of claim 1, wherein In step 3, when the width of the passable space in front of the vehicle does not meet the passable requirement, it is determined whether a condition for the vehicle to turn around on a narrow road is met, and the vehicle is controlled to return along the original route or to turn around according to a priority setting when the condition is met; The condition for the vehicle to turn around on the narrow road comprises that the current road width exceeds the length of the vehicle plus a set distance, and there is no obstacle in the front route. The process of controlling the vehicle to make a U-turn comprises repeatedly switching the driving direction of the vehicle when the vehicle determines that there is a risk of collision.

7. A low-speed automatic homing system characterized by The automatic navigation system comprises a perception unit and a low-speed navigation controller. The perception unit comprises a camera, an ultrasonic radar and an angular laser radar, which are used to determine the road scene and the situation of the front obstacle of the vehicle, and determine the width of the passable space in front of the vehicle excluding the static obstacle. The low-speed navigation controller determines that the vehicle continues to move forward when the width of the passable space in front of the vehicle meets the passable requirement, and controls the vehicle to return or make a U-turn when the width of the passable space in front of the vehicle does not meet the passable requirement. The process of determining the width of the passable space by the perception unit comprises: taking the center point of the rear axle of the vehicle as the starting coordinate origin, and obtaining at least two images of the vehicle moving at a speed v based on the camera; determining the time interval between the two images based on the camera, calculating the distance difference of the moving direction of the vehicle between the two images based on the time interval and the speed of the vehicle, and detecting the oblique distance between the vehicle and the boundary of the passable space in front of the vehicle at the two images based on the angular laser radar; calculating the width of the passable space of the vehicle based on the distance difference, the oblique distance and the width of the vehicle between the two images.

8. An electronic device, comprising: A computer device comprising a memory and a processor, wherein the processor is configured to execute a computer management program stored in the memory to implement the steps of the low-speed automatic navigation method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, A computer program product, wherein the computer program product stores a computer management program, and the computer management program is configured to be executed by a processor to implement the steps of the low-speed automatic navigation method according to any one of claims 1-6.

Images