Obstacle crossing methods, devices, unmanned vehicles, and storage media for autonomous vehicles

Abstract

This application relates to the field of autonomous driving technology, providing an obstacle-avoidance method, apparatus, autonomous vehicle, and storage medium for an unmanned vehicle. The method includes: when a static obstacle is detected, acquiring obstacle information of the static obstacle; if the obstacle information satisfies the obstacle-avoidance conditions corresponding to a target obstacle-avoidance strategy, acquiring target driving parameters corresponding to the target obstacle-avoidance strategy; and controlling the unmanned vehicle to drive towards the static obstacle based on the target driving parameters. Using this method, the unmanned vehicle can avoid replanning its obstacle avoidance path when facing static obstacles, and can also overcome static obstacles, reducing the time spent by the unmanned vehicle during obstacle avoidance.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to an obstacle crossing method, device, autonomous vehicle and storage medium for an unmanned vehicle. Background Technology

[0002] With the continuous development of autonomous driving technology, driverless vehicles based on this technology have been widely used in warehouse logistics, public transportation, and smart car models. Among these applications, obstacle avoidance is a crucial branch of autonomous driving technology.

[0003] When encountering obstacles, traditional autonomous vehicles typically plan a safe and drivable obstacle avoidance path based on the obstacle's location. However, planning and navigating around obstacles using this path usually takes a significant amount of time. Summary of the Invention

[0004] This application provides an obstacle avoidance method, device, unmanned vehicle, and storage medium for an unmanned vehicle, which can solve the problem that traditional unmanned vehicles need to spend a lot of time when avoiding obstacles.

[0005] In a first aspect, embodiments of this application provide an obstacle-crossing method for an unmanned vehicle, the method comprising:

[0006] When a static obstacle is detected, obtain the obstacle information of the static obstacle;

[0007] If the obstacle information meets the obstacle crossing conditions corresponding to the target obstacle crossing strategy, then obtain the target driving parameters corresponding to the target obstacle crossing strategy.

[0008] The autonomous vehicle is controlled to drive toward a static obstacle based on target driving parameters.

[0009] Secondly, embodiments of this application provide an obstacle-crossing device for an unmanned vehicle, the device comprising:

[0010] The obstacle information acquisition module is used to acquire obstacle information of static obstacles when they are detected.

[0011] The target driving parameter acquisition module is used to acquire the target driving parameters corresponding to the target obstacle crossing strategy if the obstacle information meets the obstacle crossing conditions corresponding to the target obstacle crossing strategy.

[0012] The control module is used to control the unmanned vehicle to move toward static obstacles based on target driving parameters.

[0013] Thirdly, embodiments of this application provide an unmanned vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in the first aspect above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0015] Fifthly, embodiments of this application provide a computer program product that, when run on an unmanned vehicle, causes the unmanned vehicle to execute the method described in the first aspect.

[0016] The beneficial effects of this application's embodiments compared to existing technologies are as follows: When the autonomous vehicle detects a static obstacle, it acquires the obstacle information of the static obstacle; then, it compares the obstacle information with the obstacle-crossing conditions of the obstacle-crossing strategy to determine the target obstacle-crossing strategy that meets the obstacle-crossing conditions, as well as the target driving parameters corresponding to the target obstacle-crossing strategy. Subsequently, the autonomous vehicle travels towards the static obstacle using the target driving parameters. In this way, when facing a static obstacle, the autonomous vehicle does not need to replan its obstacle avoidance path and can still pass through the static obstacle, thereby reducing the time spent by the autonomous vehicle in the entire obstacle avoidance process. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the implementation of an obstacle-crossing method for an unmanned vehicle according to an embodiment of this application.

[0019] Figure 2 This is a schematic diagram illustrating one implementation method for obtaining static obstacle information in an obstacle-crossing method for an unmanned vehicle provided in an embodiment of this application;

[0020] Figure 3 This is a schematic diagram illustrating an application scenario in which an unmanned vehicle acquires obstacle information of static obstacles in one embodiment of this application;

[0021] Figure 4 This is a schematic diagram illustrating one implementation method of adjusting the current driving parameters to the target driving parameters in an obstacle-crossing method for an unmanned vehicle provided in an embodiment of this application;

[0022] Figure 5 This is a schematic diagram illustrating one implementation method of adjusting the vehicle height in an obstacle-crossing method for an unmanned vehicle provided in an embodiment of this application;

[0023] Figure 6 This is a schematic diagram of the structure of an obstacle-crossing device for an unmanned vehicle provided in one embodiment of this application;

[0024] Figure 7 This is a schematic diagram of the structure of an unmanned vehicle provided in one embodiment of this application. Detailed Implementation

[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0026] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0027] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] The obstacle-crossing method for unmanned vehicles provided in this application is executed by an obstacle-crossing device of the unmanned vehicle, which can be installed inside the unmanned vehicle. The unmanned vehicle includes, but is not limited to, warehouse logistics vehicles or intelligent vehicle models; this application does not impose any restrictions on the specific type of unmanned vehicle.

