Lidar-based vehicle wading navigation method and apparatus, and vehicle and medium
By using a LiDAR-based vehicle wading navigation method, initial point cloud data and a 3D water depth map are generated using LiDAR, and a safe path is planned. This solves the problem that existing technologies cannot accurately detect water depth and navigate paths in real time, thus ensuring safe vehicle operation.
Patent Information
- Application Number
- PCT/CN2026/087478
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-10-15
- Filing Date
- 2026-03-31
- Publication Date
- 2026-11-19
AI Technical Summary
Existing technologies cannot provide real-time and accurate water depth detection and path navigation support in water-related scenarios, making vehicles prone to getting into dangerous situations.
A vehicle wading navigation method based on lidar is adopted. By controlling the lidar to rise to a first working height and scanning each detection point of the vehicle within the target range at a first frequency, initial point cloud data is generated, wading depth is calculated, a three-dimensional water depth map is constructed, and a safe path is planned.
It enables vehicles to provide real-time and accurate water depth detection and path navigation support in various water-related scenarios, preventing vehicles from getting into danger.
Smart Images

Figure CN2026087478_19112026_PF_FP_ABST
Abstract
Description
LiDAR-based vehicle wading navigation methods, devices, vehicles, and media
[0001] This application claims priority to Chinese Patent Application No. 202511474703.2, filed on October 15, 2025, entitled "Vehicle Water Navigation Method, Device, Vehicle and Medium Based on LiDAR", the entire contents of which are incorporated herein by reference. Technical Field
[0002] This application relates to the field of vehicle technology, and in particular to a vehicle wading navigation method, device, vehicle, and medium based on lidar. Background Technology
[0003] Under natural conditions such as heavy rainfall, snowmelt, or river flooding, road flooding has become a significant hazard to vehicle safety. In particular, in low-lying urban areas, tunnels, and under overpasses, water depths exceeding 30 centimeters can form in a short period of time, which can cause water to enter the vehicle's air intake, stall the engine, or even be swept away, seriously threatening the lives and property of drivers and passengers.
[0004] In related technologies, some vehicles employ passive waterproofing measures (such as raising the air intake position and strengthening the body seal), but they cannot actively identify the water depth and road conditions ahead. A few active detection solutions have significant flaws; for example, cameras are greatly affected by water mist, mud, and light, making it difficult to identify terrain under turbid water. Therefore, there are significant safety issues when vehicles are wading through water. Summary of the Invention
[0005] This application provides a vehicle wading navigation method, device, vehicle, and medium based on lidar. The technical solution provided by this application includes the following aspects.
[0006] The first aspect of this application provides a vehicle wading navigation method based on lidar, the method being executed by a computing device and including the following steps:
[0007] When the vehicle wading navigation system is in the activated state, the lidar is controlled to rise to a first working height, and the lidar is used to scan each detection point of the vehicle within the target range at a first frequency to obtain the initial point cloud data of the vehicle.
[0008] The wading depth of each detection point in the road area where the vehicle is located is calculated based on the initial point cloud data.
[0009] Based on the wading depth of each detection point, the wading environment data of the vehicle, the wading position of the vehicle, and the attitude data of the vehicle, a three-dimensional water depth map of the vehicle is constructed.
[0010] Based on the three-dimensional water depth map, a first safe path is planned for the vehicle to guide its movement.
[0011] According to one embodiment of this application, the step of scanning each detection point of the vehicle within a target range using the lidar at a first frequency to obtain initial point cloud data of the vehicle includes:
[0012] The phase difference of each transmitting unit in the laser radar transmitting array is adjusted based on the laser radar, and the reflected signal of each transmitting unit is received;
[0013] Obtain the distance between each detection point and the emission angle information of each detection point;
[0014] The initial point cloud data of the vehicle is generated based on the distance between each detection point and the emission angle information of each detection point.
[0015] According to one embodiment of this application, calculating the wading depth of each detection point in the road area where the vehicle is located based on the initial point cloud data includes:
[0016] Obtain the laser time-of-flight difference of the lidar;
[0017] Based on the laser time-of-flight difference, the first speed of light propagating in the air, and the second speed of light propagating in the water, the wading depth of each detection point in the road area where the vehicle is located is calculated.
[0018] According to one embodiment of this application, the step of planning a first safe path for the vehicle based on the three-dimensional water depth map includes:
[0019] Identify key feature data of the vehicle within the target area;
[0020] Based on the three-dimensional water depth map and combined with the preset vehicle wading safety threshold, the first safe path of the vehicle is planned.
[0021] According to one embodiment of this application, guiding the vehicle according to the first safe path includes:
[0022] Based on a preset human-computer interaction interface, the water wading information of the vehicle is displayed visually;
[0023] Based on the water wading information and the first safe path, real-time route guidance, obstacle warnings, and vehicle status information for the vehicle are generated.
[0024] The vehicle is guided to travel based on real-time route guidance, obstacle warnings, and vehicle status information.
[0025] A second aspect of this application provides a vehicle wading navigation device based on lidar, comprising:
[0026] The judgment module is used to determine whether the vehicle's wading navigation system is turned on.
