Automatic parking obstacle avoidance method, device and equipment for new energy automobile and storage medium

Abstract

The invention discloses an automatic parking obstacle avoidance method, device and equipment for a new energy automobile and a storage medium, and relates to the technical field of new energy automobile control, and the method comprises the steps: judging whether a step exists or not based on the image information of a target parking space; when the step exists, the height of the step is detected through a millimeter wave radar; determining a target driving strategy according to the height of the step and the ground clearance of the vehicle chassis; the vehicle is controlled to complete parking and obstacle avoidance based on the target driving strategy, and collision between the vehicle and the steps is effectively avoided by accurately judging the condition of the steps and generating the corresponding driving strategy, so that a vehicle body is protected from being damaged; the adaptability of the intelligent driving function is enhanced, the intelligent parking system can adapt to more complex parking environments, and the intelligent driving level of the vehicle is improved.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle control technology, and in particular to a method, device, equipment and storage medium for automatic parking and obstacle avoidance of new energy vehicles. Background Technology

[0002] With the popularization of new energy vehicles, intelligent parking function has become an important feature to enhance user experience. Low-chassis sports cars are becoming increasingly popular. However, due to their low chassis, existing new energy sports cars are prone to collisions with curbs and steps when parking, resulting in damage to the vehicle body.

[0003] Existing intelligent parking systems are primarily designed for conventional obstacles and lack the ability to accurately identify low steps. Millimeter-wave radar is susceptible to ground clutter interference, and visual recognition is unreliable under complex lighting conditions. More importantly, existing obstacle avoidance strategies can only pass through or detour around obstacles, lacking the ability to actively extricate themselves from situations where the step height is close to the chassis clearance, making it difficult to meet the safe parking needs of low-chassis vehicles.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, device, equipment, and storage medium for automatic parking and obstacle avoidance of new energy vehicles, aiming to solve the technical problem that new energy vehicles are prone to collisions with steps when parking.

[0006] To achieve the above objectives, the present invention provides a method for automatic parking and obstacle avoidance of new energy vehicles, the method comprising the following steps: Determine if a step exists based on the image information of the target parking space; When a step is determined to exist, its height is detected using millimeter-wave radar. The target driving strategy is determined based on the height of the step and the ground clearance of the vehicle chassis. Based on the target driving strategy, the vehicle is controlled to complete parking and obstacle avoidance.

[0007] In one embodiment, the step of determining whether a step exists based on the image information of the target parking space includes: Raw image data of the target parking space is collected using surround-view cameras; The original image data is subjected to denoising and distortion correction to obtain the processed image information; Edge detection is performed on the image information to extract line features; The step outline is identified based on the aforementioned line features; The image information is input into a deep learning model for classification to obtain the classification result; The presence of steps is determined by combining the step outline with the classification results.

[0008] In one embodiment, the step of detecting the height of a step using millimeter-wave radar when the presence of a step is determined includes: Millimeter-wave signals are transmitted to the step via millimeter-wave radar, and the returned millimeter-wave signals are received. Multiple distance measurements are obtained based on the returned millimeter-wave signal; The distance measurements are dynamically filtered to remove outliers, resulting in an effective distance sequence. The geometric shape of the step surface is obtained by fitting the effective distance sequence. Obtain the current pitch angle attitude parameters of the vehicle, and calculate the compensation for the geometry of the step surface based on the pitch angle attitude parameters to obtain the compensation calculation result; The step height is determined based on the compensation calculation results.

[0009] In one embodiment, the step of determining the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis includes: Determine the percentage value of the step height relative to the vehicle chassis ground clearance; When the percentage value is less than a first preset threshold, a first upper-level strategy is determined, wherein the first upper-level strategy includes controlling the vehicle to drive up the step at a preset speed; When the percentage value is greater than the first preset threshold and less than the second preset threshold, a second upper-level strategy is determined, wherein the second upper-level strategy includes controlling the wheel to swing to a preset angle so that the wheel makes priority contact with the step to raise the vehicle body; When the percentage value is greater than the second preset threshold, it is determined that the vehicle cannot pass and a parking prompt message is generated.

[0010] In one embodiment, the step of controlling the vehicle to complete parking obstacle avoidance based on the target driving strategy includes: When the target driving strategy is the second higher-order strategy, the relative positional relationship between the current position of the vehicle and the step is obtained; The direction of wheel rotation is determined based on the relative positional relationship; Control the wheels to swing in the swing direction to a preset angle, so that the front wheels contact the step laterally; Once the vehicle body is raised to a safe height, control the vehicle to continue driving uphill; After the vehicle successfully drives onto the step, switch to the parking strategy to complete the parking.

[0011] In one embodiment, the step of controlling the vehicle to complete parking obstacle avoidance based on the target driving strategy further includes: The wheel speed and chassis height are monitored in real time when the wheel contacts the step; When an abnormal increase in wheel speed is detected and the chassis height fails to reach a safe height, it is determined that slippage has occurred. When slippage is detected, reduce the driving torque and readjust the wheel yaw angle to eliminate the slippage. After the slippage is eliminated, return to the step of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

[0012] In one embodiment, the step of controlling the vehicle to complete parking obstacle avoidance based on the target driving strategy further includes: When the wheel comes into contact with the step, the vehicle body tilt angle is detected to exceed the preset angle threshold, triggering emergency braking; After the emergency braking is triggered, the vehicle is controlled to reverse back to the initial position; Once the vehicle has completed its reverse movement, the step of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy is re-executed. When the presence of multiple consecutive steps is detected by millimeter-wave radar, a segmented driving strategy is generated. After each step is completed, the vehicle chassis ground clearance is recalibrated, and the first and second preset thresholds are dynamically adjusted.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes an automatic parking obstacle avoidance device for new energy vehicles, comprising: The image processing module is used to determine whether there are steps based on the image information of the target parking space; A radar detection module is used to detect the height of a step using millimeter-wave radar when the presence of a step is determined. The strategy generation module is used to determine the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis. The vehicle control module is used to control the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes an automatic parking obstacle avoidance device for new energy vehicles. The device includes: a memory, a processor, and an automatic parking obstacle avoidance program for new energy vehicles stored in the memory and executable on the processor. The automatic parking obstacle avoidance program for new energy vehicles is configured to implement the steps of the automatic parking obstacle avoidance method for new energy vehicles as described above.