[0029] Taking an autonomous vehicle as an example, the intelligent vehicle model includes wheels and a body whose height is adjusted relative to the ground via a height adjustment device. The body may include multiple near-infrared sensors, respectively located at the front and rear of the intelligent vehicle model, for collecting distances or other parameters between the intelligent vehicle model and obstacles; a polymer battery with a capacity of 1100 mAh is used to power the various modules. Audio equipment may include a voice-sensing touchpad, a speaker, and sound outlets for voice services, such as voice wake-up. Communication equipment may be a 4G or 5G communication module, etc. This communication equipment is used to communicate with the voice recognition module, wheel drive module, or other modules to transmit voice or control commands. Lighting drive equipment may include headlights, taillights, etc. Sensors may include, but are not limited to, image acquisition sensors or radar sensors. When the sensor is an image acquisition sensor, it may include a 3-megapixel camera and supplementary lighting for collecting obstacle information. The display screen can be used to display vehicle parameters, obstacle information, or control information from smart home devices. The charging port is used to charge the polymer battery. It can be an Android charging port or a Universal Serial Bus (USB) hardware interface (TYPE-C) charging port; there is no limitation on the type.

[0030] Among these, smart car models, typically used in home environments, can not only interact intelligently with vehicles through IoT functions to control them, but also interact with smart home devices to control their operation. Generally, smart car models need to pre-plan their routes and then drive along those planned paths to control smart home devices in different locations.

[0031] The aforementioned path planning includes: modeling the home environment and generating a home map. For example, while driving through the home environment, the smart car model performs steps such as environmental data collection, data processing, and environmental enhancement to generate a home map. Furthermore, during the journey, it extracts object information. For example, it extracts device information of controllable smart home devices, or object information of other objects.

[0032] Furthermore, during subsequent control tasks, the autonomous vehicle can avoid obstacles according to pre-set obstacle-handling methods to reach the designated location and control the corresponding smart home devices. This handling method typically involves generating an obstacle avoidance path to navigate around the obstacles. However, generating and navigating this path usually takes a significant amount of time.

[0033] Based on this, in order to improve the driving efficiency of unmanned vehicles, this embodiment provides an obstacle crossing method for unmanned vehicles, enabling unmanned vehicles to choose to directly cross obstacles when facing them.

[0034] Please see Figure 1 , Figure 1 The following is a flowchart illustrating the implementation of an obstacle-crossing method for an unmanned vehicle according to an embodiment of this application. The method includes the following steps:

[0035] S201. When a static obstacle is detected, the obstacle-crossing device of the unmanned vehicle obtains the obstacle information of the static obstacle.

[0036] In one embodiment, obstacles can generally be divided into static obstacles or dynamic obstacles. Dynamic obstacles include, but are not limited to, moving objects such as animals and people. Therefore, when a dynamic obstacle is detected, a prompt message can be issued to remind people or urge animals to leave.

[0037] Understandably, if the dynamic obstacle has been cleared, you can proceed directly along the originally planned path. If the dynamic obstacle remains, you need to replan your obstacle avoidance route; for example, plan a new route from the left, right, or rear of the dynamic obstacle.

[0038] In one embodiment, static obstacles include, but are not limited to, non-movable obstacles such as tables and chairs. The autonomous vehicle can be equipped with image acquisition sensors to capture images containing the obstacles. Furthermore, the obstacle-crossing device of the autonomous vehicle also includes a recognition model for identifying obstacle images. This recognition model processes the acquired obstacle images to output the obstacle's category. Specifically, it outputs either the category of a static obstacle or a dynamic obstacle.

[0039] In one embodiment, the obstacle information includes, but is not limited to, the slope angle and / or height of static obstacles. The slope angle is the angle between the slope of the static obstacle facing the autonomous vehicle and the horizontal ground; the height is the distance between the apex of the static obstacle and the horizontal ground. The obstacle-crossing device of the autonomous vehicle can acquire the obstacle information through installed radar sensors.

[0040] Specifically, in this embodiment, referring to Figure 2 The obstacle-crossing device of the unmanned vehicle can calculate the height and / or slope angle of a static obstacle using the following steps S301-S305. Details are as follows:

[0041] S301. The obstacle-crossing device of the unmanned vehicle determines the apex and apex of a static obstacle through sensors; the apex refers to the point where the static obstacle contacts the ground, and the sensor, apex, and apex are in the same vertical plane.

[0042] In one embodiment, the aforementioned sensor has already been explained above and will not be described again.

[0043] In one embodiment, the vertex is one of the highest points of the static obstacle; the base point is one of the points where the static obstacle contacts the ground. In this embodiment, the vertex, base point, and sensor must all be in the same vertical plane. For example, the static obstacle may be a cube, where the vertex on the side facing the autonomous vehicle is a point on the upper horizontal line of that side; the base point is typically a point on the lower horizontal line of that side.

[0044] It should be noted that if the sensor, the vertex, and the datum are not in the same vertical plane, the slope angle calculated between the line segment connecting the vertex and the datum and the horizontal ground may be inaccurate. Therefore, to improve the accuracy of the calculated slope angle, the vertex and datum points must be in the same vertical plane as the sensor.

[0045] S302, the obstacle-crossing device of the unmanned vehicle respectively obtains the first distance between the sensor and the vertex, the second distance between the sensor and the bottom point, and the third distance between the sensor and the ground.