[0027] The scanning module is used to control the lidar to rise to a first working height if the vehicle wading navigation system is in the activated state, and to use the lidar to scan each detection point of the vehicle within the target range at a first frequency to obtain the initial point cloud data of the vehicle.
[0028] The navigation module is used to calculate the wading depth of each detection point in the road area where the vehicle is located based on the initial point cloud data, and to construct a three-dimensional water depth map of the vehicle based on the wading depth of each detection point, the wading environment data of the vehicle, the wading position of the vehicle, and the attitude data of the vehicle, so as to plan a first safe path for the vehicle based on the three-dimensional water depth map, and guide the vehicle to drive according to the first safe path.
[0029] According to one embodiment of this application, the scanning module is further configured to:
[0030] The phase difference of each transmitting unit in the laser radar transmitting array is adjusted based on the laser radar, and the reflected signal of each transmitting unit is received;
[0031] The distance between each detection point and the emission angle information of each detection point are obtained, so as to generate the initial point cloud data of the vehicle based on the distance between each detection point and the emission angle information of each detection point.
[0032] According to one embodiment of this application, the navigation module is further configured to:
[0033] Obtain the laser time-of-flight difference of the lidar;
[0034] Based on the laser time-of-flight difference, the first speed of light of the laser in the air, and the second speed of light of the laser in the water, the wading depth of each detection point in the road area where the vehicle is located is calculated.
[0035] Based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data, a three-dimensional water depth map of the vehicle within the target area is constructed.
[0036] According to one embodiment of this application, the navigation module is further configured to:
[0037] Identify key feature data of the vehicle within the target area;
[0038] Based on the three-dimensional water depth map and combined with the preset vehicle wading safety threshold, the first safe path of the vehicle is planned.
[0039] According to one embodiment of this application, the navigation module is further configured to:
[0040] Based on a preset human-computer interaction interface, the water wading information of the vehicle is displayed visually;
[0041] Based on the water wading information and the first safe path, real-time path guidance, obstacle warnings, and vehicle status information are generated for the vehicle to guide its movement.
[0042] According to the embodiment of this application, a vehicle wading navigation device based on lidar, when the vehicle wading navigation system is activated, controls the lidar to rise to a first working height and scans each detection point of the vehicle within the target range at a first frequency to obtain initial point cloud data of the vehicle. Based on the initial point cloud data, the wading depth of each detection point in the road area where the vehicle is located is calculated, and a three-dimensional water depth map of the vehicle is constructed based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data to obtain a first safe path for the vehicle, which guides the vehicle's movement. This solves the problem that related technologies cannot provide real-time and accurate water depth detection and path navigation support for vehicles in various wading scenarios, thus making vehicles prone to getting into dangerous situations. By utilizing lidar to collect and calculate the wading depth of each detection point around the vehicle in real time, the optimal navigation path for the vehicle is obtained.
[0043] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the LiDAR-based vehicle wading navigation method as described in the above embodiments.
[0044] A fourth aspect of this application provides a computer-readable storage medium storing computer instructions for causing the computer to perform the LiDAR-based vehicle wading navigation method as described in the above embodiments.
[0045] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the LiDAR-based vehicle wading navigation method described in the above embodiments.
[0046] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application.
[0047] The technical solution provided in this application can bring the following beneficial effects:
[0048] When the vehicle wading navigation system is activated, the lidar is raised to a first working height and scans each detection point within the target range of the vehicle at a first frequency to obtain initial point cloud data. Based on the initial point cloud data, the wading depth at each detection point in the road area where the vehicle is located is calculated. A three-dimensional water depth map of the vehicle is constructed based on the wading depth at each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data, resulting in a first safe path for the vehicle. This first safe path guides the vehicle's movement. Therefore, by using lidar to collect and calculate the wading depth at each detection point around the vehicle in real time, the optimal navigation path is obtained to navigate the vehicle through water. This provides real-time and accurate water depth detection and path navigation support for vehicles in various wading scenarios, avoiding problems such as vehicles easily getting stuck in dangerous wading situations. Attached Figure Description
[0049] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:
[0050] Figure 1 is a flowchart of a vehicle wading navigation method based on lidar according to an embodiment of this application;
[0051] Figure 2 is a schematic diagram of the overall architecture of a vehicle wading system according to an embodiment of this application;
[0052] Figure 3 is a schematic diagram of lidar detection of terrain and water area according to an embodiment of this application;
[0053] Figure 4 is a schematic diagram of a vehicle navigation system provided according to an embodiment of this application;
[0054] Figure 5 is an example diagram of a vehicle wading navigation device based on lidar according to an embodiment of this application;
[0055] Figure 6 is a structural schematic diagram of a vehicle according to an embodiment of this application. Detailed Implementation
[0056] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0057] The following description, with reference to the accompanying drawings, describes a vehicle wading navigation method, apparatus, vehicle, and medium based on lidar according to embodiments of this application. Addressing the problem mentioned in the background art that related technologies cannot provide real-time and accurate water depth detection and path navigation support for vehicles in various wading scenarios, thus making vehicles prone to getting stuck in dangerous situations, this application provides a vehicle wading navigation method based on lidar. In this method, when the vehicle wading navigation system is activated, the lidar is controlled to rise to a first working height and scans each detection point of the vehicle within the target range at a first frequency to obtain initial point cloud data of the vehicle. Based on the initial point cloud data, the wading depth of each detection point in the road area where the vehicle is located is calculated. A three-dimensional water depth map of the vehicle is constructed based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data, obtaining a first safe path for the vehicle, which guides the vehicle's movement. This solves the problem that related technologies cannot provide real-time and accurate water depth detection and path navigation support for vehicles in various wading scenarios, thus making vehicles prone to getting stuck in dangerous situations. By utilizing lidar to collect and calculate the wading depth of each detection point around the vehicle in real time, the optimal navigation path for the vehicle is obtained.
