Collision warning method, device and equipment for electric unmanned vehicle

Abstract

The present invention belongs to the field of intelligent automobile technology and discloses a collision warning method, device and equipment for electric unmanned vehicles. The method includes: obtaining environmental information data around the vehicle in real time through sensors; preprocessing the collected environmental information data to obtain valid data that can be used for subsequent analysis; calculating the predicted trajectory of the vehicle and the motion trajectory of the target object based on the obtained valid data; using a collision probability model to calculate the probability of a collision based on the calculation results; sending a warning signal to the vehicle control system when the calculated collision probability exceeds a preset threshold; after receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid a collision. The present invention uses sensors and collision probability models to achieve comprehensive monitoring of the environment around electric unmanned vehicles, predict potential collision risks in advance, and improve the safety of vehicle driving.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent vehicles, and in particular relates to a collision warning method, device and equipment for electric unmanned vehicles. Background Art

[0002] With the continuous advancement of technology and people's demand for transportation, electric autonomous vehicles have become a hot topic of research and development. As a highly autonomous and intelligent means of transportation, electric autonomous vehicles have great potential to improve travel efficiency, reduce traffic accidents, and alleviate environmental pollution. However, electric autonomous vehicles still face many challenges in practical application, one of which is how to effectively predict and avoid collisions. Collisions pose a threat to traffic safety and the safety of passengers and property. Therefore, developing a reliable collision warning method is crucial to the safety of electric autonomous vehicles.

[0003] In traditional collision warning systems, only sensors (such as radars and cameras) are usually used to perceive the surrounding environment to determine whether there is a collision risk. However, due to the high degree of autonomy of electric unmanned vehicles, relying solely on sensor data cannot meet the accuracy and real-time requirements of collision warning in complex road environments. The present invention proposes a collision warning method, device and equipment for electric unmanned vehicles. It adopts a probability calculation model based on a Bayesian network, combines vehicle dynamic information and environmental perception data, and uses a Kalman filter algorithm to update the speed and direction of the target object, thereby achieving comprehensive monitoring of the environment surrounding the electric unmanned vehicle, improving the accuracy and real-time performance of collision warnings, and ensuring the safety of vehicle driving by predicting potential collision risks in advance. Summary of the Invention

[0004] In response to the shortcomings of the above-mentioned existing methods, the present invention provides a collision warning method, device and equipment for electric unmanned vehicles, aiming to solve the core problem that traditional collision warning methods cannot meet the requirements of collision warning accuracy and real-time performance.

[0005] To achieve the above-mentioned purpose, the present invention is implemented through the following technical solutions:

[0006] A collision warning method for an electric unmanned vehicle, the method comprising the following steps:

[0007] Step S10: acquiring environmental information data and road condition information data around the vehicle in real time through sensors installed on the electric unmanned vehicle;

[0008] Step S20: Preprocessing the environmental information data and road condition information data collected in real time to obtain valid data that can be used for subsequent analysis;

[0009] Step S30: Calculating the predicted driving trajectory of the vehicle based on the obtained valid data and tracking the motion trajectory of the target object;

[0010] Step S40: Calculating the probability of collision using a collision probability model based on the calculation result of step S30 and the tracked motion trajectory of the target object;

[0011] Step S50: When the calculated collision probability exceeds a preset threshold, a warning signal is sent to the vehicle control system;

[0012] Step S60: After receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid collision.

[0013] Preferably, in step S10, the sensor refers to a variety of sensors installed on the electric unmanned vehicle, including cameras, lidars, millimeter-wave radars, and ultrasonic sensors; the environmental information data around the vehicle includes the position, speed, shape, etc. of obstacles; and the road condition information data on the vehicle includes the degree of vehicle congestion, visibility, weather conditions, etc.

[0014] Preferably, the data preprocessing step in step S20 includes noise removal, missing value filling and feature extraction.

[0015] Preferably, in step S30, the predicted driving trajectory of the vehicle is calculated by formula (1):

[0016] (1)

[0017] in, x ( t ) is the time at which the vehicle t The position at the time, x 0 is the initial position, v x is the initial velocity, a x is the acceleration.

