BSD abnormity monitoring method based on integrated audible and visual alarm

Abstract

The invention provides a BSD abnormity monitoring method based on an integrated audible and visual alarm, and belongs to the field of automatic driving, according to the method, BSD radars or cameras are installed on the left side and the right side of a vehicle respectively, and meanwhile an audible and visual vibration alarm is integrated in a control system of the vehicle. Firstly, a machine learning anomaly recognition model is created, then a BSD system monitors the environment around a vehicle in real time, and the anomaly recognition model analyzes driving behaviors and the environment. Once the model predicts to be abnormal, the alarm sends out an acousto-optic vibration signal, and the automatic driving system adjusts a driving strategy in time according to an early warning signal to control the vehicle. According to the method, the safety of the automatic driving vehicle can be improved, and the risk of traffic accidents is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of autonomous driving, and more specifically relates to a BSD anomaly monitoring method based on an integrated sound and light alarm. Background Art

[0002] The Blind Spot Detection (BSD) system is now widely used in automobile safety driving assistance systems. It detects the presence of stray objects or other vehicles in the blind spots on the left and right sides of the vehicle, mainly to reduce or avoid accidents caused by blind spots.

[0003] Existing blind spot detection systems mostly use radar or cameras as detection devices. The data they collect primarily includes the distance between the vehicle and other objects, relative speed, and multi-dimensional features such as the object's size, shape, and color. This data is fed into a pre-defined anomaly detection model for training and prediction, providing early warning of potential dangers or abnormal behavior to ensure driving safety.

[0004] However, most existing systems suffer from insufficiently refined model training, low prediction accuracy, and inability to effectively detect anomalies in complex and ever-changing real-world driving environments. They often fail to meet the real-time demands of driving environments, and their single alarm method can easily lead to drivers ignoring them, failing to achieve the desired warning effect. Summary of the Invention

[0005] This invention employs a BSD anomaly monitoring method based on an integrated sound, light, and vibration alarm. It primarily uses the Isolation Forest algorithm as an anomaly detection model, specifically training the model on multi-dimensional features collected by BSD radar or cameras to improve prediction accuracy. It also optimizes the alarm method, employing a trinity of sound, light, and vibration to alert drivers, improving the timeliness and effectiveness of early warnings.

[0006] In order to achieve the above object, the present invention is implemented by adopting the following technical solutions: the method comprises:

[0007] Install BSD radars or cameras on the left and right sides of the vehicle, and integrate sound, light, and vibration alarms into the vehicle's control system;

[0008] Create an anomaly recognition model. Use historical driving data to create a machine learning anomaly recognition model.

[0009] Real-time monitoring and prediction,The BSD system monitors the environment around the vehicle in real time;,while;

[0010] The autonomous driving system adjusts the driving strategy in time according to the early warning signal, and controls the vehicle according to the alarm signal.

[0011] In one embodiment, the BSD radar is installed on the left and right sides of the vehicle;

[0012] An encapsulated sound, light and vibration alarm is integrated into the vehicle's control system; the alarm is installed on the instrument panel.

[0013] In one embodiment, creating an anomaly recognition model includes:

[0014] Collect historical driving data collected by BSD radar or cameras, including the distance between the vehicle and other objects, relative speed, and multi-dimensional features of the objects such as size, shape, and color;

[0015] Define the Isolation Forest algorithm model to identify outliers based on isolation properties; the evaluation function of the model is expressed as:

[0016] The path length h(x) is calculated by the following formula:

[0017] h(x)=E(n)+c(n)

[0018] Where E(n) is the path length from the root node to the leaf node in the isolation forest, n is the number of samples, and c(n) is the correction factor for the sample size n. The formula is:

[0019] c(n)=2*(ln(n-1)+0.5772156649)-(2*(n-1) / n)

[0020] In the model, this path length will be used to distinguish normal data from abnormal data: samples with shorter paths are considered abnormal samples, and samples with longer paths are considered normal samples;

[0021] Model training: Input the preprocessed historical driving data into the model for training;

[0022] Model evaluation: Use the model to make predictions on the training set and validation set, and compare the predicted results with the actual results;

[0023] Model optimization: Based on the results of model evaluation, adjust the model parameters, the number of trees, and the degree of sample isolation to optimize the model performance.