[0046] In one embodiment, because the sensor has a ranging function, the obstacle-crossing device of the autonomous vehicle can directly obtain the first distance between the sensor and the vertex, and the second distance between the sensor and the base point. The third distance between the sensor and the ground can also be collected by the sensor. However, this third distance is usually fixed; therefore, the obstacle-crossing device of the autonomous vehicle only needs to collect the third distance once through the sensor. Then, the third distance is stored.

[0047] Specifically, refer to Figure 3 , Figure 3 This is a schematic diagram illustrating an application scenario in which an obstacle-crossing device of an unmanned vehicle acquires obstacle information of static obstacles in one embodiment of this application. Figure 3 Point A is the vertex of the static obstacle, and point B is the bottom point of the static obstacle; the camera is the imaging device in the image acquisition sensor, so the location of the camera can be considered as the location of the sensor; S1 is the first distance between the sensor and the vertex; S2 is the second distance between the sensor and the bottom point; H is the third distance between the sensor and the ground.

[0048] When the static obstacle information only includes the height of the static obstacle, execute S303, and the obstacle-crossing device of the unmanned vehicle calculates the height of the static obstacle based on the first distance and the third distance.

[0049] In one embodiment, when calculating the height of a static obstacle based on a first distance and a third distance, it is also necessary to determine a first angle between the first straight line containing the sensor and the vertex and the vertical direction; then, the height is calculated based on the first angle, the first distance, and the third distance. The vertical direction can be considered as... Figure 3 The dashed line represented by H. Specifically, the first included angle mentioned above is the angle θ1 between the straight line represented by S1 and the dashed line represented by H.

[0050] It should be noted that when determining the position of the vertex, the obstacle-crossing device of the aforementioned unmanned vehicle can determine the angle between the first straight line and the vertical direction by adjusting the rotation angle of the camera. That is, the obstacle-crossing device of the unmanned vehicle can determine the first angle when determining the vertex, and there is no limitation on this.

[0051] In one specific embodiment, the obstacle-crossing device of the unmanned vehicle can incorporate the first included angle, the first distance, and the third distance into the height calculation formula to obtain the height; wherein, the height calculation formula can be:

[0052] h = H - S1·cosθ1;

[0053] Where h is the height, H is the third distance, S1 is the first distance, and θ1 is the first included angle.

[0054] When the static obstacle information only includes the slope angle of the static obstacle, execute S304. The obstacle crossing device of the unmanned vehicle calculates the slope angle of the slope where the bottom point and the top point are located based on the first distance, the second distance, the third distance and the height.

[0055] In one embodiment, when calculating the slope angle, the obstacle-crossing device of the autonomous vehicle also needs to determine the second angle between the second straight line where the sensor and the bottom point are located and the vertical direction. Then, the obstacle-crossing device can import the first angle, the second angle, the first distance, the second distance, the third distance, and the height into the slope angle calculation formula to obtain the slope angle. Specifically, the slope angle calculation formula is as follows:

[0056]

[0057] Where θ3 is the slope angle, H is the third distance, h is the height, S1 is the first distance, θ1 is the first included angle, S2 is the second distance, and θ2 is the second included angle.

[0058] The method for obtaining the second included angle is similar to that for obtaining the first included angle, and will not be explained further.

[0059] It should be noted that the obstacle information mentioned above can be one type or multiple types, and there is no limitation on this. That is, in this embodiment, the obstacle information used may only include the height or slope angle of static obstacles, or it may include both height and slope angle.

[0060] When the static obstacle information includes the height and slope angle of the static obstacle, S305 is executed: the obstacle-crossing device of the unmanned vehicle calculates the height of the static obstacle based on the first distance and the third distance; and calculates the slope angle of the slope where the bottom point and the top point are located based on the first distance, the second distance, the third distance and the height.

[0061] The calculation methods for height and slope angle have been explained above and will not be repeated here.

[0062] Understandably, obstacle information can be calculated based solely on parameters such as the first distance, second distance, third distance, first angle, and second angle, all of which can be acquired through sensors, making the parameter acquisition method simple. Furthermore, when calculating based on these parameters, it is only necessary to input them into the aforementioned formula, making it more convenient for the obstacle-crossing device of the autonomous vehicle to acquire obstacle information.

[0063] S202. If the obstacle information meets the obstacle crossing conditions corresponding to the target obstacle crossing strategy, the obstacle crossing device of the unmanned vehicle obtains the target driving parameters corresponding to the target obstacle crossing strategy.

[0064] In one embodiment, the obstacle-crossing strategy stored internally in the obstacle-crossing device of the autonomous vehicle may include one or more strategies, without limitation. For example, the obstacle-crossing strategy may include a hill-climbing strategy and / or an obstacle-crossing strategy. It should be noted that each obstacle-crossing strategy corresponds to an obstacle-crossing condition. The target obstacle-crossing strategy is the obstacle-crossing strategy corresponding to the obstacle-crossing condition satisfied by the obstacle information among the multiple obstacle-crossing strategies.

[0065] In this process, after determining the target obstacle-crossing strategy, the obstacle-crossing device of the autonomous vehicle can travel towards the static obstacle according to the target driving parameters corresponding to the target obstacle-crossing strategy, thereby crossing the static obstacle. That is, the target driving parameters are the parameters that enable the obstacle-crossing device of the autonomous vehicle to cross the static obstacle. These parameters can be preset. In other words, the obstacle-crossing device of the autonomous vehicle stores the target driving parameters corresponding to each target obstacle-crossing strategy in advance.