[0015] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an automatic parking obstacle avoidance program for new energy vehicles, wherein the automatic parking obstacle avoidance program for new energy vehicles, when executed by a processor, implements the steps of the automatic parking obstacle avoidance method for new energy vehicles as described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the automatic parking and obstacle avoidance method for new energy vehicles as described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: By fusing perception through surround-view cameras and millimeter-wave radar, and through multi-point scanning, dynamic filtering, and pitch angle compensation, the system accurately identifies the contours of steps and calculates their height from multiple dimensions, significantly improving perception robustness under complex lighting and road conditions. A tiered threshold judgment mechanism is employed, subdividing the relationship between step height and chassis clearance into three strategy levels, thereby achieving differentiated intelligent decision-making and avoiding the limitations of traditional solutions that can only determine whether a step is passable or not. Wheel rotation control ensures the front wheels make lateral contact with the step edge, actively raising the vehicle body by prioritizing wheel contact with the step. Combined with slippage detection and emergency reversal mechanisms, the system monitors wheel speed and chassis height in real time to determine slippage status, triggering emergency braking and controlling the vehicle to reverse back to the initial position to re-execute the strategy. Simultaneously, the chassis clearance is dynamically calibrated and thresholds are adjusted for consecutive multi-level steps. In summary, this solution, through a complete closed-loop design of perception, decision-making, execution, and anomaly handling, enables the automatic parking system to actively avoid the risk of step collisions, significantly enhancing the safety and intelligence of low-chassis new energy vehicles in complex parking environments. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the automatic parking obstacle avoidance method for new energy vehicles in this application. Figure 2 This is a system block diagram provided for Embodiment 1 of the automatic parking obstacle avoidance method for new energy vehicles in this application; Figure 3This is a flowchart illustrating Embodiment 2 of the automatic parking obstacle avoidance method for new energy vehicles in this application; Figure 4 This is a schematic diagram of the module structure of the automatic parking obstacle avoidance device for new energy vehicles according to an embodiment of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the automatic parking and obstacle avoidance method for new energy vehicles in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an automatic parking and obstacle avoidance device for new energy vehicles. The following description uses an automatic parking and obstacle avoidance device for new energy vehicles as an example to illustrate this embodiment and the subsequent embodiments.

[0025] Based on this, embodiments of this application provide an automatic parking obstacle avoidance method for new energy vehicles, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the automatic parking obstacle avoidance method for new energy vehicles according to this application.

[0026] In this embodiment, the automatic parking obstacle avoidance method for new energy vehicles includes steps S10 to S40: Step S10: Determine whether there are steps based on the image information of the target parking space; It should be noted that the purpose of this step is to intelligently analyze the target parking space environment through the visual perception system, identify step obstacles, and provide triggering conditions and prior information for subsequent accurate ranging by millimeter-wave radar. This step is the perception entry point for the entire obstacle avoidance process, determining whether the system activates active ranging and obstacle avoidance strategies.

[0027] Image information of the target parking space refers to digital image data containing the parking space and its surrounding environment, collected by an in-vehicle surround-view camera. This information carries the geometric structure and semantic content of the scene. Steps are common curb structures at the edges of parking spaces, characterized by vertical height differences and horizontally extending edges.

[0028] Understandably, after acquiring raw image data through a surround-view camera, noise reduction and distortion correction are performed to improve image quality; then, edge detection is used to extract line features and identify the outline of the steps, while a deep learning model is used for semantic classification; finally, the geometric outline and semantic classification results are integrated for comprehensive judgment to ensure that the presence or absence of steps can still be accurately identified under complex lighting and occlusion conditions, avoiding missed or false detections.

[0029] In its implementation, when a vehicle performs intelligent parking, surround-view cameras installed on the outside of the vehicle capture image information of the parking space selected by the driver. Image processing algorithms are then used to analyze the captured images to determine if any steps are present.

[0030] Specifically, the process involves using an edge detection algorithm to identify line features in the image and determine the outline of the steps; classifying the image using a deep learning model to determine if steps exist; proceeding to the next step when a step is detected; and executing a standard parking strategy if no step is detected.

[0031] like Figure 2 As shown, the system assesses the parking space environment, identifying the presence of steps and their relative height to the vehicle's ground clearance. If the step height is less than 30% above the ground clearance or less than the ground clearance, a standard parking strategy is employed, and the vehicle parks in the space. If the step height exceeds 60% of the ground clearance, the vehicle is deemed to be parked and cannot proceed. If the step height exceeds 30% to 60% of the ground clearance, a special parking strategy is employed, specifically involving the front wheels laterally navigating the step before parking. Each step completes the parking space entry or parking determination process.

[0032] In one feasible implementation, step S10 includes steps A11 to A16: Step A11: Collect raw image data of the target parking space using a surround-view camera; It should be noted that the purpose of this step is to acquire raw visual data of the target scene, providing the basic input for subsequent image processing. The raw image data is the original sensor output without any software processing, preserving the complete details of the scene.

[0033] Surround-view cameras are wide-angle cameras installed around a vehicle to capture a 360-degree view of the surroundings. The raw image data is typically output in RAW or YUV format, containing brightness and color information for each pixel.

[0034] Understandably, by triggering the camera hardware synchronization signal, the image sensor is activated for exposure; the sensor converts the light signal into an electrical signal and generates a digital image through analog-to-digital conversion; this image data is temporarily stored in a memory buffer for subsequent noise reduction, correction, and other processing, ensuring the integrity and authenticity of the data source.

[0035] Step A12: Perform denoising and distortion correction on the original image data to obtain the processed image information; It should be noted that the purpose of this step is to eliminate noise interference and lens optical distortion introduced during image acquisition, improve image geometric accuracy and signal-to-noise ratio, and provide high-quality input for subsequent feature extraction.

[0036] Noise reduction filters out sensor thermal noise and quantization noise, while distortion correction corrects barrel or pincushion distortion in the lens. The processed image information has higher sharpness and linearity retention.

[0037] Understandably, the Gaussian filtering algorithm is used to smooth the neighboring pixels of the image and suppress random noise points; a pre-calibrated camera intrinsic parameter matrix and distortion coefficients are loaded; inverse distortion mapping calculation is performed on each pixel coordinate, and bilinear interpolation sampling is performed on the mapped non-integer coordinates; finally, distortion-free and low-noise image information is generated to ensure that the edge of the step appears as a real straight line.

[0038] Step A13: Perform edge detection on the image information and extract line features; It should be noted that the purpose of this step is to detect the geometric boundaries of the steps from the image and convert the image into a structured line representation, which will facilitate subsequent contour recognition and shape analysis.

[0039] Edge detection is an algorithm that identifies points of abrupt changes in image brightness gradient. Line features are sets of line segments formed by connecting edge points, representing geometric edges in the scene.

[0040] Understandably, the gradient magnitude and direction of each pixel in the image are calculated using the Canny operator; local gradient maxima are preserved through nonmaximum suppression; a double threshold connection strategy is used to associate strong edges with weak edges to form continuous lines; the extracted lines are stored in the form of point sequences to accurately represent the geometric shape of the step contour.

[0041] Step A14: Identify the contour of the steps based on line features; It should be noted that the purpose of this step is to filter out the unique L-shaped or stepped outline structure of the steps from all the lines, so as to distinguish the steps from other obstacles or road markings.

[0042] The outline of a step is a closed or semi-closed shape formed by the intersection of horizontal and vertical line segments at their endpoints, and has specific aspect ratios and included angle constraints.

[0043] Understandably, the Hough transform is used to detect straight line segments in line features, calculate the slope and endpoint coordinates of each line segment, filter out horizontal line segments with a slope close to 0 and vertical line segments with a slope close to infinity, find line segment pairs whose endpoint distance is less than the tolerance threshold, and calculate their included angle and length ratio; if the line segment pairs satisfy the geometric constraints of the steps, they are combined into a step outline, thus realizing the recognition from lines to semantic objects.

