A method for controlling the movement trajectory of a tidal robot

Abstract

The present invention discloses a method for controlling the movement trajectory of a tidal robot, relating to the field of tidal robot trajectory control. The method generates a target diversion position and several movement trajectories by comprehensively analyzing road data, initial traffic image data, and the initial position of the tidal robot. The reliability index of each road section is calculated in combination with real-time trajectory image data, and an optimization analysis is performed to select the path with the highest reliability, allowing the tidal robot to accurately reach the target diversion position. The method analyzes the road data and initial traffic image data of the road where the tidal robot is located, and combines this with a route planning algorithm to dynamically plan the optimal path for the robot from its initial position coordinates to the target diversion position coordinates. The method can automatically adjust the planning of movement points and trajectory sections according to different road conditions, overcoming the drawback of traditional path planning's reliance on static paths and ensuring the scientific and real-time nature of trajectory planning.

Description

Technical Field

[0001] The present invention relates to the field of tidal robot trajectory control, and in particular to a method for controlling the movement trajectory of a tidal robot. Background Art

[0002] Tidal robots are dynamic devices used in intelligent transportation systems. They aim to optimize traffic flow by adjusting road resource allocation. Their name comes from the regular changes in tidal phenomena. These robots adapt to changes in traffic demand by dynamically adjusting the direction, number or use of lanes during specific periods, similar to the rise and fall of the tide. Tidal robots are usually equipped with high-precision positioning equipment, sensors and communication modules. With the development of intelligent transportation systems, tidal robots, as a dynamic traffic optimization device, are widely used in scenarios to alleviate traffic congestion. Tidal robots dynamically adjust road resource allocation to achieve vehicle diversion during peak hours and optimize road traffic efficiency.

[0003] Prior art, such as patent application publication number CN109857108B, discloses a mobile robot trajectory tracking method and system based on an internal model control algorithm. The method comprises the following steps: obtaining the state variables of the mobile robot at a specific moment, including the state variables of the motion trajectory, the state variables of the odometer, and the state variables of the mobile robot; obtaining the deviation between the actual motion trajectory and the preset motion trajectory using the motion trajectory, odometer, and state variables; using the obtained deviation as input to an internal model controller to obtain an output at the corresponding moment; transmitting the output to the mobile robot's motor, obtaining the state variables of the odometer at the next moment, and obtaining a predicted value of the mobile robot's state variables at the next moment based on the mobile robot's kinematic equations. The method and system of the present invention achieve an improved internal model control robot trajectory with low computational complexity and good real-time performance.