[0066] For example, for a hill-climbing strategy, the corresponding obstacle-crossing condition can be: whether the slope angle of the static obstacle is less than a preset angle. If it is less, then the obstacle information is determined to meet the obstacle-crossing condition corresponding to the hill-climbing strategy. In this case, the obstacle information is the slope angle of the static obstacle.

[0067] Alternatively, if the height is less than the height of the autonomous vehicle's wheels, then the obstacle information is determined to meet the obstacle-crossing conditions corresponding to the obstacle-crossing strategy. In this case, the obstacle information is the height of the static obstacle. It can be understood that if the height is less than the height of the autonomous vehicle's wheels, it means that the autonomous vehicle can drive directly over the top of the static obstacle.

[0068] The preset angle can be set according to actual conditions; for example, the preset angle can be greater than 90°. It is understandable that when the preset angle is greater than 90°, the autonomous vehicle will be affected by gravity during operation and will fall to the ground.

[0069] It should be added that if the height of the autonomous vehicle's wheels is greater than the height of the static obstacle, the obstacle-crossing device of the autonomous vehicle does not need to consider a climbing strategy, that is, it does not need to consider the slope angle of the static obstacle. Typically, when the wheel height is greater than the obstacle height, the autonomous vehicle can directly climb over the static obstacle. The wheel height of the autonomous vehicle can be set to a value corresponding to the diameter of the wheel, a value corresponding to the radius of the wheel, or other settings depending on actual conditions; there are no restrictions on this.

[0070] It should also be added that if the acquired obstacle information includes both the height and slope angle of the static obstacle, and the slope angle satisfies the obstacle crossing conditions corresponding to the above-mentioned climbing strategy, and the height satisfies the obstacle crossing conditions corresponding to the obstacle crossing strategy, then the obstacle crossing device of the unmanned vehicle can only determine the climbing strategy as the target obstacle crossing strategy.

[0071] It's understandable that when the height of a static obstacle is less than the height of the autonomous vehicle's wheels, the vehicle can be assumed to be able to pass directly over the top of the obstacle. Therefore, we only need to consider the speed required for the autonomous vehicle to cross the static obstacle. However, for hill-climbing strategies, different slope angles typically require different speeds for the autonomous vehicle to climb the static obstacle.

[0072] It should be added that if the obstacle information does not meet the obstacle-crossing conditions corresponding to the target obstacle-crossing strategy, it means that the autonomous vehicle cannot cross the static obstacle. Therefore, the obstacle-crossing device of the autonomous vehicle can replan the obstacle avoidance route based on the static obstacle information.

[0073] Based on this, by using the climbing strategy and obstacle crossing strategy set according to the slope angle and / or height respectively, the obstacle crossing device of the unmanned vehicle can reasonably select the obstacle crossing strategy according to the obstacle information of the static obstacle when facing a static obstacle, without spending a lot of time replanning the obstacle avoidance route.

[0074] S203, The obstacle-crossing device of the unmanned vehicle controls the unmanned vehicle to drive toward a static obstacle based on the target driving parameters.

[0075] In one embodiment, as explained in S202 above, the target driving parameters are the parameters that enable the autonomous vehicle to overcome static obstacles. Therefore, the autonomous vehicle can directly overcome static obstacles based on the target driving parameters without spending a lot of time avoiding them.

[0076] In this embodiment, when the autonomous vehicle detects a static obstacle, it acquires the obstacle information of the static obstacle. Then, it compares the obstacle information with the obstacle-avoidance conditions of the obstacle-avoidance strategy to determine the target obstacle-avoidance strategy that meets the conditions, as well as the target driving parameters corresponding to the target obstacle-avoidance strategy. The autonomous vehicle then travels towards the static obstacle using the target driving parameters. In this way, when facing a static obstacle, the autonomous vehicle does not need to replan its obstacle avoidance path and can pass through the static obstacle, thereby reducing the time spent by the autonomous vehicle in the entire obstacle avoidance process.

[0077] In one specific embodiment, the target driving parameter may specifically be the target vehicle speed, as shown in the reference... Figure 4 The obstacle-crossing device of the unmanned vehicle can adjust the vehicle's current driving parameters to the target driving parameters corresponding to the target obstacle through S501-S504. Details are as follows:

[0078] S501, The obstacle crossing device of the unmanned vehicle obtains the fourth distance between the unmanned vehicle and the static obstacle.

[0079] In one embodiment, the fourth distance is the horizontal distance between the autonomous vehicle and a static obstacle. Specifically, when identifying the type of obstacle to execute steps S201-S203, the autonomous vehicle can first use a near-infrared sensor located at the front of the vehicle to travel to a position at a distance of the fourth distance from the obstacle. Then, the obstacle-crossing device of the autonomous vehicle executes steps S201-S203. At this time, the value of the fourth distance can be set according to the actual situation, and this value is a fixed value. Alternatively, during the autonomous vehicle's operation, the obstacle-crossing device identifies obstacles on the path. Then, when the obstacle is detected as a static obstacle, steps S201-S202 are executed first. Afterwards, when executing the above steps, the distance between the autonomous vehicle and the static obstacle is determined as the fourth distance. In this case, the fourth distance is not a fixed value.