[0018] Preferably, the process of tracking the motion trajectory of the target object in step S30 includes:

[0019] Target tracking: Use multi-target tracking algorithm to track surrounding dynamic objects;

[0020] Target correction: Update the speed and direction of the target object through the Kalman filter algorithm.

[0021] Preferably, the update formula of the Kalman filter algorithm is as shown in formula (2):

[0022] (2)

[0023] in, is the current estimated state, is the Kalman gain, is the measured value, H is the measurement matrix, is the estimated state at the previous moment.

[0024] Preferably, the collision probability model in step S40 adopts a Bayesian network model, which integrates information data about the vehicle's surrounding environment collected by multiple sensors through the Bayesian network and evaluates the probability of collision. The steps of constructing the collision probability model include:

[0025] Define variables: Identify variables that can affect the probability of a collision, including the vehicle's surrounding environment, vehicle status, and obstacle information;

[0026] Formulate hypotheses: Make assumptions about the relationships between variables based on how the vehicle's speed and the location of obstacles affect the likelihood of a vehicle crashing.

[0027] Determine the conditional probability table: Based on the selected variables and assumptions, construct a conditional probability table to describe the dependency relationship between variables;

[0028] Build Bayesian network structures: Use Bayesian network graphs to visualize variables and their dependencies;

[0029] Parameter learning: Using existing data, the parameters of the constructed Bayesian network are estimated through maximum likelihood estimation or Bayesian Learning;

[0030] Reasoning and prediction: Based on existing data and learned parameters, the system performs reasoning and prediction, and predicts the probability of a collision at a certain point in the future based on the information data about the vehicle's surroundings collected by sensors.

[0031] Update and optimize: After accumulating more data, the parameters of the Bayesian network are continuously updated.

[0032] Preferably, in the continuously updating of the parameters of the Bayesian network, the updating formula of the Bayesian network parameters is as shown in formula (3):

[0033] (3)

[0034] in, P ( Collision | Data ) represents the collision probability under the given vehicle surrounding environment information data collected by the sensor, P ( Data | Collision) represents the conditional probability of the vehicle surrounding environment information data collected when a collision occurs, P ( Collision ) is the prior probability of collision, P ( Data ) represents the prior probability of the information data of the vehicle's surrounding environment collected by the sensor.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also proposes a collision warning device for an electric unmanned vehicle, which is characterized by:

[0036] Data acquisition module: used to obtain environmental information data around the vehicle in real time through sensors;

[0037] Data preprocessing module: used to preprocess the collected environmental information data to obtain valid data that can be used for subsequent analysis;

[0038] Trajectory prediction and tracking module: used to calculate the vehicle's predicted trajectory based on the valid data obtained and track the movement trajectory of the target object;

[0039] Collision probability calculation module: used to calculate the probability of collision using the collision probability model based on the calculation results and the tracked target object motion trajectory;

[0040] Warning module: used to send a warning signal to the vehicle control system when the calculated collision probability exceeds a preset threshold;

[0041] Warning response module: After receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid collision.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a collision warning device for an electric unmanned vehicle, wherein the collision warning device for an electric unmanned vehicle includes: a memory, a processor, and a collision warning program for an electric unmanned vehicle stored on the memory and runnable on the processor. When the collision warning program for an electric unmanned vehicle is executed by the processor, the steps of the collision warning method for an electric unmanned vehicle as described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes a collision warning program for an electric unmanned vehicle. When the collision warning program for an electric unmanned vehicle is executed by a processor, it implements a collision warning method for an electric unmanned vehicle as described above.

[0044] The advantages and effects of the present invention are:

[0045] The present invention adopts a probability calculation model based on a Bayesian network, combines vehicle dynamic information and environmental perception data, and uses a Kalman filter algorithm to update the speed and direction of the target object, thereby achieving comprehensive monitoring of the environment around the electric unmanned vehicle, improving the accuracy and real-time performance of collision warnings, and ensuring the safety of vehicle driving by predicting potential collision risks in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 The figure is a flow chart of a collision warning method for an electric unmanned vehicle according to the present invention.