[0024] In one embodiment, the model training includes:

[0025] (1) Randomly select d feature subsets and construct d isolation trees to form an isolation forest;

[0026] (2) In each isolation tree, a feature is selected, and then a value between the minimum and maximum values ​​of the feature is randomly selected as the split point; the data with a feature value less than the split point is divided into the left subtree of the current node, and the data with a feature value greater than or equal to the split point is divided into the right subtree;

[0027] (3) Repeat (2) until the number of samples contained in a single leaf node is less than a certain threshold or the depth of the tree reaches the set maximum value.

[0028] In one embodiment, the model evaluation indicator is the outlier factor, which is calculated as follows:

[0029] OF(x)=2 -E[h(x)]

[0030] Where E[h(x)] is the average path length of sample x in all isolated trees. The closer the outlier factor is to 1, the more likely sample x is abnormal. A threshold is set to distinguish normal samples from abnormal samples.

[0031] In one embodiment, the real-time monitoring and prediction includes:

[0032] The BSD system uses radar or cameras to obtain real-time environmental information about the vehicle, including the location, speed, and direction of other vehicles. This data is represented as a multidimensional vector D = [x1, x2, ... xn], where n is the number of features and each xi represents a feature.

[0033] Data processing, filtering noise through Kalman filter;

[0034] The preprocessed data is input into the trained isolation forest model. The model calculates an outlier factor (OF) for each sample. After calculating the OF value of each sample, a threshold τ is set. When the OF value is greater than τ, the sample is considered an outlier, indicating a BSD anomaly.

[0035] When the model predicts an abnormal sample, an alarm is triggered; the alarm information is the sound, light and vibration signal emitted by the sound, light and vibration alarm.

[0036] In one embodiment, adjusting the driving strategy includes:

[0037] When the BSD radar detects an abnormality and issues an alarm through the sound, light, and vibration alarm, the autonomous driving system begins to respond;

[0038] The autonomous driving system interprets this signal and analyzes the specific factors that caused the abnormality, such as obstacles, pedestrians suddenly crossing the road, excessive lane changes, or other possible driving anomalies.

[0039] The autonomous driving system uses real-time monitoring data from BSD radar or cameras, including the vehicle's current position, speed, direction of travel, distance to other objects, and trends in these data, to obtain specific vehicle status and road environment information.

[0040] The autonomous driving system will perform emergency braking, automatic obstacle avoidance, automatic speed adjustment, and perform these control operations;

[0041] After receiving the sound, light and vibration alarm signals, the driver takes further action based on the response of the automatic driving system.

[0042] In one embodiment, the model optimization is achieved by selecting optimal parameters, wherein the main parameters are the number of trees and the maximum depth of each tree;

[0043] The number of trees is selected using cross-validation to select the optimal number of trees;

[0044] The maximum depth of each tree. For each isolated tree, its maximum depth limits the number of splits of the sample in the tree. The maximum depth is selected by cross-validation.

[0045] The objective function is as follows:

[0046] min L(n,d)=C(V(n,d))+lambda*C(n)

[0047] Where L(n,d) is the loss function, which represents the performance metric when there are n trees, each with a depth of d; V(n,d) is the performance of the model on the validation set; C(n) represents the model complexity, the number of trees, n; lambda is the regularization coefficient, which is used to balance performance and complexity; and the solution is solved using a greedy algorithm.

[0048] Beneficial effects of the present invention:

[0049] This paper proposes a BSD anomaly monitoring method based on integrated sound and light alarms. This method uses a BSD radar or camera to monitor the vehicle's surroundings in real time. It then integrates a machine-learning anomaly recognition model to analyze and predict driving behavior and the environment in real time. Furthermore, it uses sound, light, and vibration alarms to issue real-time alerts, allowing the autonomous driving system to respond immediately to BSD anomalies and adjust driving strategies. This method effectively improves the accuracy of BSD anomaly monitoring and the timeliness of early warnings, significantly reducing traffic accidents caused by driver blind spots, thereby improving driving safety and protecting the lives of drivers and passengers. It has high practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 Flow chart of the method of the present invention;

[0051] Figure 2 Create an anomaly identification model flow chart for the present invention;

[0052] Figure 3 This is a real-time monitoring and prediction flow chart of the present invention. DETAILED DESCRIPTION

[0053] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate exemplary embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0054] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0055] like Figure 1 As shown, the BSD anomaly monitoring method based on the integrated sound and light alarm includes:

[0056] S1. Install BSD radars or cameras on the left and right sides of the vehicle, and integrate sound, light and vibration alarms into the vehicle's control system.