[0058] Specifically, before introducing the embodiments of this application, let's first introduce the relevant technologies and existing problems. Under the influence of natural phenomena such as heavy rainfall, snowmelt, or floods, road flooding (wading) has become a common hidden danger threatening vehicle driving safety. Wading scenarios cover various types, such as localized flooding on urban roads due to poor drainage, persistent flooding in low-lying sections, short-term flooding caused by torrential rain, and large-scale flooding caused by river overflows or floods. In these scenarios, the water is often turbid and visibility is low. Traditional visual sensors (such as cameras) are easily affected by water mist and mud, causing them to malfunction. Drivers cannot judge the water depth, road conditions (such as hidden potholes, obstacles, and curbs) and terrain elevation ahead based solely on experience, which can easily lead to vehicles entering deep water areas (such as water exceeding the air intake height), colliding with underwater obstacles, or veering off the road, causing vehicle stalling, damage, or even personal injury.
[0059] Existing vehicle wading technologies have significant limitations: First, passive protection technologies (such as engine waterproofing and body sealing) can only reduce the risk of water damage and cannot actively avoid danger; second, a few active detection solutions have problems such as short detection distance, low accuracy, complex equipment and methods, and susceptibility to environmental interference. For example, some related technologies install lidar under the rearview mirror for wading detection. However, this method suffers from insufficient field of view due to its small distance from the ground, resulting in a detection area that cannot even detect wading conditions directly in front of or behind the vehicle. Others require installing two lidar systems on the roof and under the vehicle, along with ultrasonic detection devices, which involves a large amount of equipment, complex calculation methods, and susceptibility to environmental interference. Still others utilize sonar detectors, which are completely different from the method described in this invention and are far less fast and accurate than lidar. Thirdly, some solutions involving lidar installed on the roof require various adjustment plates for installation and adjustment, and the adjustment method requires mechanical linkage control, resulting in a complex structure. Over time, the reliability and durability will be greatly reduced, and the adjustment height is limited, with only a few positions that can be switched. Fourthly, related technologies only use various techniques to detect whether there is wading, without providing a system or method for path navigation and lacking the ability to link with navigation systems. Therefore, there is an urgent need for a system and method that can adapt to various wading scenarios, detect water depth in real time, and provide path navigation to fill the gap in existing technologies.
[0060] Based on this, the embodiments of this application utilize existing mature solid-state lidar without the need for a mechanical rotation module. Specifically, the OPA (Optical Phased Array) lidar achieves 360-degree scanning by adjusting the phase difference between each unit in the emission array to change the emission angle of the laser beam. Furthermore, the device only requires one lidar and one lifting mechanism. The lidar is mounted on the lifting mechanism, eliminating the need for a rotation mechanism. This results in a simple, reliable, and durable structure. When needed, it is raised to increase the field of view for a wide-range 360-degree omnidirectional water depth scan; when not needed, it is lowered with minimal impact. Simultaneously, this application can utilize the lidar to collect real-time water depth data around the vehicle. Based on this data, navigation can be provided to the driver, allowing them to navigate away from dangerous wading areas. Throughout the process, the data can be displayed in real-time on the central control screen via software, ensuring the driver is always aware of the water conditions and reducing panic.
[0061] Specifically, Figure 1 is a schematic flowchart of a vehicle wading navigation method based on lidar provided in an embodiment of this application. This method is executed by a computing device; in this embodiment, an in-vehicle computing device is used as an example for illustrative purposes. This embodiment can be implemented as an independent embodiment or in combination with any other embodiment, and is not limited thereto.
[0062] As shown in Figure 1, the vehicle wading navigation method based on lidar includes at least one of the following steps (101-104).
[0063] Step 101: With the vehicle wading navigation system in the activated state, control the lidar to rise to the first working height, and use the lidar to scan each detection point of the vehicle within the target range at the first frequency to obtain the initial point cloud data of the vehicle.
[0064] Among them, the vehicle wading navigation system is an intelligent vehicle assistance system designed for wading scenarios during vehicle operation. Optionally, the vehicle wading system is deployed in an on-board computing device, or in a cloud server, or in a distributed manner across both the on-board computing device and the cloud server.