[0044] Step A15: Input the image information into the deep learning model for classification and obtain the classification result; It should be noted that the purpose of this step is to use artificial intelligence algorithms to determine whether there are steps in the image from a semantic level, so as to make up for the limitations of traditional vision methods in complex scenes and improve detection robustness.

[0045] Deep learning models are pre-trained convolutional neural networks that have the ability to extract deep semantic features of images; the classification result is the confidence score output by the model, indicating the probability that the image belongs to the step category.

[0046] Understandably, the image information is scaled to the model input size and normalized; the input convolutional neural network extracts features through multiple convolutions and pooling; the fully connected layer maps the features to classification probabilities; if the step category probability exceeds a preset threshold, the classification result is that a step exists, providing an independent basis for semantic judgment.

[0047] Step A16: Determine whether steps exist based on the step outline and classification results.

[0048] It should be noted that the purpose of this step is to integrate the results of geometric contour recognition with the results of deep learning classification, and to improve the detection accuracy and robustness by cross-validating multi-source information, thereby reducing the false alarm rate and false negative rate of a single method.

[0049] The comprehensive judgment method uses weighted voting or logical AND / OR rules to merge the results of two independent judgments into a final decision.

[0050] Understandably, by reading the geometric parameters of the step outline (such as outline area and aspect ratio) identified in step A14, a geometric confidence score is calculated; the classification probability output in step A15 is read as a semantic confidence score; the two scores are weighted and summed; if the weighted score exceeds the comprehensive judgment threshold, the step is finally determined to exist; this mechanism effectively combines geometric accuracy and semantic robustness to ensure high confidence in the detection results.

[0051] Step S20: When it is determined that there is a step, the height of the step is detected by millimeter-wave radar; It should be noted that the purpose of this step is to activate the active ranging sensor to accurately acquire the three-dimensional height information of the step after visually confirming its existence, so as to provide a quantitative decision-making basis for subsequent strategy formulation and realize the transition from perception to measurement.

[0052] Millimeter-wave radar is a radar sensor that operates in the millimeter-wave frequency band and can transmit frequency-modulated continuous waves and measure echo delay; step height is the height difference between the vertical surface of a step and the horizontal road surface, measured in millimeters or centimeters.

[0053] Understandably, the process involves sending a start command to the millimeter-wave radar to put it into ranging mode; the radar emits electromagnetic waves that are reflected off the stepped surface and then the echo is received; the frequency difference between the transmitted and received signals is measured to calculate the slant range; the vertical height is calculated by combining the vehicle's attitude and geometric relationship; this height value is used to quantitatively assess the risk of passage and provide a basis for strategy selection.

[0054] In practice, once a step is detected, a millimeter-wave radar installed at the front of the vehicle is activated to accurately detect the height of the step. The millimeter-wave radar calculates the distance between the step and the vehicle chassis by transmitting and receiving millimeter-wave signals, thereby determining the height of the step. Based on the detected step height, it is determined whether the vehicle can pass safely.

[0055] In one feasible implementation, step S20 includes steps A21 to A26: Step A21: Transmit millimeter-wave signals to the step using millimeter-wave radar and receive the returned millimeter-wave signals; It should be noted that the purpose of this step is to realize the physical process of radar active ranging, obtain the original echo signal of the step reflection, and provide basic data for subsequent distance calculation.

[0056] Millimeter-wave signals are electromagnetic waves with frequencies between 30 GHz and 300 GHz, possessing the characteristics of penetrating fog and dust and having high resolution; the return signal is the echo reflected from the surface of the step, carrying time delay and intensity information.

[0057] Understandably, by configuring the transmission parameters of the millimeter-wave radar, setting the waveform modulation method and transmission power, the radar antenna array is triggered to transmit millimeter-wave signals, which propagate at the speed of light to the surface of the step. The surface of the step produces diffuse reflection, and some energy returns to the radar receiving antenna. The receiver captures the weak echo signal, which is then amplified, mixed, and filtered with low noise, and outputs an intermediate frequency signal for subsequent processing, thus completing the physical layer signal interaction.

[0058] Step A22: Obtain multiple distance measurements based on the returned millimeter-wave signal; It should be noted that the purpose of this step is to extract distance information from the echo signal and improve data reliability through multiple measurements, avoiding errors from a single measurement, and providing a data foundation for subsequent filtering and fitting.

[0059] The distance measurement value is the straight-line distance between the radar and each point on the surface of the step, which is calculated by measuring the round-trip time delay of the electromagnetic wave; multiple measurement values ​​refer to the distance measurement samples collected at different angles or at different time points.

[0060] Understandably, by performing a Fourier transform on the returned intermediate frequency signal, the time-domain signal is converted into a frequency-domain signal, and the distance frequency corresponding to the frequency peak is identified; the frequency is converted into a distance value according to the frequency modulation slope, and a distance value is obtained from a single measurement; the radar beam is controlled to scan multiple points (such as 3-5 points) in the horizontal direction, or to continuously sample multiple times at a fixed angle, to obtain a sequence of distance measurement values ​​covering different positions of the step, providing a data basis for subsequent filtering and fitting.

[0061] Step A23: Perform dynamic filtering on each distance measurement value to remove outliers and obtain the effective distance sequence; It should be noted that the purpose of this step is to filter out noise and abnormal jump points in the measurement data, improve the stability and accuracy of the distance data, avoid misjudgments caused by interference, and ensure data quality.

[0062] Dynamic filtering is an adaptive filtering algorithm that dynamically adjusts the filtering parameters according to the data change trend; outliers are measurement points that deviate far from the true value and are caused by multipath reflection or clutter interference.

[0063] Understandably, by iterating through multiple distance measurements using a sliding window, the arithmetic mean and standard deviation of the data within the window are calculated. Statistical tests are then used to mark measurements that deviate from the mean by more than three times the standard deviation as outliers and remove them. An exponentially weighted moving average filter is applied to the remaining data points to smooth out minor fluctuations. Finally, an effective distance sequence is obtained, which truly reflects the geometric shape of the step surface with a controllable error range.

[0064] Step A24: Obtain the surface geometry of the step based on the effective distance sequence fitting; It should be noted that the purpose of this step is to reconstruct the three-dimensional surface profile of the steps from discrete distance points, and to obtain geometric parameters such as the slope and curvature of the steps, so as to provide a model basis for accurate height calculation.

[0065] Fitting refers to using mathematical functions to approximate discrete data points and generate continuous curves or surfaces; geometry is the mathematical expression of a step surface, such as a straight line, curve, or plane.

[0066] Understandably, the optimal planar or surface equation is generated by converting the point coordinates (distance values, angle values) in the effective distance sequence into three-dimensional spatial coordinates (x, y, z); fitting these spatial points using the least squares method; if the step surface is approximately planar, a linear function is used for fitting; if a surface exists, a quadratic polynomial is used for fitting; the fitted equation describes the geometry of the step surface, from which the positions of the highest and lowest points can be calculated.

[0067] Step A25: Obtain the current pitch angle attitude parameters of the vehicle, perform compensation calculation on the geometry of the step surface based on the pitch angle attitude parameters, and obtain the compensation calculation result; It should be noted that the purpose of this step is to eliminate the influence of the vehicle pitch angle on the distance measurement geometry, correct the measurement error caused by the vehicle body tilt, and ensure that the height calculation is based on the horizontal reference.