[0004] Based on the above solution, it is found that the limitations of the existing technology include at least the following problems. First, the existing technology lacks a comprehensive analysis of actual road data and robot behavior in complex dynamic traffic environments, which easily leads to error accumulation in traffic environment applications, and ignores many factors such as road dynamic characteristics, real-time traffic conditions, and path planning reliability, causing the robot's movement trajectory to deviate from the preset trajectory, affecting the accuracy and stability of trajectory tracking. Second, the existing technology has difficulty in reliability evaluation and optimization selection of multiple candidate paths for the movement trajectory, and thus it is difficult to adapt to real-time changing traffic conditions and complex road environments, which easily leads to inflexible trajectory planning and reduces the robot's adaptability in dynamic environments. At the same time, the existing technology's planning of the robot's target diversion position coordinates is only based on static settings, and fails to fully combine the road environment and traffic conditions to dynamically optimize and comprehensively analyze the movement path, resulting in inefficiency of the robot in path diversion, and thus it is difficult to improve the overall traffic efficiency of the traffic road. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a mobile trajectory control method for a tidal robot, which solves the problem that the existing technology lacks comprehensive analysis of actual road data and robot behavior in complex dynamic traffic environments, which easily leads to error accumulation in traffic environment applications, and ignores many factors such as road dynamic characteristics, real-time traffic conditions and path planning reliability, thereby causing the robot's mobile trajectory to deviate from the preset trajectory, affecting the accuracy and stability of trajectory tracking. Secondly, it is difficult for the existing technology to perform reliability evaluation and optimization selection on multiple candidate paths of the mobile trajectory, and thus it is difficult to adapt to real-time changing traffic conditions and complex road environments, which easily leads to inflexible trajectory planning and reduces the robot's adaptability in dynamic environments. At the same time, the existing technology only plans the robot's target diversion position coordinates based on static settings, and fails to fully combine the road environment and traffic conditions to dynamically optimize and comprehensively analyze the mobile path, resulting in the robot being inefficient in path diversion, and thus it is difficult to improve the overall traffic efficiency of the traffic road.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for controlling the movement trajectory of a tidal robot, comprising the following steps: obtaining road data, initial traffic image data and initial position coordinates of the tidal robot within a set traffic road, and performing preprocessing, wherein the road data are specifically the road width value, road length value, starting point position coordinates and end point position coordinates of each traffic section, the initial traffic image data are specifically the pixel value and two-dimensional position coordinates of each pixel point in the traffic image, and the initial position coordinates are specifically the initial three-dimensional vertical position coordinate value, the initial three-dimensional horizontal position coordinate value and the initial three-dimensional height position coordinate value; performing data analysis on the preprocessed road data and initial traffic image data within the set traffic road to obtain the target diversion position coordinates of the tidal robot arriving at the set traffic road, and combining the route planning algorithm to control the tidal robot. The robot's initial position coordinates and the target diversion position coordinates when arriving at the set traffic road are comprehensively analyzed to obtain several moving trajectories of the tidal robot in the set traffic road; each moving trajectory of the tidal robot in the set traffic road is divided into sections to obtain several moving sections of each moving trajectory of the tidal robot in the set traffic road; the trajectory image data of each moving section of each moving trajectory of the tidal robot in the set traffic road is obtained in real time, and a comprehensive analysis is performed to obtain the reliability index of each moving section of each moving trajectory of the tidal robot in the set traffic road, wherein the trajectory image data specifically includes the trajectory pixel value and the trajectory two-dimensional position coordinates of each trajectory pixel point; the reliability index of each moving section of each moving trajectory of the tidal robot in the set traffic road is comprehensively analyzed in real time, and trajectory adjustment measures are taken based on the analysis results.

[0007] The present invention has the following beneficial effects:

[0008] (1) The mobile trajectory control method of the tidal robot analyzes the road data and initial traffic image data of the road where the tidal robot is located, and combines the route planning algorithm to dynamically plan the optimal path of the robot from the initial position coordinates to the target diversion position coordinates, so that the planning of the moving point and the trajectory section can be automatically adjusted according to different road conditions, overcoming the defect of traditional path planning that relies on static paths, ensuring the scientificity and real-time nature of trajectory planning, and improving the robot's adaptability to complex traffic scenes.

[0009] (2) The mobile trajectory control method of the tidal robot obtains trajectory image data in real time and calculates the reliability index of the trajectory, evaluating the safety and effectiveness of each mobile trajectory from multiple dimensions, thereby effectively identifying potential risks and obstacles, and eliminating inappropriate paths based on reliability evaluation, ensuring that the tidal robot always chooses the optimal path to operate, thereby improving the accuracy of trajectory evaluation, significantly reducing the risk of path failure, and ensuring the operational stability of the tidal robot.

[0010] (3) The mobile trajectory control method of the tidal robot formulates a control strategy based on the reliability index analysis results of each mobile trajectory, thereby achieving refined management of the tidal robot's operating status, and by dynamically adjusting the control strategy, it can effectively respond to sudden traffic conditions or trajectory obstacles, ensuring that the robot is always in the optimal operating state. In addition, through real-time feedback adjustment strategy, the tidal robot can efficiently complete the diversion task in complex traffic roads, and comprehensively improve the task execution effect and resource utilization.

[0011] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a flow chart of a method for controlling the movement trajectory of a tidal robot according to the present invention.

[0013] Figure 2 This is a flow chart of the steps of obtaining the target diversion position coordinates of the tidal robot within a set traffic road in a movement trajectory control method of the tidal robot of the present invention. DETAILED DESCRIPTION

[0014] The embodiment of the present application solves the problem that the existing technology lacks comprehensive analysis of actual road data and robot behavior in complex dynamic traffic environments through a mobile trajectory control method for a tidal robot, which easily leads to error accumulation in traffic environment applications and ignores many factors such as road dynamic characteristics, real-time traffic conditions and path planning reliability, causing the robot's movement trajectory to deviate from the preset trajectory, affecting the accuracy and stability of trajectory tracking. Secondly, it is difficult for the existing technology to perform reliability evaluation and optimization selection on multiple candidate paths of the movement trajectory, and thus it is difficult to adapt to real-time changing traffic conditions and complex road environments, which easily leads to inflexible trajectory planning and reduces the robot's adaptability in dynamic environments. At the same time, the existing technology's planning of the robot's target diversion position coordinates is only based on static settings, and fails to fully combine the road environment and traffic conditions to dynamically optimize and comprehensively analyze the movement path, resulting in the robot's inefficiency in path diversion, and thus it is difficult to improve the overall traffic efficiency of the traffic road.