[0048] Figure 2 Schematic diagram of the steps of constructing a collision probability model of the present invention.

[0049] Figure 3 The figure is a schematic structural diagram of a collision warning device for an electric unmanned vehicle according to the present invention.

[0050] Figure 4 This is a schematic block diagram of the structure of the collision warning electronic equipment for an electric unmanned vehicle of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] The present invention provides a collision warning method for an electric unmanned vehicle, the method is as follows: Figure 1 As shown, the following steps are included:

[0053] Step S10: Acquire environmental information data and road condition information data around the vehicle in real time through sensors installed on the electric unmanned vehicle.

[0054] Sensors refer to a variety of sensors installed on electric unmanned vehicles, including cameras, lidar, millimeter-wave radar, and ultrasonic sensors; environmental information data around the vehicle includes information such as the position, speed, and shape of other vehicles, pedestrians, and obstacles; and road condition information data on the vehicle includes information such as the degree of vehicle congestion, visibility, and weather conditions.

[0055] Cameras are commonly used on-board cameras and may also have infrared night vision capabilities. They are primarily used for recording driving and capturing images of the vehicle's surroundings. LiDAR, with its high resolution and long-range detection capabilities, is primarily used for long-range detection of distant obstacles, other vehicles, pedestrians, and animals, enabling the vehicle control system to issue timely collision warnings. Millimeter-wave radars have strong penetrating power and are suitable for adverse weather conditions. In severe weather conditions such as heavy rain, snow, dust, and fog, millimeter-wave radar's strong penetration allows it to detect obstacles, other vehicles, pedestrians, and animals in front of the vehicle. It can promptly collect target motion data, calculate the target's predicted trajectory, and track the target's motion trajectory. This allows it to calculate the probability of a collision between the vehicle and the target, providing timely warnings when a collision is imminent. Ultrasonic sensors utilize sound waves with a frequency above the human hearing range (typically greater than 20 kHz), commonly called ultrasound. The sensor transmits ultrasonic pulses and receives reflected echoes to measure distance. These sensors are widely used in various applications, particularly in autonomous vehicles and robotics, for obstacle detection, distance measurement, and environmental perception. By comprehensively utilizing the above devices, the stability and accuracy of data acquisition for electric unmanned vehicles can be significantly improved, enabling the collision probability model to more accurately calculate the collision probability and issue early warnings.

[0056] Step S20: Preprocessing the environmental information data and road condition information data collected in real time, including noise removal, missing value filling and feature extraction, to obtain valid data that can be used for subsequent analysis.

[0057] Noise refers to irrelevant, meaningless, or erroneous information in the data. During data preprocessing, some methods are needed to remove noise to prevent it from negatively impacting the model. Common noise removal methods include smoothing, filtering, and outlier detection. Smoothing reduces data volatility by performing operations such as averaging, weighted averaging, or sliding windows. For example, moving average or exponential smoothing can be used to smooth time series data. Filtering removes noise components in the frequency domain through filters. Common filtering methods include low-pass filtering, high-pass filtering, and band-pass filtering. For example, Fourier transform can be used to convert the signal to the frequency domain for processing. Outliers are data points that are significantly different from other observations. Statistical methods (such as the 3σ principle) or distance and density-based algorithms (such as LOF and DBSCAN) can be used to detect and remove outliers.

[0058] Missing values ​​refer to situations where certain variables or observations are missing in the data. Before conducting data analysis, missing values ​​need to be processed to avoid affecting the training and prediction capabilities of the model. Common methods for filling missing values ​​include deletion, interpolation, and model prediction. Deletion means that if the proportion of missing values ​​is small and randomly distributed, you can choose to directly delete samples or features with missing values; interpolation means estimating missing values ​​through some methods and replacing them with estimated values. Common interpolation methods include mean interpolation, median interpolation, mode interpolation, and regression interpolation. Model prediction means that if the number of missing values ​​is large, you can use other features as prediction targets to build a model, and then use this model to predict and fill in the missing values.