[0065] In some embodiments, as shown in FIG2, the vehicle wading navigation system involved in the embodiments of this application is first introduced, which mainly includes a lidar module, a lifting mechanism, a rotation module, an environmental perception module, a data processing and navigation module, a human-machine interaction module, and an execution control module.
[0066] Optionally, the lidar module may employ at least one of the following:
[0067] Solid-state lidar eliminates the need for mechanical rotating modules. It is fixed to the center of the vehicle roof (longitudinal axis) via a lifting mechanism, ensuring that the detection range is unobstructed by the vehicle body.
[0068] • OPA phased array lidar changes the emission angle of the laser beam by adjusting the phase difference of each unit in the emission array, thereby achieving 360-degree scanning;
[0069] • Flash floodlight array lidar, like a flashlight, can emit laser light to cover an area in a short time and use a highly sensitive receiver to construct a three-dimensional image. It can acquire information within a certain range at once and can achieve 360-degree scanning without rotation. This type of lidar has no mechanical moving parts, has an extremely long lifespan, excellent vibration resistance and waterproof performance, and is fast, making it very suitable for harsh environments such as wading.
[0070] In some embodiments, the lifting mechanism can adjust the height of the lidar module according to the vehicle's wading depth and driving status to avoid the laser beam being blocked by the vehicle body, accumulated water, or obstacles. It mainly includes a waterproof electric telescopic rod (travel 0-80cm), a guide rail, and an electromagnetic locking assembly. The telescopic rod adopts an IP6K9K waterproof design, supports a lifting speed of 0-50cm / s, and has a maximum load capacity of 10kg. The locking assembly locks after the radar rises to the target height and has a vibration resistance level of ≥10G. Its control logic mainly supports manual triggering (controlled by the driver via buttons), automatic triggering (started when the environmental perception module detects a water depth of ≥5cm), and intelligent adjustment (dynamically adjusting the height according to the real-time water depth to ensure that the laser emission point is 10-30cm above the water surface).
[0071] In some embodiments, the environmental perception module can assist in acquiring vehicle status and surrounding environment information to provide supplementary data for navigation decisions. It mainly includes millimeter-wave radar (to detect obstacles), inertial measurement unit (to acquire vehicle attitude), and GPS (Global Positioning System) / BeiDou module (to locate vehicle position).
[0072] In some embodiments, the data processing and navigation module receives data from the lidar and environmental perception module to perform water depth calculation, road condition modeling, and path planning.
[0073] The data processing and navigation module includes water depth calculation, 3D road condition modeling, and path planning.
[0074] In a schematic representation, water depth calculation is implemented as follows: based on the laser time-of-flight difference, distinguishing between the air propagation segment (radar to water surface) and the underwater propagation segment (water surface to bottom), combined with air (3×10) 8 m / s) and water (2.25×10 8 The speed of light (m / s) is used to calculate the water depth (water depth = time to propagate in water × speed of light in water). A lidar emits laser pulses towards the water surface. Part of the laser is reflected by the water surface, and part penetrates the surface to reach the seabed and is reflected back. For a dual-color laser airborne LiDAR (Light Detection and Ranging) depth sounding system, it emits infrared light with a wavelength of 1064nm and blue-green light with a wavelength of 532nm. The infrared light is reflected by the sea surface, while the blue-green light penetrates the surface to reach the seabed and is reflected back. By recording the time difference between the return of the two beams and combining this with factors such as the incident angle of the blue-green light and the refractive index of the seawater, the instantaneous water depth at the measurement point can be calculated.
[0075] The 3D road condition modeling is achieved by fusing LiDAR point cloud data with IMU attitude data to construct a 3D terrain model of the first range around the vehicle (e.g., 30 meters), which is used to identify key features such as curbs, potholes, and underwater obstacles (e.g., stones, missing manhole covers).
[0076] Path planning is implemented as follows: Based on a 3D model and combined with the vehicle's wading safety threshold, an optimal path is planned that satisfies at least one of the following rules:
[0077] Rule a: Water depth is less than or equal to the safety threshold;
[0078] Rule b: No obstacles;
[0079] Rule c: The slope is less than a preset slope threshold (e.g., 15°).
[0080] In some embodiments, the data processing and navigation module continuously updates the optimal path according to a preset path update frequency. In one example, the path update frequency is ≥1Hz.
[0081] Optionally, the above-mentioned security threshold can be set in at least one of the following ways:
[0082] • The maximum safe water depth preset according to the vehicle model is used as the safety threshold, for example, 30-50cm;
[0083] • The safety threshold is determined by combining the preset maximum safe water depth with the dynamic value dynamically determined by weather factors. For example, based on the preset maximum safe water depth, the threshold increase or decrease is selected according to different weather types. For instance, when the current weather is rainy, the threshold is reduced based on the preset maximum safe water depth, thereby planning the route with a smaller safety threshold and ensuring driving safety in rainy conditions.