[0015] The overall approach to the problems in the embodiments of this application is as follows:

[0016] First, the road data, initial traffic image data and initial position coordinates of the tidal robot in the set traffic road are obtained, the collected data are preprocessed, and the preprocessed data are comprehensively analyzed to generate the target diversion position coordinates of the tidal robot in the set traffic road. Combined with the route planning algorithm, the initial position coordinates and the target diversion position coordinates of the tidal robot are comprehensively analyzed to obtain several moving trajectories of the tidal robot in the set traffic road, and each trajectory is divided into sections to obtain multiple moving sections. By acquiring the trajectory image data of each section of each trajectory in real time, the reliability index of each moving section of each moving trajectory of the tidal robot in the set traffic road is obtained. Finally, the reliability index of the first moving section of each moving trajectory is analyzed first, and the best path is selected as the optimal trajectory. Then, the reliability index of each subsequent section is continued to be comprehensively analyzed and optimized until the tidal robot reaches the target diversion position coordinates in the set traffic road.

[0017] See also Figure 1, an embodiment of the present invention provides a technical solution: a method for controlling the movement trajectory of a tidal robot, comprising the following steps: obtaining road data, initial traffic image data and initial position coordinates of the tidal robot within a set traffic road (in this embodiment, all three-dimensional position coordinates are based on the device that takes the initial traffic image as the origin, the X-axis points to the right side of the device, from the perspective of the device, the Y-axis points to the front of the device, that is, from the position of the device, pointing to the target object or the farther direction in the scene, and the Z-axis represents the vertical height of the vehicle or obstacle relative to the ground), and pre-processing, wherein the road data is specifically for each The road width value, road length value, starting point position coordinates of the traffic section (i.e., the starting three-dimensional vertical position coordinate value of the section, the starting three-dimensional horizontal position coordinate value of the section, and the starting three-dimensional height position coordinate value of the section), and the end point position coordinates of the section (i.e., the end point three-dimensional vertical position coordinate value of the section, the end point three-dimensional horizontal position coordinate value of the section, and the end point three-dimensional height position coordinate value of the section). The initial traffic image data specifically includes the pixel value and two-dimensional position coordinates of each pixel point in the traffic image (with the upper left corner of the image as the origin of the two-dimensional position coordinate system, and the X axis: points to the horizontal direction of the image (from left to right), and the Y axis: points to the vertical direction of the image ( From top to bottom), the initial position coordinates are specifically the initial three-dimensional vertical position coordinate value, the initial three-dimensional horizontal position coordinate value, and the initial three-dimensional height position coordinate value; the pre-processed road data and the initial traffic image data in the set traffic road are analyzed to obtain the target diversion position coordinates of the tidal robot arriving at the set traffic road, and the initial position coordinates of the tidal robot and the target diversion position coordinates of the tidal robot arriving at the set traffic road are comprehensively analyzed in combination with the route planning algorithm to obtain several movement trajectories of the tidal robot in the set traffic road; each movement trajectory of the tidal robot in the set traffic road is analyzed separately The road segments are divided to obtain several moving sections of each moving trajectory of the tidal robot in the set traffic road; the trajectory image data of each moving section of each moving trajectory of the tidal robot in the set traffic road is obtained in real time, and a comprehensive analysis is performed to obtain the reliability index of each moving section of each moving trajectory of the tidal robot in the set traffic road, wherein the trajectory image data specifically includes the trajectory pixel value and the trajectory two-dimensional position coordinates of each trajectory pixel point; the reliability index of each moving section of each moving trajectory of the tidal robot in the set traffic road is comprehensively analyzed in real time, and trajectory adjustment measures are taken based on the analysis results.