[0080] S502, The obstacle crossing device of the unmanned vehicle determines the maximum speed of the unmanned vehicle when it travels to a static obstacle based on the fourth distance and the preset acceleration range of the unmanned vehicle.

[0081] In one embodiment, the aforementioned preset acceleration range can be determined in advance. Typically, for intelligent vehicle models, their driving speed is not high; therefore, the maximum acceleration required is usually relatively small. Furthermore, the preset acceleration range of the autonomous vehicle can also be determined in advance at the factory.

[0082] In one embodiment, the maximum speed is the maximum speed of the unmanned vehicle when it travels to a static obstacle, which can be calculated by the obstacle-crossing device of the unmanned vehicle based on the current speed, maximum acceleration, and fourth distance.

[0083] It should be noted that the maximum speed should be less than or equal to the maximum actual speed at which the autonomous vehicle can travel. That is, if the maximum actual speed of the autonomous vehicle is Vmax, then the maximum speed should be less than Vmax.

[0084] S503. If the maximum vehicle speed is greater than or equal to the target vehicle speed, the obstacle crossing device of the unmanned vehicle will adjust the current vehicle speed of the unmanned vehicle to the target vehicle speed according to the fourth distance and the preset acceleration range.

[0085] Understandably, if the maximum speed is greater than or equal to the target speed, it indicates that the autonomous vehicle can adjust its current speed to the corresponding target speed before reaching a static obstacle. During this adjustment process, the autonomous vehicle's obstacle-crossing device can select an appropriate acceleration from a preset angular velocity range based on the current speed and the fourth distance, allowing the autonomous vehicle to accelerate reasonably. Alternatively, it can adjust the current speed based on the maximum acceleration and maintain the target speed once it is reached, reducing the time required for the autonomous vehicle to cross the static obstacle.

[0086] Understandably, if the current speed is greater than the target speed, there is no need to adjust the current speed.

[0087] S504. If the maximum vehicle speed is less than the target vehicle speed, the obstacle crossing device of the unmanned vehicle adjusts the fourth distance between the unmanned vehicle and the static obstacle according to the fourth distance and the preset acceleration range, and determines the target vehicle speed according to the adjusted fourth distance.

[0088] In one embodiment, if the autonomous vehicle cannot adjust its current speed to the target speed even with maximum acceleration, it can use its obstacle-crossing device to calculate the distance the vehicle needs to travel from zero speed to the target speed using maximum acceleration, based on the maximum acceleration and the target speed. This distance is then determined as the adjusted fourth distance. For example, the autonomous vehicle moves backward by the corresponding distance.

[0089] Specifically, when adjusting the current vehicle speed to the target speed based on the adjusted fourth distance, the current vehicle speed should be zero. That is, after the autonomous vehicle moves backward a certain distance, it has no initial forward speed. Therefore, when the autonomous vehicle is at the adjusted fourth distance, its current speed is 0.

[0090] It's worth noting that after calculating the adjusted fourth distance, the autonomous vehicle's obstacle-crossing device can first determine whether the adjusted fourth distance exceeds the preset driving distance. If it does, the device can choose to generate an obstacle avoidance route to bypass the static obstacle. That is, after calculating the adjusted fourth distance, the sum of the time it takes for the autonomous vehicle to reverse to the adjusted fourth distance and the time required to travel within that distance and cross the static obstacle may exceed the time required for the vehicle to generate and travel along the obstacle avoidance route. Based on this, the obstacle-crossing device can rationally choose whether to attempt obstacle crossing or avoidance based on the comparison between the adjusted fourth distance and the preset driving distance, thereby reducing the time required for the autonomous vehicle to travel.

[0091] In one embodiment, when the autonomous vehicle is traveling toward a static obstacle based on target driving parameters, the vehicle body may collide with the static obstacle, making it impossible for the autonomous vehicle to pass the obstacle.

[0092] Therefore, in this embodiment, the vehicle body can be configured as an adjustable body, meaning the height of the vehicle body relative to the ground is adjustable. (Refer to...) Figure 5 The obstacle-crossing device of the autonomous vehicle can adjust the vehicle height via S601-S603 as follows. Details are as follows:

[0093] S601. During the operation of the unmanned vehicle, the obstacle-crossing device of the unmanned vehicle collects the shortest distance between the vehicle body and static obstacles.

[0094] S602. If the shortest distance is greater than the preset distance threshold, the obstacle crossing device of the unmanned vehicle will control the vehicle height to remain unchanged.

[0095] S603. If the shortest distance is less than or equal to a preset distance threshold, the obstacle-crossing device of the unmanned vehicle adjusts the vehicle height so that the shortest distance is greater than the preset distance threshold.

[0096] In one embodiment, the obstacle-crossing device of the aforementioned unmanned vehicle can acquire the distance between the vehicle body and static obstacles using near-infrared sensors. Multiple near-infrared sensors can be configured to acquire multiple distances, and then the shortest distance with the smallest value is determined from these multiple distances.