[0068] The pitch angle attitude parameter is the rotation angle of the vehicle around the lateral axis, representing the vertical tilt of the vehicle's front relative to the horizontal plane; the compensation calculation is to adjust the geometric model based on the pitch angle and correct the rotation transformation of the coordinate system.

[0069] Understandably, the current pitch angle is calculated by reading data from the vehicle's inertial measurement unit (IMU) or accelerometer. If the vehicle is in an uphill attitude, the radar beam points towards the sky, and the measured slant range needs to be projected onto the vertical direction. The vertical component correction is calculated based on the sine of the pitch angle and subtracted from the fitted geometry. Finally, the geometry of the step surface based on the horizontal road surface is obtained, eliminating the interference of attitude deviation.

[0070] Step A26: Determine the step height based on the compensation calculation results.

[0071] It should be noted that the purpose of this step is to extract the vertical height value of the steps from the compensated geometric model as the final quantitative indicator, providing an accurate basis for strategy judgment.

[0072] The compensation calculation result is a geometric model of the step surface after pitch angle correction, which contains accurate vertical coordinate information; the step height is the maximum vertical drop, that is, the height difference between the top and bottom of the step.

[0073] Understandably, the z-coordinate values ​​of all points are extracted from the compensated geometric equation; the difference between the maximum and minimum z-coordinate values ​​is calculated, and this difference is the vertical height of the step; this height value is output and converted to centimeters; this height value is used for subsequent percentage calculations with the chassis ground clearance to determine which driving strategy to adopt, directly affecting parking safety.

[0074] Step S30: Determine the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis; It should be noted that the purpose of this step is to generate the optimal driving strategy based on the quantified step height and the vehicle's inherent chassis parameters through a hierarchical decision-making mechanism, so as to achieve step passage or safe rejection with controllable risks, and to transform the perception data into an executable control scheme.

[0075] The target driving strategy is a set of control schemes output by the system, including parameters such as speed setting, wheel angle, and execution sequence; the vehicle chassis ground clearance is the vertical distance from the lowest point of the chassis to the ground when the vehicle is stationary, and is a fixed vehicle parameter.

[0076] Understandably, the process involves comparing and proportionally calculating the step height with the chassis ground clearance; classifying scenarios into low-risk, medium-risk, and high-risk categories based on preset risk level thresholds; generating strategies directly for low-risk scenarios, raising the vehicle body for medium-risk scenarios, and providing parking reminders for high-risk scenarios; this strategy determination process transforms perceived data into a sequence of executable control commands, which is the core of intelligent decision-making.

[0077] In the implementation, a corresponding driving strategy is generated based on the height of the step and the vehicle's ground clearance: If the step height is less than the vehicle's ground clearance, the vehicle can pass safely. In this case, the vehicle's speed is adjusted, and it slowly drives up the step. If the step height is greater than the vehicle's ground clearance, the vehicle cannot pass directly. In this case, the vehicle's direction is adjusted, causing the wheels to rotate at a certain angle of 45°. By prioritizing contact between the wheels and the step, the vehicle body is raised, avoiding collisions and achieving a smooth ascent. During the ascent, the vehicle's driving status is monitored in real time, including parameters such as speed, wheel speed, and chassis height, to ensure the vehicle safely and smoothly ascends the step.

[0078] In one feasible implementation, step S30 includes steps A31 to A34: Step A31: Determine the percentage value of the step height relative to the vehicle chassis ground clearance; It should be noted that the purpose of this step is to convert the absolute height difference into a relative proportion, so as to facilitate the establishment of a unified risk assessment standard, adapt to the differences in chassis height of different vehicle models, and achieve a universal judgment that is independent of vehicle model.

[0079] The percentage value is the percentage of the step height to the chassis ground clearance. For example, the calculation formula is (step height / chassis ground clearance) × 100%.

[0080] Understandably, by dividing the step height value determined in step A26 by the vehicle's pre-stored chassis ground clearance parameter value, and multiplying the quotient by 100, a percentage value is obtained. This value eliminates vehicle model differences and establishes a universal risk assessment scale. For example, 30% indicates that the step height is only 30% of the chassis clearance, with a low risk; 60% indicates that the step height exceeds half of the chassis clearance, with a high risk, providing standardized input for subsequent threshold judgment.

[0081] Step A32: When the percentage value is less than the first preset threshold, determine the first upper-level strategy, wherein the first upper-level strategy includes controlling the vehicle to drive up the step at a preset speed; It should be noted that the purpose of this step is to develop a conservative approach for low-risk scenarios, ensuring a smooth uphill climb while avoiding impacts and collisions, and guaranteeing a smooth ride.

[0082] The first preset threshold is the risk threshold set by the system (e.g., 30%). A percentage value less than this value indicates that the step height is much lower than the chassis clearance, and the risk of passing through is extremely small. The first step-up strategy is a control scheme that allows the vehicle to drive directly onto the step, which includes speed limits and stability requirements.

[0083] Understandably, by comparing the percentage value calculated in step A31 with the first preset threshold, if it is less than the threshold, it is determined to be a low-risk scenario; a first upper-level strategy is generated, setting the vehicle target speed to a preset slow speed (such as 5km / h), and disabling rapid acceleration and sharp turns; this strategy ensures that the wheels slowly contact the step, the impact force is small, and the chassis has enough margin to avoid touching the edge of the step, thus achieving safe and smooth passage.

[0084] Step A33: When the percentage value is greater than the first preset threshold and less than the second preset threshold, determine the second upper-level strategy, wherein the second upper-level strategy includes controlling the wheel to swing to a preset angle so that the wheel contacts the step first to raise the vehicle body. It should be noted that the purpose of this step is to develop an active lifting strategy for medium-risk scenarios. By controlling the geometric contact between the wheels and the steps, the wheels are used as fulcrums to lift the vehicle body, avoiding direct impact to the chassis and achieving active extrication.

[0085] The second preset threshold is a higher risk threshold (e.g., 60%). A percentage value between the first and second thresholds indicates that the step height is close to the chassis clearance, and passing through directly is risky. The second upper-level strategy is a control scheme that uses wheel rotation to raise the vehicle body, which raises the vehicle body by changing the wheel contact angle.

[0086] Understandably, by comparing numerical values ​​to confirm that the percentage value is in the medium-risk range, a second higher-order strategy is generated, which calculates the preset angle (e.g., 45°) that the wheels need to turn. This strategy instructs the vehicle to adjust the direction of the front wheels before approaching the step, so that the tire sidewalls rather than the tire treads contact the step first. As the vehicle moves forward, the wheels roll on the edge of the step, gradually raising the vehicle body and increasing the chassis clearance, thereby safely crossing the step and achieving active extrication.

[0087] Step A34: When the percentage value is greater than the second preset threshold, determine that the vehicle cannot pass and generate a parking prompt message.

[0088] It should be noted that the purpose of this step is to adopt a safety rejection strategy for high-risk scenarios, prevent vehicles from forcibly passing through and causing serious damage to the chassis or battery pack, ensure vehicle safety, and return the decision-making power to the driver.