[0084] Furthermore, the human-machine interaction module can visually display water wading information and navigation guidance to the driver, while supporting human-machine interaction operation. The main content displayed includes a 3D water depth map (color coding: green ≤ safe water depth, yellow > safe water depth but ≤ warning water depth, red > warning water depth), real-time route guidance (arrow markings), obstacle warnings (icons + text), and vehicle status (current water depth, radar altitude). Users can operate through the touch screen (zoom, switch views), voice interaction (such as "show water depth on the left"), and sound and light alarms (a buzzer and flashing red light when in danger).
[0085] Furthermore, the execution control module can control the vehicle's driving status (suitable for autonomous driving scenarios) or provide operation suggestions to the driver (suitable for manual driving scenarios) based on the path planning of the navigation module. This mainly includes autonomous driving mode and manual assistance mode. In autonomous driving mode, the system communicates with the vehicle's power, steering, and braking systems via the CAN (Controller Area Network) bus to achieve automatic obstacle avoidance, detour, and speed control (speed limit ≤30km / h when wading). In manual assistance mode, recommended driving routes are marked on the human-machine interface. When the driver's operation may lead to a dangerous area, voice prompts such as "Water depth exceeds the standard ahead, please turn right" are issued, and warnings are provided through steering wheel vibration feedback. Thus, the wading navigation function is realized based on the collaboration of the above modules. The following will explain the detailed vehicle wading navigation method.
[0086] In some embodiments, before step 101, the method further includes determining whether the vehicle wading navigation system is in an activated state.
[0087] According to one embodiment of this application, a lidar is used to scan each detection point of the vehicle within the target range at a first frequency to obtain initial point cloud data of the vehicle. This includes: adjusting the phase difference of each transmitting unit in the transmitting array based on the lidar, and receiving the reflected signal of each transmitting unit; obtaining the distance between each detection point and the emission angle information of each detection point, so as to generate initial point cloud data of the vehicle based on the distance between each detection point and the emission angle information of each detection point.
[0088] The first frequency can be set by those skilled in the art based on actual water navigation needs, or obtained from a limited number of computer simulations, and is not specifically limited here.
[0089] In other words, based on the phased array principle, beam scanning is achieved by adjusting the phase difference of each transmitting unit in the transmitting array, and initial point cloud data is generated according to the distance and transmission angle. The process provides higher angular resolution and point cloud density by finely controlling the phase gradient of the transmitting array, so that the generated initial point cloud data can better reflect the actual road conditions of the current road, thereby improving the accuracy of downstream wading depth calculation.
[0090] For example, as shown in Figures 3 and 4, firstly, it is determined whether the vehicle's wading navigation system has been triggered. This mainly includes the driver manually activating the "wading navigation mode," or the environmental perception module automatically activating it when it detects a water depth ≥ 5cm. When the vehicle's wading navigation system is activated, the lifting mechanism raises the LiDAR module to the first working height (e.g., 30cm), and each module performs self-checks and synchronizes its time. Secondly, the LiDAR module scans each detection point of the vehicle within the target range at a first frequency. For example, the LiDAR module scans a 30-meter range in front of and to both sides of the vehicle at a frequency of 20-50Hz, outputting initial point cloud data. This involves adjusting the phase difference of each transmitting unit in the LiDAR module's transmitting array and receiving the reflected signal from each transmitting unit. Then, the distance between each detection point within the target range and the emission angle information of each detection point are obtained. Based on these information, the initial point cloud data of the vehicle is generated. The lidar module emits a laser beam in all directions (360 degrees) within a 30-meter radius and receives reflected signals. By analyzing the propagation characteristics of lasers in air and water, it calculates the water depth and terrain data for each detection point. For every minute angle (e.g., 0.1°), the laser emitter emits a laser beam, and the detector receives the reflected signal and calculates the distance to that point. A large number of continuous "angle + distance" data combinations form a "point cloud" (i.e., a collection of multiple detection points) covering a specific area, which is the initial point source data. All water depth and terrain data are collected in approximately 0.2 seconds. The lidar module uses a pulsed lidar with a laser wavelength of 532nm (blue-green band, strong penetration in water). The detection angle covers 360 degrees horizontally and 45° vertically (30° depression to 15° elevation). The detection distance is 0-30 meters (dynamically adjustable according to vehicle speed; high-precision short-range detection at low speeds and extended long-range detection at high speeds), with a ranging accuracy ≤5cm and a scanning frequency of 20-50Hz (ensuring real-time performance).
[0091] Step 102: Calculate the wading depth of each detection point in the road area where the vehicle is located based on the initial point cloud data.
[0092] According to one embodiment of this application, calculating the wading depth of each detection point in the road area where the vehicle is located based on initial point cloud data includes: obtaining the laser time-of-flight difference of the lidar; and calculating the wading depth of each detection point in the road area where the vehicle is located based on the laser time-of-flight difference, the first speed of light of the laser in the air, and the second speed of light of the laser in the water.
[0093] In other words, by utilizing the significant difference in the propagation speed of lasers in air and water, and combining this with the dual echo characteristics of surface and bottom echoes detected by lidar, the wading depth at each detection point can be calculated, thereby achieving precise measurement of the wading depth on the road surface and improving the accuracy of the output wading depth.