[0097] It is understandable that if the shortest distance is greater than a preset distance threshold, then it can be assumed that other parts of the vehicle body will also be greater than the preset distance threshold. That is, the obstacle-crossing device of the autonomous vehicle can adjust the vehicle height only based on the determination result of the shortest distance and the preset distance threshold, and when the shortest distance is greater than the preset distance threshold, it can be assumed that the autonomous vehicle body will not collide with the static obstacle when crossing it, thus affecting the obstacle-crossing process of the autonomous vehicle.

[0098] It should be noted that because the surface (usually a slope) where the static obstacle contacts the autonomous vehicle may be irregular, the vehicle may collide with the static obstacle when crossing it. For details, please refer to... Figure 3 The surface of a static obstacle.

[0099] Therefore, if the shortest distance is less than or equal to a preset distance threshold, it indicates that the vehicle may collide with a static obstacle during operation. Thus, the vehicle height needs to be adjusted to ensure the shortest distance exceeds the preset distance threshold. Conversely, if the shortest distance exceeds the preset distance threshold, it indicates that the autonomous vehicle's obstacle-crossing device does not require height adjustment, and the vehicle height can be kept constant.

[0100] The aforementioned preset distance threshold can be set according to actual conditions. It is understood that because the surface of static obstacles is irregular, the autonomous vehicle may vibrate when crossing them, causing the vehicle body, which was not initially in contact with the obstacle, to collide with it. Therefore, setting a preset distance threshold can prevent this from happening and ensure the safe operation of the autonomous vehicle.

[0101] Please see Figure 6 , Figure 6 This is a structural block diagram of an obstacle-crossing device for an unmanned vehicle provided in an embodiment of this application. The obstacle-crossing device for the unmanned vehicle in this embodiment includes modules for performing... Figure 1 , Figure 2 , Figure 4 and Figure 5 The steps in the corresponding embodiments. Please refer to the details. Figure 1 , Figure 2 , Figure 4 and Figure 5 as well as Figure 1 , Figure 2 , Figure 4 and Figure 5 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. See also... Figure 6 The obstacle-crossing device 700 of the unmanned vehicle may include: an obstacle information acquisition module 710, a target driving parameter module 720, and a control module 730, wherein:

[0102] The obstacle information acquisition module 710 is used to acquire obstacle information of a static obstacle when a static obstacle is detected.

[0103] The target driving parameter acquisition module 720 is used to acquire the target driving parameters corresponding to the target obstacle crossing strategy if the obstacle information meets the obstacle crossing conditions corresponding to the target obstacle crossing strategy.

[0104] The control module 730 is used to control the unmanned vehicle to drive toward a static obstacle based on the target driving parameters.

[0105] In one embodiment, the obstacle information includes slope angle and / or height, and the obstacle information acquisition module 710 is further configured to:

[0106] The vertex and apex of a static obstacle are determined using sensors; the apex is the point where the static obstacle contacts the ground, and the sensor, vertex, and apex are in the same vertical plane; the first distance between the sensor and the vertex, the second distance between the sensor and the apex, and the third distance between the sensor and the ground are obtained respectively; the height of the static obstacle is calculated based on the first and third distances; and / or, the slope angle of the slope where the apex and apex are located is calculated based on the first, second, and third distances and the height.

[0107] In one embodiment, the obstacle information acquisition module 710 is further configured to:

[0108] Determine the first angle between the first straight line containing the sensor and the vertex and the vertical direction; import the first angle, the first distance, and the third distance into the height calculation formula to obtain the height; the height calculation formula is:

[0109] h = H - S1·cosθ1;

[0110] Where h is the height, H is the third distance, S1 is the first distance, and θ1 is the first included angle.

[0111] In one embodiment, the obstacle information acquisition module 710 is further configured to:

[0112] Determine the first angle between the sensor and the vertex on the first straight line and the vertical direction; determine the second angle between the sensor and the base on the second straight line and the vertical direction; import the first angle, the second angle, the first distance, the second distance, the third distance, and the height into the slope angle calculation formula to obtain the slope angle; the slope angle calculation formula is:

[0113]

[0114] Where θ3 is the slope angle, H is the third distance, h is the height, S1 is the first distance, θ1 is the first included angle, S2 is the second distance, and θ2 is the second included angle.

[0115] In one embodiment, the target obstacle-crossing strategy includes a hill-climbing strategy and / or an obstacle-crossing strategy; the obstacle-crossing device 700 of the unmanned vehicle further includes:

[0116] The obstacle crossing condition determination module is used to determine whether the obstacle information meets the obstacle crossing condition corresponding to the climbing strategy if the slope angle is less than or equal to a preset angle; or, if the height is less than the wheel height of the unmanned vehicle, to determine whether the obstacle information meets the obstacle crossing condition corresponding to the obstacle crossing strategy.

[0117] The target obstacle crossing strategy determination module is used to determine the climbing strategy as the target obstacle crossing strategy if the obstacle information satisfies both the obstacle crossing conditions corresponding to the climbing strategy and the obstacle crossing conditions corresponding to the obstacle crossing strategy.

[0118] In one embodiment, the target driving parameters include the target vehicle speed; the obstacle-crossing device 700 of the unmanned vehicle further includes:

[0119] The fourth distance acquisition module is used to acquire the fourth distance between the autonomous vehicle and static obstacles.

[0120] The maximum speed determination module is used to determine the maximum speed of the unmanned vehicle when it travels to a static obstacle, based on the fourth distance and the preset acceleration range of the unmanned vehicle.