[0089] The second preset threshold is the upper limit of risk that the system allows to pass. A percentage value greater than this value indicates that the height of the step exceeds the chassis clearance, and forcibly passing through will inevitably lead to a collision. The parking prompt information is a visual and auditory warning to the driver, informing him that automatic parking is not possible.

[0090] Understandably, by comparing numerical values ​​and confirming that the percentage value exceeds the second preset threshold, the system determines that the height of the step exceeds the vehicle's ability to pass; it generates a prompt message containing risk warnings and suggested actions, displays "Step too high, cannot park automatically, please select another parking space" on the in-vehicle display screen, and plays a voice warning at the same time; this strategy ensures that the system does not perform dangerous operations, returns the decision-making power to the driver, and avoids irreversible vehicle damage.

[0091] Step S40: Control the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

[0092] It should be noted that the purpose of this step is to transform the determined target driving strategy into specific vehicle control commands, drive the actuators to act, realize a closed loop from decision-making to execution, and complete the entire obstacle avoidance and parking process.

[0093] The target driving strategy is a control scheme that includes parameters such as speed, angle, and timing; parking obstacle avoidance refers to the vehicle safely passing over steps and parking in the target parking space, avoiding chassis collisions throughout the process.

[0094] Understandably, by parsing the various control parameters in the target driving strategy, corresponding CAN bus messages are generated; these messages are sent to execution units such as the engine controller, steering controller, and brake controller; vehicle status feedback is monitored in real time to form a closed-loop control; and the strategy is continuously executed until the vehicle successfully drives onto the step and completes the subsequent parking action, thus realizing the entire automatic parking obstacle avoidance task.

[0095] In practice, after the vehicle successfully drives onto the step, it continues to complete the parking action according to the conventional parking strategy. During the parking process, the vehicle's intelligent driving system monitors the surrounding environment in real time to ensure the safety of the parking process.

[0096] In one possible implementation, after step S40, steps A41 to A44 are further included: Step A41: Monitor wheel speed and chassis height in real time when the wheel contacts the step; It should be noted that the purpose of this step is to monitor key status parameters and promptly identify dangerous conditions such as wheel slippage or abnormal vehicle body lifting when executing the second higher-level strategy, so as to provide triggering conditions for abnormal handling.

[0097] Wheel speed is the angular velocity of the tire rotation, measured by a wheel speed sensor; chassis height is the vertical distance from the lowest point of the vehicle body to the ground, measured by a height sensor or suspension travel sensor; real-time monitoring refers to continuous sampling at high frequency (e.g., every 10ms).

[0098] Understandably, by reading the pulse signals from the ABS wheel speed sensors, the instantaneous rotational speed of each wheel is calculated; at the same time, the values ​​from the air suspension height sensor or acceleration sensor are read and converted into the chassis ground clearance; the two sets of data are stored in a loop buffer for subsequent trend analysis; this monitoring process starts the moment the wheel contacts the step and continues until the vehicle body is fully raised and stable, achieving full-process perception of critical states.

[0099] Step A42: When an abnormal increase in wheel speed is detected and the chassis height has not reached the safe height, it is determined that slippage has occurred; It should be noted that the purpose of this step is to automatically identify wheel slippage based on monitoring data, prevent the vehicle from being unable to lift or slipping uncontrollably due to tire spinning, and trigger anti-skid measures in a timely manner.

[0100] An abnormal increase refers to the wheel speed exceeding the expected value (such as exceeding the target speed by 150%); the safe height is the minimum ground clearance to ensure that the chassis will not be damaged, usually set as the step height plus a safety margin (such as 5cm); the slippage judgment is a data-driven state machine transition condition.

[0101] Understandably, by comparing the real-time wheel speed with the expected speed calculated based on the vehicle speed, if the speed difference exceeds a preset threshold and lasts for more than 500ms, the speed is determined to be abnormal; at the same time, the real-time chassis height is compared with the safe height threshold, and if the height does not meet the standard; when both conditions are met, the system determines that the wheel is slipping on the step, that is, the tire is sliding relative to the step surface rather than rolling, triggering the anti-slip processing procedure in step A43, thereby realizing the automatic diagnosis of dangerous conditions.

[0102] Step A43: When slippage is determined, reduce the driving torque and readjust the wheel yaw angle to eliminate the slippage. It should be noted that the purpose of this step is to eliminate the slippage that has occurred. By reducing the driving force and changing the wheel posture, the effective contact between the tires and the step is restored, allowing the vehicle body to continue to rise.

[0103] Driving torque is the torque output by the engine or motor that drives the wheels to rotate; readjusting the sway angle is to make a small adjustment to the wheel from the current angle (such as ±5°), changing the position of the contact point.

[0104] Understandably, by sending a torque reduction command to the power controller, the drive torque is reduced to 50% or less of its original value, thus reducing tire slippage. At the same time, a fine-tuning command is sent to the steering controller to increase or decrease the wheel yaw angle by a small amount, allowing the tire to contact different positions on the step. After waiting 100ms, the speed and height are re-monitored. This process breaks the slippage balance by reducing torque and slippage, and adjusting the angle and changing the contact point, allowing the tire to re-engage with the step surface and restore effective drive.

[0105] Step A44: After the slippage is eliminated, return to the steps of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

[0106] It should be noted that the purpose of this step is to restore the normal execution flow of the higher-level strategy after the slippage fault is resolved, continue to complete the parking task, and achieve closed-loop regression of the anomaly handling.

[0107] The slippage state is eliminated when the wheel speed returns to normal and the chassis height reaches the safe threshold; the return step means that the program control flow jumps back to the main strategy execution flow.

[0108] Understandably, by continuously monitoring the wheel speed and chassis height after step A43, if the speed difference returns to the normal range and the chassis height exceeds the safety threshold, it is determined that the slippage has been eliminated; the system clears the slippage flag and restores the original driving torque; the program counter jumps back to step S40 to continue executing the remaining actions of the second upper-level strategy; this mechanism ensures that abnormal handling does not affect the overall task completion and improves the system's fault tolerance.

[0109] In one possible implementation, after step S40, steps A51 to A54 are further included: Step A51: When the wheel contacts the step, the vehicle body tilt angle is detected to exceed the preset angle threshold, triggering emergency braking; It should be noted that the purpose of this step is to monitor the vehicle's attitude and take immediate emergency braking measures when the vehicle tilts excessively, which may cause a rollover or loss of control, to ensure the safety of the vehicle and its occupants.

[0110] The vehicle body tilt angle is the roll angle of the vehicle around its longitudinal axis, measured by a gyroscope or accelerometer; the preset angle threshold is the maximum safe roll angle allowed by the system (e.g., 15°); emergency braking is the rapid application of maximum braking force.

[0111] Understandably, by reading the roll angle data from the IMU sensor, the tilt angle of the vehicle body relative to the horizontal plane is calculated in real time. If the angle value continues to exceed the preset threshold, it indicates that the vehicle body is unstable during the wheel lifting process. The system immediately sends an emergency braking command to the brake controller, applies maximum braking pressure, and brings the vehicle to a rapid stop. At the same time, the hazard warning lights are illuminated to alert the driver and the surrounding environment and prevent the situation from escalating.