[0057] First, BSD radars or cameras need to be installed on the left and right sides of the vehicle to detect and monitor the vehicle's blind spots. These two devices are generally fixed to the vehicle's rearview mirrors or taillights, and they must ensure that they have sufficient observation range and can operate clearly in all weather and road conditions.

[0058] Secondly, encapsulated audible, visual, and vibration alarms should be integrated into the vehicle's control system. The installation location of the alarm should fully consider driver comfort and the effectiveness of the alarm signal. Consider installing it in a location that is intuitive to the driver, such as the instrument panel, so that the driver can immediately notice the alarm signal.

[0059] S2. Create an anomaly recognition model. Use historical driving data to create a machine learning anomaly recognition model. Isolation Forest is an unsupervised learning algorithm based on decision trees. It performs better than typical ensemble methods for outlier detection. This model is computationally efficient when processing large datasets and does not require data normalization, making it more adaptable to real-world data distribution. Furthermore, Isolation Forest is more resilient to datasets with multi-dimensional features, making it a better candidate for outlier detection than distance- or density-based anomaly detection algorithms.

[0060] The key idea behind the Isolation Forest algorithm is that outliers are easier to distinguish within a decision tree because they are often more isolated in feature space. Compared to normal data, outliers have shorter paths within the tree, meaning they are isolated earlier. This, in turn, results in greater sensitivity in identifying outliers. This can be used to build a BSD anomaly detection model and provide early warning of potential anomalies.

[0061] like Figure 2 As shown, the creation of the anomaly recognition model includes:

[0062] S201. Collect historical driving data collected by BSD radars, cameras, and other devices, including the distance between the vehicle and other objects, relative speed, and multi-dimensional features such as object size, shape, and color. The data undergoes certain preprocessing, such as denoising and missing value filling, to ensure data quality.

[0063] S202. Define the Isolation Forest algorithm model. Its main idea is to identify outliers based on their isolation properties. Specifically, a randomly selected feature and a randomly selected cutpoint value are used to recursively generate an isolation tree. Normal samples have a relatively long average path length in the isolation tree, while outliers have a shorter average path length due to their greater distance from other samples and different characteristics. Specifically, the evaluation function of this model can be expressed as:

[0064] The path length h(x) is calculated by the following formula:

[0065] h(x)=E(n)+c(n)

[0066] Where E(n) is the path length from the root node to the leaf node in the isolation forest, n is the number of samples, and c(n) is the correction factor for the sample size n. The formula is:

[0067] c(n)=2*(ln(n-1)+0.5772156649)-(2*(n-1) / n)

[0068] In the model, this path length will be used to distinguish normal data from abnormal data: samples with shorter paths are considered abnormal samples, and samples with longer paths are considered normal samples.

[0069] S203, model training: inputting the pre-processed historical driving data into the model for training;

[0070] The model training includes:

[0071] (1) Randomly select d feature subsets and construct d isolation trees to form an isolation forest;

[0072] The Isolation Forest algorithm first randomly selects a subset of all training data. Each subset is used to generate a decision tree, thus forming a forest. Assuming the number of selected subsets (i.e., the number of decision trees) is t, and the number of samples in a subset is ψ, we can randomly select ψ samples with replacement from the total number of n samples to form t subsets. The construction of feature subsets can be implemented using the Fisher-Yates algorithm, which has a time complexity of O(d), where d is the feature dimension.

[0073] (2) In each isolation tree, a feature is selected, and then a value between the minimum and maximum values ​​of the feature is randomly selected as the split point; the data with a feature value less than the split point is divided into the left subtree of the current node, and the data with a feature value greater than or equal to the split point is divided into the right subtree.

[0074] Then, in each isolated tree, a feature dimension i is randomly selected (the range of feature dimensions is 1 to d), and a cutoff value p is randomly selected within the value range [min, max] for that feature. A decision rule is generated based on the selected feature and its corresponding cutoff value. A feature i is randomly selected from the d features, and a cutoff value p is randomly selected between the maximum and minimum values ​​of feature i.