[0121] The first target vehicle speed adjustment module is used to adjust the current vehicle speed of the unmanned vehicle to the target vehicle speed according to the fourth distance and the preset acceleration range if the maximum vehicle speed is greater than or equal to the target vehicle speed.

[0122] The second target vehicle speed adjustment module is used to adjust the fourth distance between the unmanned vehicle and the static obstacle according to the fourth distance and the preset acceleration range if the maximum vehicle speed is less than the target vehicle speed, and adjust the current vehicle speed to the target vehicle speed according to the adjusted fourth distance.

[0123] In one embodiment, the unmanned vehicle includes a vehicle body; the vehicle body height relative to the ground is adjustable; the obstacle-crossing device 700 of the unmanned vehicle further includes:

[0124] The data acquisition module is used to collect the shortest distance between the vehicle body and static obstacles during the autonomous vehicle's operation.

[0125] The vehicle height control module is used to keep the vehicle height unchanged if the shortest distance is greater than a preset distance threshold.

[0126] The vehicle height adjustment module is used to adjust the vehicle height so that the shortest distance is greater than the preset distance threshold if the shortest distance is less than or equal to the preset distance threshold.

[0127] When it is understood that, Figure 6 The structural block diagram of the obstacle-crossing device for the unmanned vehicle shown illustrates that each module is used to perform... Figure 1 , Figure 2 , Figure 4 and Figure 5 The steps in the corresponding embodiments, and for Figure 1 , Figure 2, Figure 4 and Figure 5 The steps in the corresponding embodiments have been explained in detail in the above embodiments. Please refer to them for details. Figure 1 , Figure 2 , Figure 4 and Figure 5 as well as Figure 1 , Figure 2 , Figure 4 and Figure 5 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0128] Figure 7 This is a structural block diagram of an unmanned vehicle provided in one embodiment of this application. Figure 7 As shown, the unmanned vehicle 800 of this embodiment includes: a processor 810, a memory 820, and a computer program 830 stored in the memory 820 and executable by the processor 810, such as a program for an obstacle-crossing method for the unmanned vehicle. When the processor 810 executes the computer program 830, it implements the steps of each embodiment of the obstacle-crossing method for the unmanned vehicle described above, for example... Figure 1 S201 to S203 are shown. Alternatively, the processor 810 implements the above when executing computer program 830. Figure 6 The functions of each module in the corresponding embodiments, for example, Figure 6 For details on the functions of modules 710 to 730 shown, please refer to [link / reference]. Figure 6 The relevant descriptions in the corresponding embodiments.

[0129] For example, the computer program 830 can be divided into one or more modules, one or more of which are stored in the memory 820 and executed by the processor 810 to implement the obstacle-crossing method for the unmanned vehicle provided in this embodiment. One or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 830 in the unmanned vehicle 800. For example, the computer program 830 can implement the obstacle-crossing method for the unmanned vehicle provided in this embodiment.

[0130] The autonomous vehicle 800 may include, but is not limited to, a processor 810 and a memory 820. Those skilled in the art will understand that... Figure 7 This is merely an example of an autonomous vehicle 800 and does not constitute a limitation on the autonomous vehicle 800. It may include more or fewer components than shown, or combine certain components, or different components. For example, an autonomous vehicle may also include input / output devices, network access devices, buses, etc.

[0131] The processor 810 may be a central processing unit, or it may be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0132] The memory 820 can be an internal storage unit of the autonomous vehicle 800, such as the hard drive or memory of the autonomous vehicle 800. The memory 820 can also be an external storage device of the autonomous vehicle 800, such as a plug-in hard drive, smart memory card, flash memory card, etc., equipped on the autonomous vehicle 800. Furthermore, the memory 820 can include both internal storage units and external storage devices of the autonomous vehicle 800.

[0133] This application provides a computer-readable storage medium, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the obstacle-crossing method for the unmanned vehicle as described in the above embodiments.

[0134] This application provides a computer program product that, when run on an unmanned vehicle, causes the unmanned vehicle to execute the obstacle-crossing methods described in the above embodiments.

[0135] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for obstacle crossing by an unmanned vehicle, characterized in that, The method includes: When a static obstacle is detected, the obstacle information of the static obstacle is obtained; If the obstacle information satisfies the obstacle crossing conditions corresponding to the target obstacle crossing strategy, then the target driving parameters corresponding to the target obstacle crossing strategy are obtained; the target driving parameters include the target vehicle speed. The unmanned vehicle is controlled to move toward the static obstacle based on the target driving parameters; The target driving parameters include the target vehicle speed; after obtaining the target driving parameters corresponding to the target obstacle-crossing strategy, the method further includes: Obtain the fourth distance between the unmanned vehicle and the static obstacle; Based on the fourth distance and the preset acceleration range of the unmanned vehicle, determine the maximum speed of the unmanned vehicle when it travels to the static obstacle; If the maximum vehicle speed is greater than or equal to the target vehicle speed, then the current vehicle speed of the unmanned vehicle is adjusted to the target vehicle speed according to the fourth distance and the preset acceleration range; If the maximum vehicle speed is less than the target vehicle speed, then the fourth distance between the unmanned vehicle and the static obstacle is adjusted according to the fourth distance and the preset acceleration range, and the current vehicle speed is adjusted to the target vehicle speed according to the adjusted fourth distance; The method further includes: If the sum of the time it takes for the unmanned vehicle to retreat to the adjusted fourth distance and the time required to travel at the adjusted fourth distance and cross the static obstacle exceeds the time required for the unmanned vehicle to generate an obstacle avoidance route and travel along the obstacle avoidance route, then the vehicle will travel along the obstacle avoidance route.