[0112] Step A52: After triggering emergency braking, control the vehicle to reverse back to the initial position; It should be noted that the purpose of this step is to return the vehicle from a dangerous step contact state to a safe initial position after emergency braking, creating conditions for retrying or aborting the task.

[0113] The initial position is the position when the vehicle first detects the step, and this position has been recorded in the system memory; the reverse control is to reverse back based on the recorded trajectory data.

[0114] Understandably, by reading historical trajectory data, the vehicle's driving path from its initial position to its current position is obtained; a reversing path is planned, and the steering wheel is turned in the opposite direction; the vehicle is driven to reverse at a low speed (such as 3 km / h), and obstacles behind are monitored in real time; when the deviation between the vehicle's position and the initial position coordinates is less than the preset tolerance, the reversing is stopped; this process ensures that the vehicle safely leaves the step contact and avoids continuing to stay in a dangerous posture.

[0115] Step A53: Once the vehicle has completed its reverse movement, re-execute the steps for controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy; It should be noted that the purpose of this step is to retry the second higher-level strategy after a safe reset, giving the system a second chance to execute, improving the success rate of the task, and avoiding complete task failure due to a single anomaly.

[0116] "Reversal complete" means the vehicle has come to a stable stop in the initial position and the brakes have been applied; "Re-execution" means calling the S40 main process again with the same strategy parameters.

[0117] Understandably, by clearing the emergency braking flag, resetting the state of all actuators, reloading the target driving strategy parameters to the control queue, and re-executing the swing, forward, and elevation process of step S40, this retry mechanism typically fine-tunes the initial parameters (such as slightly increasing the swing angle), significantly improving the success rate of the second attempt and enhancing the robustness of the system.

[0118] Step A54: When the presence of multiple consecutive steps is detected by millimeter-wave radar, a segmented driving strategy is generated, and after each step is completed, the ground clearance of the vehicle chassis is recalibrated, and the first and second preset thresholds are dynamically adjusted.

[0119] It should be noted that the purpose of this step is to deal with complex terrain with multiple steps in front of the parking space. By segmenting the process and adjusting dynamic parameters, continuous passage capability can be achieved, avoiding the situation where a fixed strategy would prevent subsequent steps from being passed.

[0120] Continuous multi-level steps refer to two or more steps arranged consecutively, with each step potentially having a different height; segmented driving strategy is a strategy sequence generated independently for each step; dynamic threshold adjustment is the real-time modification of risk classification standards based on changes in the current chassis height.

[0121] Understandably, the system continuously scans the terrain ahead using millimeter-wave radar to detect the edges of multiple steps; it segments the steps by distance and executes the S30 strategy determination process for each step; after the vehicle completes the ascent of the first step, the ground clearance of the chassis increases due to the increased vehicle height; the system remeasures the current chassis height and proportionally adjusts the first and second preset thresholds according to the new height; subsequent steps are assessed using the updated thresholds, making the strategy more adaptable to the elevated vehicle state and avoiding overly conservative approaches that could lead to subsequent steps being misjudged as impassable, thus enabling continuous and safe passage through multiple steps.

[0122] This embodiment provides an automatic parking obstacle avoidance method for new energy vehicles. By accurately judging the condition of steps and generating corresponding driving strategies, it can effectively avoid collisions between the vehicle and steps, protect the vehicle body from damage, and significantly improve the parking safety of low-chassis vehicles in complex parking environments. It also enables the intelligent parking system to adapt to more complex parking scenarios, including parking spaces with steps of varying heights. This not only enhances the vehicle's intelligent driving capabilities but also strengthens the versatility and practicality of the intelligent parking system in real-world applications, providing users with a more convenient and reliable parking experience.

[0123] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S40 includes steps S401 to S405: Step S401: When the target driving strategy is the second upper-level strategy, obtain the relative positional relationship between the current position of the vehicle and the step; It should be noted that the purpose of this step is to accurately obtain the spatial relative relationship between the vehicle and the step before executing the second upper-level strategy, so as to provide a positioning reference for the subsequent calculation of the wheel rotation direction and angle.

[0124] The target driving strategy is the second-highest level strategy, meaning the system determines the step height is in the medium-risk range and requires raising the vehicle body by rotating the wheels to pass. Relative positional relationships include spatial parameters such as the horizontal distance between the vehicle's longitudinal axis and the edge of the step, lateral offset, and the angle between the vehicle's front-end orientation and the step.

[0125] Understandably, by reading image information from surround-view cameras or front-view cameras, the position of the step edge line in the image coordinate system is identified; combined with the vehicle's own coordinate system, the distance and azimuth angle of the step edge relative to the vehicle's front bumper are calculated; at the same time, the vehicle's GPS or SLAM positioning data is read to determine the vehicle's precise position in the global map; and by combining the above information, a relative positional relationship description is generated to provide decision input for step S402.

[0126] Step S402: Determine the wheel rotation direction based on the relative positional relationship; It should be noted that the purpose of this step is to calculate the direction (left or right) in which the wheels should turn based on the spatial geometry between the vehicle and the step, ensuring that the wheels are accurately aligned with the edge of the step in a lateral manner, thus creating conditions for raising the vehicle body.

[0127] The wheel turning direction refers to the left and right direction of the front wheel steering angle. Lateral contact requires the side of the wheel to contact the step rather than the front. The determination process is a geometric optimization calculation, which needs to take into account the lateral position of the vehicle relative to the step and the direction of the vehicle's front.

[0128] Understandably, by analyzing the lateral offset in the relative positional relationship, if the vehicle is to the left, it will swing to the right, and if it is to the right, it will swing to the left; the angle between the vehicle's front orientation and the perpendicular line to the edge of the step will be calculated so that the side normal of the wheel is aligned with the edge of the step after the wheel swings; the swing direction command (left or right) will be output to the steering controller to ensure that the subsequent swing angle can make the side of the wheel contact the step at the optimal angle, thereby improving the lifting efficiency.

[0129] Step S403: Control the wheels to swing in the swing direction to a preset angle so that the front wheels contact the step in a lateral manner; It should be noted that the purpose of this step is to perform the actual steering action, turn the front wheels to the preset lateral angle, make the tire sidewall contact the edge of the step, and use the wheel structure as a lifting fulcrum to gradually raise the vehicle body.

[0130] The preset angle is the calibrated optimal swing angle (such as 45°) to make stable contact between the wheel side and the edge of the step; the lateral contact refers to the tire sidewall rather than the tire tread contacting the step, using the curvature of the tire sidewall to engage with the edge of the step.

[0131] Understandably, by sending a target angle command to the steering controller, the steering motor is controlled to drive the wheels to rotate in the swing direction; the steering angle sensor is monitored in real time, and steering stops when the angle reaches the preset value; the vehicle moves forward slowly, so that the sidewalls of the front wheels contact the vertical surface of the step; as the vehicle moves forward, the wheels roll on the edge of the step, generating an upward component force, which gradually raises the front of the vehicle body, and the ground clearance of the chassis increases accordingly, preventing the chassis from directly hitting the step.

[0132] Step S404: When the vehicle body is raised to a safe height, control the vehicle to continue driving to complete the uphill climb; It should be noted that the purpose of this step is to perform the actual steering action, turn the front wheels to the preset lateral angle, make the tire sidewall contact the edge of the step, and use the wheel structure as a lifting fulcrum to gradually raise the vehicle body.