[0018] Specifically, if Figure 2As shown, the specific steps for obtaining the target diversion position coordinates of the tidal robot in the set traffic road are as follows: the pixel value and two-dimensional position coordinates of each pixel point in the image in the set traffic road are input into the pre-established target detection model for comprehensive analysis to obtain the vehicle two-dimensional position coordinates, vehicle confidence of several vehicle prediction bounding boxes in the set traffic road and the obstacle two-dimensional position coordinates and obstacle confidence of several obstacle prediction bounding boxes; the vehicle prediction two-dimensional position coordinates, vehicle prediction confidence of each vehicle prediction bounding box in the set traffic road and the obstacle prediction two-dimensional position coordinates and obstacle confidence of each obstacle prediction bounding box are comprehensively analyzed in combination with the non-maximum suppression method to obtain the vehicle two-dimensional position coordinates of several vehicle boundary boxes in the set traffic road and the obstacle two-dimensional position coordinates of several obstacle boundary boxes; the vehicle two-dimensional position coordinates of each vehicle boundary box in the set traffic road and the obstacle two-dimensional position coordinates of each obstacle boundary box are comprehensively analyzed. The three-dimensional position coordinates of each vehicle boundary box and the three-dimensional position coordinates of each obstacle boundary box in the set traffic road are obtained, wherein the three-dimensional position coordinates of the vehicle are the three-dimensional vertical position coordinate value, the three-dimensional horizontal position coordinate value, and the three-dimensional height position coordinate value of the vehicle, and the three-dimensional position coordinates of the obstacle are the three-dimensional vertical position coordinate value, the three-dimensional horizontal position coordinate value, and the three-dimensional height position coordinate value of the obstacle; the three-dimensional position coordinates of each vehicle boundary box and the three-dimensional position coordinates of each obstacle boundary box in the set traffic road are comprehensively analyzed with the road width and road length values of each traffic section to obtain the congestion index of each traffic section in the set traffic road; the congestion index of each traffic section in the set traffic road is arranged in descending order to generate a congestion arrangement section table, and the section starting point position coordinates of the first sequence of sections are marked as target diversion position coordinates.

[0019] The specific process of obtaining the vehicle 2D position coordinates of several vehicle bounding boxes and the obstacle 2D position coordinates of several obstacle bounding boxes within the set traffic road is as follows: the vehicle prediction confidence of each vehicle prediction bounding box and the obstacle prediction confidence of each obstacle prediction bounding box are sorted in descending order, and the prediction bounding box and obstacle prediction bounding box with the vehicle prediction confidence, obstacle prediction confidence and obstacle prediction bounding box in the first sequence are selected as the "reference box". The overlap with other bounding boxes is calculated. If the overlap between the current bounding box and the reference box is greater than a preset threshold (such as 0.5), it is considered that the two boxes overlap too much and the box with high overlap is deleted. Otherwise, the box is retained and the bounding boxes that have not been deleted are used as new candidate boxes. The box with the highest confidence is then selected for the next round of suppression until all boxes are processed. The vehicle prediction 2D position coordinates, vehicle prediction confidence of several vehicle prediction bounding boxes, and obstacle prediction 2D position coordinates and obstacle prediction confidence of several obstacle prediction bounding boxes are marked as the vehicle 2D position coordinates of each vehicle bounding box and the obstacle 2D position coordinates of each obstacle bounding box.

[0020] The specific process of obtaining the vehicle three-dimensional position coordinates of each vehicle bounding box within the set traffic road is: obtaining the horizontal focal length value, vertical focal length value, horizontal resolution value, vertical resolution value, physical width value of the sensor (in the shooting device), physical height value of the sensor (in the shooting device) and the vehicle depth information value corresponding to each vehicle pixel point in each vehicle bounding box of the corresponding shooting device within the set traffic road, and performing comprehensive analysis to obtain the vehicle three-dimensional vertical position coordinate value and vehicle three-dimensional horizontal position coordinate value of each vehicle pixel point in each vehicle bounding box within the set traffic road, and using the vehicle depth information value corresponding to the vehicle pixel point as the vehicle three-dimensional height value, and marking it as the vehicle three-dimensional position coordinates of each vehicle pixel point in each vehicle bounding box within the set traffic road.