[0059] Feature extraction converts raw data into more representative feature representations to facilitate subsequent model training and prediction. Common feature extraction methods include principal component analysis (PCA), linear discriminant analysis (LDA), feature selection, and feature construction. PCA is an unsupervised dimensionality reduction method that maps high-dimensional data into a low-dimensional space through linear transformation, retaining the most important features. Linear discriminant analysis is a supervised dimensionality reduction method that seeks the optimal projection direction, aligning the projection points of samples of the same type as closely as possible and those of samples of different types as far apart as possible. Feature selection selects a subset of features from the original features that have better predictive power for the target variable. Common feature selection methods include filtering, wrapping, and embedding.

[0060] Step S30: Calculate the predicted driving trajectory of the vehicle based on the obtained valid data, and track the motion trajectory of the target object.

[0061] The predicted driving trajectory of the vehicle is calculated by formula (1):

[0062] (1)

[0063] in, x ( t ) is the time at which the vehicle t The position at the time, x 0 is the initial position, v x is the initial velocity of the vehicle, a x is the acceleration of the vehicle.

[0064] The process of tracking the target object's motion trajectory includes:

[0065] Target tracking: Use multi-target tracking algorithm to track surrounding dynamic objects;

[0066] Target correction: Update the speed and direction of the target object through the Kalman filter algorithm.

[0067] Multi-Object Tracking (MOT) algorithms are used to continuously track and identify multiple targets in a video sequence. Their goal is to accurately detect and track all targets of interest in video captured by a vehicle's cameras, and to re-identify them if they are lost or occluded. MOT algorithms can be divided into two main steps: target detection and target association.

[0068] Object detection refers to finding the location of an object of interest in each frame of a video sequence by using an object detection algorithm. Commonly used object detection algorithms include deep learning-based methods such as Faster R-CNN, YOLO, and SSD, as well as traditional feature extraction and machine learning methods such as HOG+SVM.

[0069] Target association refers to matching and associating targets detected in adjacent frames to form trajectories, which usually includes target matching and trajectory management. Target matching aims to determine the correspondence between the target detected in the current frame and the target that already existed in the previous frame. Common target matching methods include Kalman filtering, Hungarian algorithm, association filter, and correlation filter. Trajectory management is responsible for maintaining the trajectory information of the tracked target and predicting and updating it according to the target's motion model. Common trajectory management methods include Kalman filtering, particle filtering, and multi-hypothesis tracking.

[0070] In the target correction step, the update formula of the Kalman filter algorithm used is shown in formula (2):

[0071] (2)

[0072] in, is the current estimated state, is the Kalman gain, is the measured value, H is the measurement matrix, is the estimated state at the previous moment.

[0073] Step S40: Calculate the probability of collision using a collision probability model based on the calculation result of step S30 and the tracked motion trajectory of the target object.

[0074] Among them, the collision probability model adopts the Bayesian network model, which integrates multiple sensors through the Bayesian network and evaluates the probability of collision. The steps of constructing the collision probability model are as follows: Figure 2 Shown, including:

[0075] Define variables: Identify variables that can affect the probability of a collision, including sensor data, environmental information, vehicle status, and obstacle information;

[0076] Formulate hypotheses: Make assumptions about the relationships between variables based on the actual situation and problem requirements;

[0077] Determine the conditional probability table: Based on the selected variables and assumptions, construct a conditional probability table to describe the dependency relationship between variables;

[0078] Build Bayesian network structures: Use Bayesian network graphs to visualize variables and their dependencies;

[0079] Parameter learning: Using existing data, the parameters of the constructed Bayesian network are estimated through maximum likelihood estimation or Bayesian Learning;

[0080] Reasoning and prediction: Based on existing data and learned parameters, reasoning and prediction are performed. Based on real-time sensor data, the probability of a collision occurring at a certain point in the future is predicted.

[0081] Update and optimize: After accumulating more data, the parameters of the Bayesian network are continuously updated.