[0094] Step 103: Based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data, construct a three-dimensional water depth map of the vehicle.
[0095] According to one embodiment of this application, a three-dimensional water depth map of a vehicle is constructed based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data. This includes: constructing a three-dimensional water depth map of the vehicle within a target range based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data.
[0096] Optionally, the target range can be a pre-set fixed range, a user-defined custom range, or a dynamic value determined dynamically based on the current road condition complexity.
[0097] Here, the aforementioned road condition complexity refers to the complexity of the road surface condition at the vehicle's current location. In some embodiments, since the vehicle captures the road surface condition through an onboard camera in water-crossing scenarios, the road condition complexity can be obtained as follows: obtain the vehicle's current location information; obtain map data corresponding to the current road based on the vehicle's current location information, the map data including pre-collected and recorded road condition information of the current road under normal weather conditions, such as road geometry and lane lines, road surface physical properties, static obstacles and facilities, etc.; determine the road condition complexity of the current road based on the map data.
[0098] In some embodiments, when the map data includes at least two types of road condition information, a conversion formula for the corresponding complexity of different road condition information is pre-configured. The at least two types of road condition information are converted into corresponding road condition complexities according to the conversion formula. The road condition complexities corresponding to the at least two types of road condition information are weighted and summed to obtain the road condition complexity of the current road.
[0099] Step 104: Plan a first safe path for the vehicle based on the three-dimensional water depth map, so as to guide the vehicle to travel according to the first safe path.
[0100] Specifically, the environmental perception module synchronously collects the wading depth, vehicle wading environment data (e.g., obstacles), vehicle wading position, and vehicle attitude data at each detection point. This collected data is then transmitted to the data processing and navigation module, which calculates the wading depth at each detection point every 0.1 seconds. The module then integrates multi-source data to construct a three-dimensional water depth map of the vehicle and continuously updates it. In other words, based on the characteristics of lidar—the time difference of laser flight, the first speed of light in air, and the second speed of light in water—the wading depth at each detection point in the road area where the vehicle is located is calculated (water depth = time of propagation in water × speed of light in water). Based on the constructed three-dimensional water depth map, a first safe path is planned for the vehicle to guide it away from dangerous wading areas.
[0101] According to one embodiment of this application, planning a first safe path for a vehicle based on a three-dimensional water depth map includes: identifying key feature data of the vehicle within a target range; and planning a first safe path for the vehicle based on the three-dimensional water depth map and in conjunction with a preset vehicle wading safety threshold.
[0102] Optionally, the key feature data can be implemented as features such as abrupt changes in underwater elevation, areas of sudden slope changes, or isolated obstacles, without any limitation here.
[0103] In other words, a decision-making mechanism that integrates key feature data recognition with three-dimensional water depth maps was introduced, and combined with the vehicle's own wading safety threshold, a closed loop from "environmental perception" to "behavioral decision-making" was achieved.
[0104] According to one embodiment of this application, guiding a vehicle to travel according to a first safe path includes: visually displaying the vehicle's water wading information based on a preset human-machine interface; generating real-time path guidance, obstacle warnings, and vehicle status information based on the water wading information and the first safe path, so as to guide the vehicle to travel based on the real-time path guidance, obstacle warnings, and vehicle status information.
[0105] In other words, by visually displaying the vehicle's water wading information through a human-computer interaction interface, drivers can clearly understand the status of the water-wading area, providing strong support for drivers' driving decisions, thereby improving driving safety in water-wading scenarios, providing effective warnings of potential dangers in water-wading driving scenarios, and thus assisting drivers in risk avoidance.
[0106] In one example, after constructing a three-dimensional water depth map, this embodiment of the application identifies key feature data of the vehicle within the target range and, in conjunction with a preset vehicle wading safety threshold (e.g., 30cm), plans a first safe path that meets conditions such as "water depth ≤ safety threshold, no obstacles, and slope ≤ 15°". Then, if the vehicle is currently in autonomous driving mode, the execution control module directly sends control commands (steering, acceleration, braking) to the vehicle chassis system via the CAN bus to control the vehicle to travel along the first safe path. If the vehicle is currently in manual assistance mode, the human-machine interaction module displays a color water depth map and arrow guidance on the central control screen and can remind the driver through voice ("Deep water ahead, please turn left"), steering wheel vibration, etc., and output control signals or operation suggestions.
[0107] In some embodiments, the system continuously monitors the wading depth throughout the entire operation. If the water depth increases, it controls the lifting mechanism to raise the radar further. If the road conditions change, it replans the route in real time. If the vehicle does not detect water (water depth ≤ 3cm) for a first consecutive period of time (e.g., 60 seconds), or if the driver manually turns off the system, it indicates that the vehicle is not in a dangerous wading area. The lidar will then return to its initial position, the system will exit, and enter standby mode.