[0075] (3) Split the data according to the decision rule determined in step (2) to form left and right subtrees. Recursively execute steps (2) and (3) on the left and right subtrees respectively. Go down the decision tree. When the termination condition is met (the size of the data set is less than a certain threshold or the depth of the decision tree reaches the set maximum depth), stop splitting and return a single node as the subtree.

[0076] If the dataset size is less than a certain threshold or the decision tree depth reaches the maximum depth, a single node is returned as a subtree; otherwise, the dataset is split into two parts according to the decision rule determined in step (2), which serve as the left and right subtrees of the current node respectively.

[0077] The above is the model training process of the isolation forest. After such training, each sample will have an average path length on all decision trees in the forest. This length can be used to quantify the normality of the sample. A lower average path length means that the sample is more likely to be an outlier.

[0078] S204, Model Evaluation: Use the model to predict the training set and validation set, and compare the predicted results with the actual results;

[0079] The indicator of model evaluation is the outlier factor, which is calculated as follows:

[0080] OF(x)=2 -E[h(x)]

[0081] Where E[h(x)] is the average path length of sample x in all isolated trees. The closer the outlier factor is to 1, the more likely sample x is abnormal. A threshold is set to distinguish normal samples from abnormal samples.

[0082] S205, Model Optimization: Based on the results of the model evaluation, adjust the model parameters, such as the number of trees and the degree of sample isolation, to optimize the model performance. Model optimization is achieved by selecting optimal parameters, with two main parameters being the number of trees and the maximum depth of each tree.

[0083] Number of trees: Use cross-validation to select the optimal number of trees. For example, split the dataset into training and validation sets, train and validate with different numbers of trees, record the model performance (such as AUC, accuracy, etc.) in each case, and finally select the number of trees with the best performance. However, be aware that increasing the number of trees increases computational complexity, so a balance between performance and computational complexity must be struck in practical applications.

[0084] Maximum depth of each tree: For each isolated tree, its maximum depth limits the number of splits a sample can undergo within the tree. Generally speaking, a greater depth improves the expressiveness of the model, but excessively deep trees can lead to overfitting. Therefore, selecting the maximum depth also requires cross-validation. The process is similar to selecting the number of trees: record the model performance at different depths and select the depth that performs best.

[0085] The objective function is as follows:

[0086] min L(n,d)=C(V(n,d))+lambda*C(n)

[0087] Where L(n,d) is the loss function, which represents the performance metric when there are n trees, each with a depth of d; V(n,d) is the performance of the model on the validation set; C(n) represents the model complexity, the number of trees, n; lambda is the regularization coefficient, which is used to balance performance and complexity; and the solution is solved using a greedy algorithm.

[0088] like Figure 3 As shown, S3, real-time monitoring and prediction, the BSD system monitors the environment around the vehicle in real time.

[0089] S301. Data Acquisition: The BSD system uses radar or cameras to acquire real-time information about the vehicle's surroundings, including the location, speed, and direction of other vehicles. This data can be represented as a multidimensional vector D = [x1, x2, ..., xn], where n is the number of features and each xi represents a feature, such as location or speed.

[0090] S302, Data Processing: Since the real-time collected data contains noise, pre-processing is required, such as denoising and normalization, to make the data more suitable for model analysis. For example, the noise can be filtered out using a filter, such as a Kalman filter.

[0091] S303. Model Prediction: The preprocessed data is fed into the trained isolation forest model. The model calculates an anomaly score (outlier factor, OF) for each sample. The OF calculation formula for the isolation forest model is: OF(x) = 2^-E(h(x)), where E(h(x)) is the average path length of sample x across all isolated trees. After calculating the OF value for each sample, a threshold τ can be set. When the OF value is greater than τ, the sample is considered an outlier, indicating a BSD anomaly.

[0092] S304, abnormal warning: When the model predicts an abnormal sample, an alarm is triggered. The alarm information can be an audible and visual vibration signal emitted by an audible and visual vibration alarm, or an abnormal information displayed by the control system.

[0093] S4. The autonomous driving system adjusts the driving strategy in a timely manner according to the early warning signal, and controls the vehicle according to the alarm signal.

[0094] When the BSD system detects an abnormality and sounds an alarm through the sound, light and vibration alarm, the automatic driving system begins to respond.