[0082] Preferably, in the continuously updating the parameters of the Bayesian network, the updating formula of the Bayesian network parameters is as shown in formula (3):

[0083] (3)

[0084] in, P ( Collision | Data ) represents the collision probability under the given vehicle surrounding environment information data collected by the sensor, P ( Data | Collision ) represents the conditional probability of the vehicle surrounding environment information data collected when a collision occurs, P ( Collision ) is the prior probability of collision, P ( Data ) represents the prior probability of the information data of the vehicle's surrounding environment collected by the sensor.

[0085] Step S50: When the calculated collision probability exceeds a preset threshold, a warning signal is sent to the vehicle control system.

[0086] Determining the preset threshold is an important decision that needs to be adjusted according to specific situations and needs. The present invention adjusts the threshold by taking into account acceptable risk levels, performance balance, and data-driven approaches.

[0087] The acceptable risk level refers to determining a threshold based on the degree of risk accepted in the application scenario. This requires considering the consequences and impact of a potential collision. For example, in a road traffic system, vehicles on highways may have a lower collision probability threshold, while a higher threshold may be required in urban areas or densely populated areas.

[0088] Performance balance involves determining the threshold by balancing the accuracy of alerts with the false alarm rate. Too frequent alerts may cause drivers to ignore real dangers, while overly conservative alerts increase the false alarm rate. Therefore, metrics such as ROC curves, precision, and recall are used to evaluate performance at different thresholds and select an appropriate threshold to achieve a balance.

[0089] Data-driven means using existing data to determine thresholds, analyzing historical data and testing based on real scenarios to obtain performance under different collision probabilities, and selecting appropriate thresholds based on needs.

[0090] It should be understood that the preset threshold is not fixed and may be dynamically adjusted based on factors such as the application environment, system performance requirements, and user feedback. Therefore, in actual applications, the present invention monitors and adjusts the threshold based on real-time conditions to ensure the accuracy and reliability of the system.

[0091] Step S60: After receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid collision.

[0092] After the vehicle control system confirms the existence of a potential collision risk, it will calculate the required braking force and send corresponding instructions to the braking system. The calculation of the required braking force involves factors such as the dynamic model, road friction coefficient, and vehicle mass, which need to be considered comprehensively; after the braking system receives the emergency braking instruction, it immediately performs the corresponding braking operation, which may trigger the anti-lock braking system (ABS) or electronic stability control system (ESC) to ensure vehicle stability and optimal braking effect; in order to further optimize the braking effect, the vehicle control system may adjust the braking force distribution of each wheel, and through the dynamic brake force distribution system (EBD) or traction control system (TCS), it can make real-time adjustments according to different road conditions and vehicle dynamic characteristics; at the same time, the vehicle control system will also send a warning signal to the driver, reminding him or her of the occurrence of an emergency through visual, sound and other means, which helps to attract the driver's attention and enable him or her to make an appropriate response.

[0093] In addition, the present invention also proposes a collision warning device for an electric unmanned vehicle, please refer to Figure 3 , the collision warning device for an electric unmanned vehicle comprises:

[0094] Data acquisition module: used to obtain environmental information data around the vehicle in real time through sensors;

[0095] Data preprocessing module: used to preprocess the collected environmental information data to obtain valid data that can be used for subsequent analysis;

[0096] Trajectory prediction and tracking module: used to calculate the vehicle's predicted trajectory based on the valid data obtained and track the movement trajectory of the target object;

[0097] Collision probability calculation module: used to calculate the probability of collision using the collision probability model based on the calculation results and the tracked target object motion trajectory;

[0098] Warning module: used to send a warning signal to the vehicle control system when the calculated collision probability exceeds a preset threshold;

[0099] Warning response module: After receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid collision.

[0100] The collision warning device for an electric unmanned vehicle provided in this application utilizes the collision warning method for an electric unmanned vehicle described in the aforementioned embodiments, and can address the technical issues inherent in conventional collision warning methods, which cannot meet the requirements for accurate and real-time collision warnings. Compared to the prior art, the beneficial effects of the collision warning device for an electric unmanned vehicle provided in this application are the same as those of the collision warning method for an electric unmanned vehicle provided in the aforementioned embodiments. Other technical features of the collision warning device for an electric unmanned vehicle are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0101] The present application provides a collision warning device for an electric unmanned vehicle, the collision warning device for the electric unmanned vehicle comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the collision warning method for the electric unmanned vehicle in the above-mentioned embodiment one.