[0108] In summary, this application can achieve the following beneficial effects:
[0109] (1) Wide range of applicable scenarios: It covers a variety of water-related scenarios such as rainstorm water accumulation, urban waterlogging, floods, and water accumulation in low-lying road sections, breaking through the limitation of only targeting specific scenarios and making it more practical;
[0110] (2) Wide range of applicable scenarios: It covers a variety of water-related scenarios such as rainstorm water accumulation, urban waterlogging, floods, and water accumulation in low-lying road sections, breaking through the limitation of only targeting specific scenarios and making it more practical;
[0111] (3) Intelligent path planning: Dynamically plan the optimal path by combining vehicle safety parameters, supporting both autonomous driving and manual driving modes, and adapting to different vehicle models and driving needs;
[0112] (4) Intelligent path planning: Combines vehicle safety parameters to dynamically plan the optimal path, supports both autonomous driving and manual driving modes, and adapts to different vehicle models and driving needs.
[0113] According to the LiDAR-based vehicle wading navigation method of this application embodiment, when the vehicle wading navigation system is activated, the LiDAR is controlled to rise to a first working height and scans each detection point of the vehicle within the target range at a first frequency to obtain initial point cloud data of the vehicle. Based on the initial point cloud data, the wading depth of each detection point in the road area where the vehicle is located is calculated, and a three-dimensional water depth map of the vehicle is constructed based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data to obtain a first safe path for the vehicle, which guides the vehicle's movement. Thus, by using LiDAR to collect and calculate the wading depth of each detection point around the vehicle in real time, the optimal navigation path of the vehicle is obtained to navigate the vehicle through water, providing real-time and accurate water depth detection and path navigation support for the vehicle in various wading scenarios, avoiding problems such as the vehicle easily getting stuck in dangerous situations in wading scenarios.
[0114] Next, referring to the accompanying drawings, a vehicle wading navigation device based on lidar according to an embodiment of this application is described.
[0115] Figure 5 is a block diagram of a vehicle wading navigation device based on lidar according to an embodiment of this application.
[0116] As shown in Figure 5, the vehicle wading navigation device 10 based on lidar includes a scanning module 200 and a navigation module 300.
[0117] The judgment module 100 is used for;
[0118] The scanning module 200 is used to control the lidar to rise to a first working height when the vehicle wading navigation system is turned on, and to use the lidar to scan each detection point of the vehicle within the target range at a first frequency to obtain the initial point cloud data of the vehicle.
[0119] The navigation module 300 is used to calculate the wading depth of each detection point in the road area where the vehicle is located based on the initial point cloud data; construct a three-dimensional water depth map of the vehicle based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data; and plan a first safe path for the vehicle based on the three-dimensional water depth map to guide the vehicle's driving according to the first safe path.
[0120] According to one embodiment of this application, the LiDAR-based vehicle wading navigation device 10 further includes a judgment module 100, used to determine whether the vehicle wading navigation system is in an on state.
[0121] According to one embodiment of this application, the scanning module 200 is further configured to:
[0122] The phase difference of each transmitting unit in the transmitting array is adjusted based on the lidar, and the reflected signal of each transmitting unit is received;
[0123] Obtain the distance between each detection point and the emission angle information of each detection point;
[0124] The initial point cloud data of the vehicle is generated based on the distance between each detection point and the emission angle information of each detection point.
[0125] According to one embodiment of this application, the navigation module 300 is further configured to:
[0126] Obtain the time-of-flight difference of the laser from the lidar;
[0127] Based on the laser's time-of-flight difference, the first speed of light for laser propagation in air, and the second speed of light for laser propagation in water, the wading depth at each detection point in the road area where the vehicle is located is calculated.
[0128] A three-dimensional water depth map of the vehicle within the target area is constructed based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data.
[0129] According to one embodiment of this application, the navigation module 300 is further configured to:
[0130] Identify key feature data of vehicles within the target range;
[0131] Based on a 3D water depth map and a preset vehicle wading safety threshold, the first safe path for the vehicle is planned.
[0132] According to one embodiment of this application, the navigation module 300 is further configured to:
[0133] Based on a pre-set human-computer interaction interface, the vehicle's water wading information is displayed visually;
[0134] Real-time route guidance, obstacle warnings, and vehicle status information are generated based on water wading information and the first safe path.
[0135] The system guides vehicles based on real-time route guidance, obstacle warnings, and vehicle status information.
[0136] According to the embodiment of this application, a vehicle wading navigation device based on lidar, when the vehicle wading navigation system is activated, controls the lidar to rise to a first working height and scans each detection point of the vehicle within the target range at a first frequency to obtain initial point cloud data of the vehicle. Based on the initial point cloud data, the wading depth of each detection point in the road area where the vehicle is located is calculated, and a three-dimensional water depth map of the vehicle is constructed based on the wading depth of each detection point, the vehicle's wading environment data, the vehicle's wading position, and the vehicle's attitude data to obtain a first safe path for the vehicle, guiding the vehicle to travel according to the first safe path. Thus, by using lidar to collect and calculate the wading depth of each detection point around the vehicle in real time, the optimal navigation path of the vehicle is obtained to navigate the vehicle wading through water, realizing real-time and accurate water depth detection and path navigation support for vehicles in various wading scenarios, avoiding problems such as vehicles easily getting stuck in dangerous wading situations.