[0095] The autonomous driving system will immediately receive this abnormal alarm signal and begin to analyze the signal to understand the specific factors that caused the abnormality, such as obstacles, pedestrians suddenly crossing the road, lane changes too frequently, or other possible driving abnormalities.

[0096] At the same time, the autonomous driving system will refer to real-time monitoring data from BSD radar or cameras, such as the vehicle's current position, speed, driving direction, distance to other objects, and changing trends of these data, to obtain specific vehicle status and road environment information.

[0097] Based on this information, the autonomous driving system will select the most appropriate handling method according to pre-programmed decision-making strategies, such as emergency braking, automatic obstacle avoidance, automatic speed adjustment, etc., and execute these control operations so that the vehicle can remain stable and safe in abnormal situations.

[0098] After receiving the sound, light and vibration alarm signal, the driver can take further actions based on the response of the automatic driving system, such as emergency braking, steering avoidance, etc. in conjunction with the control of the automatic driving system, so that driving safety is further ensured.

[0099] Example 1

[0100] The method of the present invention is used to monitor and alarm the BSD anomaly of a certain car.

[0101] First, a BSD radar is installed on each side of the car, and an audible, visual and vibration alarm is integrated into the car's control system. The alarm is installed in a position where the driver can clearly see and hear it, such as in the dashboard.

[0102] Next, historical driving data is collected for model training. For each drive, the BSD radar collects the vehicle's driving data, including the distance and relative speed between the vehicle and other objects, as well as the size, shape, and color of the objects. For example, the previous driving data records information such as the distance and speed to 1,000 other vehicles. After preprocessing, this data forms a training set containing 1,000 samples. Each sample is a multidimensional vector, with each dimension corresponding to a feature. For example, the sample (50m, 60km / h, 1.8m, 4.5m, "red") indicates that the distance to the other vehicle is 50 meters, the relative speed is 60km / h, and the other vehicle is 1.8 meters long, 4.5 meters wide, and red in color.

[0103] Next, we create an isolation forest model for training. Here, we set the parameters for the isolation forest model as follows: the number of trees is 100, and the maximum depth of each tree is 8. Based on these parameters, we create an isolation forest model and input the training set for model training.

[0104] Once training is complete, driving behavior and the environment can be monitored and predicted in real time. For example, during a particular drive, the BSD radar acquired real-time information about the vehicle's surroundings, detecting an object 30 meters to the right, traveling at a relative speed of 80 km / h, measuring 2.0 m x 1.5 m, and colored blue. This multidimensional vector was input into the model and received an anomaly score of 0.65, exceeding the preset threshold of 0.5. Therefore, the sample was identified as an anomaly, and the audible, visual, and vibration alarms immediately issued a warning signal.

[0105] The car's autonomous driving system received the signal, analyzed it, and detected an object approaching rapidly from the right. It then adjusted its driving strategy, slowing down and making an evasive move based on real-time radar data, thus avoiding a potential collision.

[0106] Therefore, the method of the present invention plays a good role in BSD abnormality monitoring and alarm, ensuring driving safety.

[0107] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0108] It should be understood that the detailed description of the technical solutions of the present invention using the preferred embodiments above is illustrative and not restrictive. A person skilled in the art, after reading the present specification, may modify the technical solutions described in the embodiments or replace some of the technical features therein with equivalents; such modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A BSD abnormality monitoring method based on an integrated sound and light alarm, characterized in that: The method includes: Install BSD radar or cameras on the left and right sides of the vehicle, and integrate sound, light and vibration alarms into the vehicle's control system; Create an anomaly recognition model, create a machine learning anomaly recognition model; Real-time monitoring and prediction: real-time monitoring of the environment around the vehicle; The autonomous driving system adjusts the driving strategy in time according to the early warning signals, and controls the vehicle according to the alarm signals.

2. The BSD abnormality monitoring method based on an integrated sound and light alarm according to claim 1, characterized in that: The BSD radar is installed on the left and right sides of the vehicle; A packaged sound, light and vibration alarm is integrated into the vehicle's control system; the alarm is installed on the instrument panel.