[0102] Reference below Figure 4, which shows a schematic structural diagram of a collision warning device for an electric unmanned vehicle suitable for implementing an embodiment of the present application. The collision warning device for an electric unmanned vehicle in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and the like, as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The collision warning device for an electric unmanned vehicle shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0103] Figure 4 The collision warning device for an electric unmanned vehicle shown may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the collision warning device for an electric unmanned vehicle. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An 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 device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the collision warning device for an electric unmanned vehicle to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a collision warning device for an electric unmanned vehicle with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0104] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are performed.

[0105] The collision warning device for electric unmanned vehicles provided in this application utilizes the collision warning method for electric unmanned vehicles described in the aforementioned embodiments, and can address the technical issues with conventional collision warning methods, which lack the accuracy and real-time performance required for collision warnings. Compared to the prior art, the beneficial effects of the collision warning device for electric unmanned vehicles provided in this application are the same as those of the collision warning method for electric unmanned vehicles provided in the aforementioned embodiments. Other technical features of the collision warning device for electric unmanned vehicles are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0106] 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 appropriate manner in any one or more embodiments or examples.

[0107] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the collision warning method for an electric unmanned vehicle as described above.

[0108] The computer program product provided in this application can address the technical issues inherent in conventional collision warning methods, which often lack accuracy and real-time performance. Compared to existing technologies, the computer program product provided in this application offers the same beneficial effects as the collision warning method for electric unmanned vehicles provided in the aforementioned embodiments, and will not be further elaborated upon here.

[0109] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A collision warning method for an electric unmanned vehicle, characterized in that: The method comprises the following steps: Step S10: Acquire environmental information data and road condition information data around the vehicle in real time through sensors; Step S20: pre-processing the collected environmental information data to obtain valid data that can be used for subsequent analysis; Step S30: Calculating the predicted driving trajectory of the vehicle based on the obtained valid data and tracking the motion trajectory of the target object; Step S40: Calculating the probability of collision using a collision probability model based on the calculation result of step S30 and the tracked motion trajectory of the target object; Step S50: When the calculated collision probability exceeds a preset threshold, a warning signal is sent to the vehicle control system; Step S60: After receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid collision; The sensors refer to a variety of sensors installed on electric unmanned vehicles, including cameras, lidar, millimeter-wave radar, and ultrasonic sensors; the environmental information data around the vehicle includes the location, speed, and shape of obstacles; the road condition information data on the vehicle includes the degree of traffic congestion, visibility, and weather conditions; The construction of the collision probability model in step S40 includes defining variables, formulating hypotheses, determining conditional probability tables, constructing a Bayesian network structure, parameter learning, reasoning and prediction, and updating and optimization. The updating refers to updating the parameters in the Bayesian network, and the update formula used is shown in formula (1): Among them, P(Collision|Data) represents the collision probability under the condition of the vehicle surrounding environment information data collected by the given sensor, P(Data|Collision) represents the conditional probability of the vehicle surrounding environment information data collected by the sensor when a collision occurs, P(Collision) is the prior probability of collision, and P(Data) represents the prior probability of the vehicle surrounding environment information data collected by the sensor.

2. The collision warning method for an electric unmanned vehicle according to claim 1, characterized in that: The data preprocessing steps in step S20 include noise removal, missing value filling and feature extraction.

3. The collision warning method for an electric unmanned vehicle according to claim 1, characterized in that: In step S30, the predicted driving trajectory of the vehicle is calculated by formula (2): Where x(t) is the position of the vehicle at time t, x0 is the initial position, and v x is the initial velocity, a x is the acceleration.