[0133] The preset angle is the calibrated optimal swing angle (such as 45°) to make stable contact between the wheel side and the edge of the step; the lateral contact refers to the tire sidewall rather than the tire tread contacting the step, using the curvature of the tire sidewall to engage with the edge of the step.

[0134] Understandably, by sending a target angle command to the steering controller, the steering motor is controlled to drive the wheels to rotate in the swing direction; the steering angle sensor is monitored in real time, and steering stops when the angle reaches the preset value; the vehicle moves forward slowly, so that the sidewalls of the front wheels contact the vertical surface of the step; as the vehicle moves forward, the wheels roll on the edge of the step, generating an upward component force, which gradually raises the front of the vehicle body, and the ground clearance of the chassis increases accordingly, preventing the chassis from directly hitting the step.

[0135] Step S405: After the vehicle successfully drives onto the step, switch to the parking strategy to complete parking.

[0136] It should be noted that the purpose of this step is to switch the control mode from obstacle avoidance strategy to normal parking strategy after successfully passing the step obstacle, and continue to complete the remaining parking actions to achieve a closed loop of the entire automatic parking task.

[0137] The parking strategy is a conventional automatic parking path planning and trajectory tracking algorithm, including parking space alignment, path curvature calculation, and automatic steering wheel control; the switching refers to the transfer from the dedicated step obstacle avoidance control logic to the standard parking logic.

[0138] Understandably, by detecting whether the vehicle's position has completely passed the step and the chassis height has returned to stability, the step-passing phase is considered complete; the automatic parking module is invoked, and the path to the target parking space is replanned from the current position; the vehicle is controlled to drive along the planned path, completing precise positioning and attitude adjustment within the parking space; after the vehicle stops steadily in the center of the parking space and the steering wheel is straightened, a parking completion signal is sent, and the entire automatic parking obstacle avoidance process ends.

[0139] This embodiment provides a method for automatic parking obstacle avoidance for new energy vehicles. It utilizes the wheels as lifting fulcrums, changing the traditional wheel-step frontal collision mode. This actively raises the vehicle body during contact with the step, thus solving the obstacle avoidance problem for low-chassis vehicles when the step height is close to the chassis clearance. After the vehicle body is raised to a safe height, it smoothly transitions to uphill driving, ensuring the chassis remains within a safe distance. After successfully navigating the step, it automatically switches to a conventional parking strategy, achieving a seamless transition from obstacle avoidance to parking. The entire execution chain, through the organic coordination of geometric relationship calculations, swing direction optimization, lateral contact lifting, safe height monitoring, and mode switching, enables low-chassis vehicles to actively avoid the risk of step collisions, significantly improving the safety and success rate of the automatic parking system in complex parking environments.

[0140] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the automatic parking and obstacle avoidance method for new energy vehicles in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0141] This application also provides an automatic parking obstacle avoidance device for new energy vehicles. Please refer to... Figure 4 The automatic parking obstacle avoidance device for new energy vehicles includes: Image processing module 10 is used to determine whether there is a step based on the image information of the target parking space; Radar detection module 20 is used to detect the height of a step using millimeter-wave radar when the presence of a step is determined. Strategy generation module 30 is used to determine the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis. The vehicle control module 40 is used to control the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

[0142] The automatic parking obstacle avoidance device for new energy vehicles provided in this application, employing the automatic parking obstacle avoidance method for new energy vehicles in the above embodiments, can solve the technical problem of new energy vehicles easily colliding with steps when parking. Compared with the prior art, the beneficial effects of the automatic parking obstacle avoidance device for new energy vehicles provided in this application are the same as those of the automatic parking obstacle avoidance method for new energy vehicles provided in the above embodiments, and other technical features in the automatic parking obstacle avoidance device for new energy vehicles are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0143] In one embodiment, the image processing module 10 is further configured to acquire raw image data of the target parking space via a surround-view camera; The original image data is denoised and distortion corrected to obtain the processed image information; Edge detection is performed on the image information to extract line features; Step contour recognition based on line features; Image information is input into a deep learning model for classification, and the classification result is obtained. The presence of steps is determined by combining the step outline with the classification results.

[0144] In one embodiment, the radar detection module 20 is also used to transmit millimeter-wave signals to the step via millimeter-wave radar and receive the returned millimeter-wave signals; Multiple distance measurements are obtained based on the returned millimeter-wave signal; Dynamic filtering is applied to each distance measurement value to remove outliers and obtain an effective distance sequence. The geometry of the step surface is obtained by fitting the effective distance sequence. Obtain the vehicle's current pitch angle attitude parameters, and calculate the compensation for the geometry of the step surface based on the pitch angle attitude parameters to obtain the compensation calculation results; The step height is determined based on the compensation calculation results.

[0145] In one embodiment, the strategy generation module 30 is also used to determine the percentage value of the step height and the ground clearance of the vehicle chassis; When the percentage value is less than a first preset threshold, a first upper-level strategy is determined, wherein the first upper-level strategy includes controlling the vehicle to drive up the step at a preset speed. When the percentage value is greater than the first preset threshold and less than the second preset threshold, a second upper-level strategy is determined. The second upper-level strategy includes controlling the wheel to swing to a preset angle so that the wheel contacts the step first to raise the vehicle body. When the percentage value is greater than the second preset threshold, it is determined that the vehicle cannot pass and a parking prompt message is generated.

[0146] In one embodiment, the vehicle control module 40 is further configured to obtain the relative positional relationship between the current position of the vehicle and the step when the target driving strategy is the second upper-level strategy; The direction of wheel rotation is determined based on the relative positional relationship; Control the wheels to swing in the swing direction to a preset angle, so that the front wheels contact the step laterally; Once the vehicle body is raised to a safe height, control the vehicle to continue driving uphill; After the vehicle successfully drives onto the step, switch to the parking strategy to complete the parking.

[0147] In one embodiment, the vehicle control module 40 is also used to monitor the wheel speed and chassis height in real time when the wheel contacts the step; When an abnormal increase in wheel speed is detected and the chassis height does not reach a safe level, it is determined that slippage has occurred; When slippage is detected, reduce the driving torque and readjust the wheel yaw angle to eliminate the slippage. After the slippage is eliminated, return to the steps of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

[0148] In one embodiment, the vehicle control module 40 is further configured to detect when the vehicle body tilt angle exceeds a preset angle threshold when the wheel contacts the step, and trigger emergency braking. After triggering emergency braking, control the vehicle to reverse back to the initial position; Once the vehicle has completed its reverse maneuver, the steps for controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy are re-executed. When the presence of multiple consecutive steps is detected by millimeter-wave radar, a segmented driving strategy is generated. After each step is completed, the vehicle chassis ground clearance is recalibrated, and the first and second preset thresholds are dynamically adjusted.

[0149] This application provides an automatic parking obstacle avoidance device for new energy vehicles. The automatic parking obstacle avoidance device for new energy vehicles includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the automatic parking obstacle avoidance method for new energy vehicles in the above embodiment 1.