2. The method according to claim 1, characterized in that, The obstacle information includes slope angle and / or height; obtaining the obstacle information of the static obstacle includes: The vertex and bottom point of the static obstacle are determined by a sensor; the bottom point refers to the point where the static obstacle contacts the ground, and the sensor, the vertex, and the bottom point are in the same vertical plane; The first distance between the sensor and the vertex, the second distance between the sensor and the base point, and the third distance between the sensor and the ground are obtained respectively. Calculate the height of the static obstacle based on the first distance and the third distance; And / or, calculate the slope angle of the slope where the bottom point and the top point are located based on the first distance, the second distance, the third distance and the height.

3. The method according to claim 2, characterized in that, The step of calculating the height of the static obstacle based on the first distance and the third distance includes: Determine the first angle between the sensor and the first straight line containing the vertex and the vertical direction; The first included angle, the first distance, and the third distance are imported into the height calculation formula to obtain the height; the height calculation formula is: ； Where h is the height, H is the third distance, and S1 is the first distance. This is the first included angle.

4. The method according to claim 2, characterized in that, The step of calculating the slope angle of the slope surface where the bottom point and the top point are located based on the first distance, the second distance, the third distance, and the height includes: Determine the first angle between the sensor and the first straight line containing the vertex and the vertical direction; Determine the second angle between the second straight line containing the sensor and the bottom point and the vertical direction; The first included angle, the second included angle, the first distance, the second distance, the third distance, and the height are imported into the slope angle calculation formula to obtain the slope angle; the slope angle calculation formula is: ； in, Let H be the slope angle, H be the third distance, h be the height, and S1 be the first distance. S1 is the first included angle, and S2 is the second distance. This is the second included angle.

5. The method according to claim 2, characterized in that, The target obstacle-crossing strategy includes a climbing strategy and / or an obstacle-crossing strategy; after obtaining the obstacle information of the static obstacle, it also includes: If the slope angle is less than or equal to a preset angle, then the obstacle information is determined to meet the obstacle crossing conditions corresponding to the climbing strategy; or, if the height is less than the wheel height of the unmanned vehicle, then the obstacle information is determined to meet the obstacle crossing conditions corresponding to the obstacle crossing strategy. Before obtaining the target driving parameters corresponding to the target obstacle-crossing strategy, the method further includes: If the obstacle information satisfies the obstacle-crossing conditions corresponding to the climbing strategy and the obstacle-crossing conditions corresponding to the obstacle-crossing strategy, then the climbing strategy is determined as the target obstacle-crossing strategy.

6. The method according to any one of claims 1-4, characterized in that, The unmanned vehicle includes a body; the body height between the body and the ground is adjustable; controlling the unmanned vehicle to move toward the static obstacle based on the target driving parameters includes: During the operation of the unmanned vehicle, the shortest distance between the vehicle body and the static obstacle is collected; If the shortest distance is greater than a preset distance threshold, the vehicle height is kept constant. If the shortest distance is less than or equal to the preset distance threshold, the vehicle height is adjusted so that the shortest distance is greater than the preset distance threshold.

7. An obstacle-crossing device for an unmanned vehicle, characterized in that, The device includes: An obstacle information acquisition module is used to acquire obstacle information of a static obstacle when it is detected. The target driving parameter acquisition module is used to acquire the target driving parameters corresponding to the target obstacle crossing strategy if the obstacle information satisfies the obstacle crossing conditions corresponding to the target obstacle crossing strategy; the target driving parameters include the target vehicle speed. The control module is used to control the unmanned vehicle to travel toward the static obstacle based on the target driving parameters; The fourth distance acquisition module is used to acquire the fourth distance between the unmanned vehicle and the static obstacle; The maximum vehicle speed determination module is used to determine the maximum vehicle speed of the unmanned vehicle when it travels to the static obstacle based on the fourth distance and the preset acceleration range of the unmanned vehicle; The first target vehicle speed adjustment module is used to adjust the current vehicle speed of the unmanned vehicle to the target vehicle speed according to the fourth distance and the preset acceleration range if the maximum vehicle speed is greater than or equal to the target vehicle speed. The second target vehicle speed adjustment module is used to adjust the fourth distance between the unmanned vehicle and the static obstacle according to the fourth distance and the preset acceleration range if the maximum vehicle speed is less than the target vehicle speed, and adjust the current vehicle speed to the target vehicle speed according to the adjusted fourth distance. The obstacle avoidance driving module is configured to drive along the obstacle avoidance route if the sum of the time it takes for the unmanned vehicle to retreat to the adjusted fourth distance and the time required to travel at the adjusted fourth distance and cross the static obstacle exceeds the time required for the unmanned vehicle to generate an obstacle avoidance route and drive along the obstacle avoidance route.

8. An unmanned vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images