4. The collision warning method for an electric unmanned vehicle according to claim 1, characterized in that: The process of tracking the motion trajectory of the target object in step S30 includes: Target tracking: Use multi-target tracking algorithm to track surrounding dynamic objects; Target correction: Update the speed and direction of the target object through the Kalman filter algorithm.

5. The collision warning method for an electric unmanned vehicle according to claim 4, characterized in that: The update formula of the Kalman filter algorithm is shown in formula (3): in, is the current estimated state, K k is the Kalman gain, z k is the measurement value, H is the measurement matrix, is the estimated state at the previous moment.

6. The collision warning method for an electric unmanned vehicle according to claim 1, characterized in that: The collision probability model in step S40 adopts a Bayesian network model. The Bayesian network integrates information data about the vehicle's surrounding environment collected by multiple sensors and evaluates the probability of a collision. The steps of constructing the collision probability model include: Define variables: Identify variables that can affect the probability of a collision, including the vehicle's surrounding environment, vehicle status, and obstacle information; Formulate hypotheses: Make assumptions about the relationships between variables based on how the vehicle's speed and the location of obstacles affect the likelihood of a vehicle crashing. Determine the conditional probability table: Based on the selected variables and assumptions, construct a conditional probability table to describe the dependency relationship between variables; Build Bayesian network structures: Use Bayesian network graphs to visualize variables and their dependencies; Parameter learning: Using existing data, the parameters of the constructed Bayesian network are estimated through maximum likelihood estimation or Bayesian Learning; Reasoning and prediction: Based on existing data and learned parameters, the system performs reasoning and prediction, and predicts the probability of a collision at a certain point in the future based on the information data about the vehicle's surroundings collected by sensors. Update and Optimize: Update parameters in Bayesian networks.

7. A collision warning device for an electric unmanned vehicle, characterized by: Data acquisition module: used to obtain environmental information data around the vehicle in real time through sensors; Data preprocessing module: used to preprocess the collected environmental information data to obtain valid data that can be used for subsequent analysis; Trajectory prediction and tracking module: used to calculate the vehicle's predicted trajectory based on the valid data obtained and track the movement trajectory of the target object; Collision probability calculation module: used to calculate the probability of collision using the collision probability model based on the calculation results and the tracked target object motion trajectory; Warning module: used to send a warning signal to the vehicle control system when the calculated collision probability exceeds a preset threshold; Warning response module: After receiving the warning signal, the vehicle control system takes corresponding emergency braking measures to avoid collision; The sensors in the data acquisition module refer to a variety of sensors installed on the electric unmanned vehicle, including cameras, lidar, millimeter-wave radar, and ultrasonic sensors; the environmental information data around the vehicle includes the location, speed, and shape of obstacles; the road condition information data on the vehicle includes the degree of traffic congestion, visibility, and weather conditions; The construction of the collision probability model in the collision probability calculation module includes defining variables, formulating hypotheses, determining conditional probability tables, constructing Bayesian network structures, parameter learning, reasoning and prediction, and updating and optimization. The updating refers to updating the parameters in the Bayesian network, and the update formula used is shown in formula (1): Among them, P(Collision|Data) represents the collision probability under the condition of the vehicle surrounding environment information data collected by the given sensor, P(Data|Collision) represents the conditional probability of the vehicle surrounding environment information data collected by the sensor when a collision occurs, P(Collision) is the prior probability of collision, and P(Data) represents the prior probability of the vehicle surrounding environment information data collected by the sensor.

8. A collision warning device for an electric unmanned vehicle, characterized in that: The collision warning device for an electric unmanned vehicle comprises: A memory, a processor, and a collision warning program for an electric unmanned vehicle stored in the memory and executable on the processor, wherein the collision warning program for the electric unmanned vehicle, when executed by the processor, implements a collision warning method for an electric unmanned vehicle as claimed in any one of claims 1 to 6.

9. A computer program product, characterized in that The computer program product includes a collision warning program for an electric unmanned vehicle, and when the collision warning program for an electric unmanned vehicle is executed by a processor, the collision warning method for an electric unmanned vehicle according to any one of claims 1 to 6 is implemented.

Images