[0137] Figure 6 is a structural schematic diagram of a vehicle provided in an embodiment of this application. The vehicle may include:
[0138] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.
[0139] When the processor 602 executes the program, it implements the vehicle wading navigation method based on lidar provided in the above embodiments.
[0140] Furthermore, the vehicle also includes:
[0141] Communication interface 603 is used for communication between memory 601 and processor 602.
[0142] The memory 601 is used to store computer programs that can run on the processor 602.
[0143] The memory 601 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.
[0144] If the memory 601, processor 602, and communication interface 603 are implemented independently, they can be interconnected via a bus to communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 6, but this does not indicate that there is only one bus or one type of bus.
[0145] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.
[0146] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0147] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described LiDAR-based vehicle wading navigation method.
[0148] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0149] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0150] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0151] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections with one or more wires (electronic devices), portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, fiber optic devices, and compact disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0152] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, pin-grid arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0153] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.
[0154] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0155] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.
Claims
1. A vehicle wading navigation method based on lidar, the method being executed by a computing device, comprising the following steps: When the vehicle wading navigation system is in the activated state, the lidar is controlled to rise to a first working height, and the lidar is used to scan each detection point of the vehicle within the target range at a first frequency to obtain the initial point cloud data of the vehicle. The wading depth of each detection point in the road area where the vehicle is located is calculated based on the initial point cloud data. Based on the wading depth of each detection point, the wading environment data of the vehicle, the wading position of the vehicle, and the attitude data of the vehicle, a three-dimensional water depth map of the vehicle is constructed. Based on the three-dimensional water depth map, a first safe path is planned for the vehicle to guide its movement.
2. The method of claim 1, wherein, The step of scanning each detection point of the vehicle within the target range using the lidar at a first frequency to obtain initial point cloud data of the vehicle includes: The phase difference of each transmitting unit in the laser radar transmitting array is adjusted based on the laser radar, and the reflected signal of each transmitting unit is received; Obtain the distance between each detection point and the emission angle information of each detection point; The initial point cloud data of the vehicle is generated based on the distance between each detection point and the emission angle information of each detection point.
3. The method of claim 1 or 2, wherein, The calculation of the wading depth at each detection point in the road area where the vehicle is located based on the initial point cloud data includes: Obtain the laser time-of-flight difference of the lidar; Based on the laser time-of-flight difference, the first speed of light propagating in the air, and the second speed of light propagating in the water, the wading depth of each detection point in the road area where the vehicle is located is calculated.
4. The method according to any one of claims 1 to 3, wherein, The step of planning a first safe path for the vehicle based on the three-dimensional water depth map includes: Identify key feature data of the vehicle within the target area; Based on the three-dimensional water depth map and combined with the preset vehicle wading safety threshold, the first safe path of the vehicle is planned.
5. The method according to any one of claims 1 to 4, wherein, Guiding the vehicle according to the first safe path includes: Based on a preset human-computer interaction interface, the water wading information of the vehicle is displayed visually; Based on the water wading information and the first safe path, real-time route guidance, obstacle warnings, and vehicle status information for the vehicle are generated. The vehicle is guided to travel based on real-time route guidance, obstacle warnings, and vehicle status information.
6. A vehicle wading navigation device based on lidar, comprising: The scanning module is used to control the lidar to rise to a first working height when the vehicle wading navigation system is in the activated state, and to use the lidar to scan each detection point of the vehicle within the target range at a first frequency to obtain the initial point cloud data of the vehicle. The navigation module is used to calculate the wading depth of each detection point in the road area where the vehicle is located based on the initial point cloud data; Based on the wading depth of each detection point, the wading environment data of the vehicle, the wading position of the vehicle, and the attitude data of the vehicle, a three-dimensional water depth map of the vehicle is constructed. Based on the three-dimensional water depth map, a first safe path is planned for the vehicle to guide its movement.
7. The apparatus of claim 6, wherein, The scanning module is also used for: The phase difference of each transmitting unit in the laser radar transmitting array is adjusted based on the laser radar, and the reflected signal of each transmitting unit is received; Obtain the distance between each detection point and the emission angle information of each detection point; The initial point cloud data of the vehicle is generated based on the distance between each detection point and the emission angle information of each detection point.
8. The apparatus of claim 6, wherein, The navigation module is also used for: Obtain the laser time-of-flight difference of the lidar; Based on the laser time-of-flight difference, the first speed of light propagating in the air, and the second speed of light propagating in the water, the wading depth of each detection point in the road area where the vehicle is located is calculated.
9. A vehicle comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the LiDAR-based vehicle wading navigation method as described in any one of claims 1-5.
10. A computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the LiDAR-based vehicle wading navigation method as described in any one of claims 1-5.
11. A computer program product comprising a computer program stored in a computer-readable storage medium, wherein a processor reads from and executes the computer program to implement the vehicle wading navigation method based on lidar as described in any one of claims 1 to 5.