[0150] The following is for reference. Figure 5 This document illustrates a structural schematic diagram suitable for implementing the automatic parking and obstacle avoidance device for new energy vehicles in the embodiments of this application. The automatic parking and obstacle avoidance device for new energy vehicles in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The automatic parking obstacle avoidance device for new energy vehicles shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0151] like Figure 5As shown, the automatic parking and obstacle avoidance device for new energy vehicles may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the automatic parking and obstacle avoidance device for new energy vehicles. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the new energy vehicle automatic parking and obstacle avoidance device to exchange data with other devices wirelessly or via wired communication. Although the figure shows a new energy vehicle automatic parking and obstacle avoidance device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0152] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0153] The automatic parking obstacle avoidance device for new energy vehicles provided in this application, employing the automatic parking obstacle avoidance method for new energy vehicles in the above embodiments, can solve the technical problem of new energy vehicles easily colliding with steps when parking. Compared with the prior art, the beneficial effects of the automatic parking obstacle avoidance device for new energy vehicles provided in this application are the same as the beneficial effects of the automatic parking obstacle avoidance method for new energy vehicles provided in the above embodiments, and other technical features in this automatic parking obstacle avoidance device for new energy vehicles are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0154] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0155] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0156] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the automatic parking and obstacle avoidance method for new energy vehicles in the above embodiments.

[0157] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0158] The aforementioned computer-readable storage medium may be included in the automatic parking and obstacle avoidance device for new energy vehicles; or it may exist independently and not be installed in the automatic parking and obstacle avoidance device for new energy vehicles.

[0159] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the new energy vehicle automatic parking obstacle avoidance device, the new energy vehicle automatic parking obstacle avoidance device: determines whether there is a step based on the image information of the target parking space; when it is determined that there is a step, it detects the height of the step by millimeter-wave radar; determines the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis; and controls the vehicle to complete parking obstacle avoidance based on the target driving strategy.

[0160] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0161] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0162] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0163] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described automatic parking obstacle avoidance method for new energy vehicles, thereby solving the technical problem that new energy vehicles are prone to collisions with steps when parking. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the automatic parking obstacle avoidance method for new energy vehicles provided in the above embodiments, and will not be repeated here.

[0164] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for automatic parking and obstacle avoidance of new energy vehicles.

[0165] The computer program product provided in this application can solve the technical problem that new energy vehicles are prone to collision with steps when parking. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the automatic parking obstacle avoidance method for new energy vehicles provided in the above embodiments, and will not be repeated here.

[0166] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for automatic parking and obstacle avoidance of new energy vehicles, characterized in that, The method includes: Determine if a step exists based on the image information of the target parking space; When the presence of a step is determined, the height of the step is detected using millimeter-wave radar. The target driving strategy is determined based on the height of the step and the ground clearance of the vehicle chassis. Based on the target driving strategy, the vehicle is controlled to complete parking and obstacle avoidance.

2. The method as described in claim 1, characterized in that, The step of determining whether a step exists based on the image information of the target parking space includes: Raw image data of the target parking space is collected using surround-view cameras; The original image data is subjected to denoising and distortion correction to obtain the processed image information; Edge detection is performed on the image information to extract line features; The step outline is identified based on the aforementioned line features; The image information is input into a deep learning model for classification to obtain the classification result; The presence of steps is determined by combining the step outline with the classification results.

3. The method as described in claim 1, characterized in that, The step of detecting the height of a step using millimeter-wave radar when the presence of a step is determined includes: Millimeter-wave signals are transmitted to the step via millimeter-wave radar, and the returned millimeter-wave signals are received. Multiple distance measurements are obtained based on the returned millimeter-wave signal; The distance measurements are dynamically filtered to remove outliers, resulting in an effective distance sequence. The geometric shape of the step surface is obtained by fitting the effective distance sequence. Obtain the current pitch angle attitude parameters of the vehicle, and calculate the compensation for the geometry of the step surface based on the pitch angle attitude parameters to obtain the compensation calculation result; The step height is determined based on the compensation calculation results.

4. The method as described in claim 1, characterized in that, The step of determining the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis includes: Determine the percentage value of the step height relative to the vehicle chassis ground clearance; When the percentage value is less than a first preset threshold, a first upper-level strategy is determined, wherein the first upper-level strategy includes controlling the vehicle to drive up the step at a preset speed; When the percentage value is greater than the first preset threshold and less than the second preset threshold, a second upper-level strategy is determined, wherein the second upper-level strategy includes controlling the wheel to swing to a preset angle so that the wheel makes priority contact with the step to raise the vehicle body; When the percentage value is greater than the second preset threshold, it is determined that the vehicle cannot pass and a parking prompt message is generated.

5. The method as described in claim 1, characterized in that, The steps of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy include: When the target driving strategy is the second higher-order strategy, the relative positional relationship between the current position of the vehicle and the step is obtained; The direction of wheel rotation is determined based on the relative positional relationship; Control the wheels to swing in the swing direction to a preset angle, so that the front wheels contact the step laterally; Once the vehicle body is raised to a safe height, control the vehicle to continue driving uphill; After the vehicle successfully drives onto the step, switch to the parking strategy to complete the parking.

6. The method as described in claim 1, characterized in that, The step of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy further includes: The wheel speed and chassis height are monitored in real time when the wheel contacts the step; When an abnormal increase in wheel speed is detected and the chassis height fails to reach a safe height, it is determined that slippage has occurred. When slippage is detected, reduce the driving torque and readjust the wheel yaw angle to eliminate the slippage. After the slippage is eliminated, return to the step of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

7. The method as described in claim 1, characterized in that, The step of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy further includes: When the wheel comes into contact with the step, the vehicle body tilt angle is detected to exceed the preset angle threshold, triggering emergency braking; After the emergency braking is triggered, the vehicle is controlled to reverse back to the initial position; Once the vehicle has completed its reverse movement, the step of controlling the vehicle to complete parking and obstacle avoidance based on the target driving strategy is re-executed. When the presence of multiple consecutive steps is detected by millimeter-wave radar, a segmented driving strategy is generated. After each step is completed, the vehicle chassis ground clearance is recalibrated, and the first and second preset thresholds are dynamically adjusted.

8. An automatic parking obstacle avoidance device for new energy vehicles, characterized in that, include: The image processing module is used to determine whether there are steps based on the image information of the target parking space; A radar detection module is used to detect the height of a step using millimeter-wave radar when the presence of a step is determined. The strategy generation module is used to determine the target driving strategy based on the height of the step and the ground clearance of the vehicle chassis. The vehicle control module is used to control the vehicle to complete parking and obstacle avoidance based on the target driving strategy.

9. A new energy vehicle automatic parking obstacle avoidance device, characterized in that, The device includes: a memory, a processor, and a new energy vehicle automatic parking obstacle avoidance program stored in the memory and executable on the processor, the new energy vehicle automatic parking obstacle avoidance program being configured to implement the steps of the new energy vehicle automatic parking obstacle avoidance method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores an automatic parking obstacle avoidance program for new energy vehicles. When the processor executes the automatic parking obstacle avoidance program for new energy vehicles, it implements the steps of the automatic parking obstacle avoidance method for new energy vehicles as described in any one of claims 1 to 7.

Images