3. The BSD abnormality monitoring method based on an integrated sound and light alarm according to claim 1, characterized in that: The creation of an abnormality recognition model includes: Collect historical driving data collected by BSD radar or camera, including the distance between the vehicle and other objects, relative speed, and multi-dimensional features of the size, shape, and color of the objects; Define the Isolation Forest algorithm model to identify outliers based on isolation properties; the evaluation function of the model is expressed as: The path length h(x) is calculated by the following formula: h(x)=E(n)+c(n) Among them, E(n) is the path length from the root node to the leaf node in the isolation forest, n is the number of samples, and c(n) is the correction factor of the sample size n. The formula is: c(n)=2*(ln(n-1)+0.5772156649)-(2*(n-1) / n) In the model, this path length is used to distinguish normal data from abnormal data: samples with shorter paths are considered abnormal samples, and samples with longer paths are considered normal samples; Model training: input the preprocessed historical driving data into the model for training; Model evaluation: Use the model to predict the training set and validation set, and compare the predicted results with the actual results; Model optimization: Based on the results of model evaluation, adjust the model parameters, the number of trees, the degree of sample isolation, and optimize the performance of the model.

4. The BSD abnormality monitoring method based on an integrated sound and light alarm according to claim 3 is characterized in that: The model training includes: (1) Randomly select d feature subsets and construct d isolation trees to form an isolation forest; (2) In each isolation tree, select a feature, and then randomly select a value between the minimum and maximum values ​​of the feature as the split point; the data with feature values ​​less than the split point are divided into the left subtree of the current node, and the data with feature values ​​greater than or equal to the split point are divided into the right subtree; (3) Repeat (2) until the number of samples contained in a single leaf node is less than a certain threshold or the depth of the tree reaches the set maximum value.

5. The BSD abnormality monitoring method based on integrated sound and light alarm according to claim 3 is characterized in that: The indicator of model evaluation is the outlier factor, which is calculated as follows: OF(x)=2 -E[h(x)] Among them, E[h(x)] is the average path length of sample x in all isolated trees. The closer the outlier factor is to 1, the more abnormal the sample x is. A threshold is set to distinguish normal samples from abnormal samples.

6. The BSD abnormality monitoring method based on integrated sound and light alarm according to claim 1 is characterized in that: The real-time monitoring and prediction include: Real-time acquisition of environmental information around the vehicle, including the location, speed, and driving direction of other vehicles; represented as a multidimensional vector D = [x1, x2, ... xn], where n is the number of features and each xi represents a feature; Data processing, filtering data noise through Kalman filter; The processed data is input into the trained isolation forest model, and an outlier score, namely the outlier factor OF, is calculated for each sample. After calculating the OF value of each sample, a threshold τ is set. When the OF value is greater than τ, the sample is considered to be an abnormal sample, that is, there is a BSD anomaly. When the model predicts an abnormal sample, an alarm is triggered; the alarm information is the sound, light and vibration signal emitted by the sound, light and vibration alarm.

7. The BSD abnormality monitoring method based on integrated sound and light alarm according to claim 1 is characterized in that: The adjusting driving strategy includes: When the BSD radar detects an abnormality and sounds an alarm through the sound, light and vibration alarm, the autopilot system begins to respond; The autonomous driving system interprets this signal and analyzes the specific factors that caused the abnormality, including obstacles, pedestrians suddenly crossing the road, lane switching too frequently, or other driving abnormalities; The autonomous driving system refers to the real-time monitoring data from the BSD radar or camera, the vehicle's current position, speed, driving direction, distance to other objects, and the changing trends of these data to obtain specific vehicle status and road environment information; The autonomous driving system can perform emergency braking, automatic obstacle avoidance, and automatic speed adjustment; After receiving the sound, light and vibration alarm signals, the driver can take further actions based on the response of the automatic driving system.

8. The BSD abnormality monitoring method based on integrated sound and light alarm according to claim 3 is characterized in that: The model optimization is achieved by selecting the best parameters, there are two parameters, the number of trees and the maximum depth of each tree; The number of trees is selected using cross-validation. The maximum depth of each isolated tree limits the number of splits of a sample in the tree; the maximum depth is selected by cross-validation; The objective function is as follows: min L(n,d)=C(V(n,d))+lambda*C(n) Among them, L(n,d) is the loss function, which represents the performance measure when there are n trees and each tree has a depth of d; V(n,d) is the performance of the model on the validation set, C(n) represents the model complexity, the number of trees n; lambda is the regularization coefficient, which is used to balance performance and complexity; it is solved by the greedy algorithm method.

Images