[0021] The specific process of obtaining the three-dimensional position coordinates of each obstacle boundary box within the set traffic road is consistent with the process of obtaining the three-dimensional position coordinates of each vehicle boundary box, and the calculation logic and calculation formula are consistent.

[0022] In this implementation, the accuracy of vehicle and obstacle detection is improved by introducing a target detection model and combining it with the non-maximum suppression method to screen and optimize bounding boxes. The non-maximum suppression method effectively removes redundant and overlapping bounding boxes, retains the optimal detection results, and ensures that the final output two-dimensional position coordinates have high confidence, thereby avoiding detection errors caused by overlap and noise. This in turn improves the tidal robot's ability to identify the traffic environment and the accuracy of path planning. Secondly, by comprehensively utilizing the physical parameters of the camera equipment (such as horizontal focal length, resolution, and sensor size) and depth information, a mapping relationship from two-dimensional to three-dimensional is established for vehicles and obstacles, thereby ensuring the accuracy of three-dimensional spatial data and providing strong spatial information support for subsequent path planning and congestion analysis. Finally, based on the three-dimensional position coordinate data of vehicles and obstacles and the width and length information of the road, the congestion index of each road section is quantified, and a congested road section table is generated by sorting in descending order. This enables the tidal robot to prioritize sections with heavy traffic pressure and determine target diversion points. It also fully considers the dynamic characteristics of traffic and can adjust the diversion strategy in real time, thereby improving the overall efficiency of traffic flow and alleviating congestion problems.

[0023] Specifically, the target detection model is a convolutional neural network model, and the pre-establishment steps of the target detection model are as follows: obtaining several groups of initial traffic image data within a set traffic road, and establishing a traffic data set, and dividing the traffic data set into a traffic training data set and a traffic verification data set; initializing the convolutional neural network model, specifically initializing the connection weights of each layer in the convolutional neural network model (the "connection strength" between the input signal of each layer of neurons and the output signal of the previous layer); training the pre-established target detection model based on the traffic training data set, and calculating the traffic regression loss function; and evaluating the performance of the target detection model based on the traffic verification data set, and adjusting the model parameters according to the verification results until the model prediction results meet the expected standards.

[0024] It should be explained that the convolutional neural network model includes an input layer, a feature extraction layer, a candidate box layer, a bounding box regression and classification layer, and an output layer.

[0025] The input layer is used to receive the input image and normalize it to suit the network requirements.

[0026] The feature extraction layer is used to extract features from the input image through convolution and pooling operations.

[0027] The candidate box layer is used to generate candidate boxes based on features and locate areas where objects may exist.

[0028] The bounding box regression and classification layer is used to accurately locate and classify the candidate box and output the bounding box and category of the target.

[0029] The output layer is used to output the category bounding box and the corresponding confidence.

[0030] The specific process of obtaining the vehicle two-dimensional position coordinates and vehicle confidence of each vehicle prediction bounding box within the set traffic road and the obstacle two-dimensional position coordinates and obstacle confidence of each obstacle prediction bounding box is as follows: inputting the image data within the set traffic road into the input layer of the target detection model.

[0031] Normalize, resize, and perform data augmentation (such as rotation, flipping, and cropping) on the input image to adapt to the input requirements of the model.

[0032] The input layer passes the pixel values and two-dimensional position coordinates of the image to the feature extraction layer.

[0033] Features are extracted through convolutional layers and pooling layers, including edge, texture, region, shape, and size features of the image.

[0034] Use deep networks to extract global and local features and retain important information in the image.

[0035] The feature map is passed to the candidate box layer, and the region proposal network (RPN) generates candidate regions based on the feature map sliding window. Each sliding window predicts multiple candidate boxes (of different scales and aspect ratios) and assigns a confidence value of "whether it may contain an object" to each candidate box.

[0036] The candidate boxes are passed to the bounding box regression and classification layers.

[0037] In the bounding box regression layer, the position coordinates of each candidate box are corrected to make it fit the target object more accurately. The position coordinates of the upper left corner and the lower right corner are output.

[0038] In the classification layer, each candidate box is assigned a category label (such as vehicle, obstacle), and the confidence value of the candidate box is predicted, indicating the possibility that the box contains an object.

[0039] The output layer of the model integrates the location coordinates, categories, and confidence values of all candidate boxes.

[0040] In this implementation, through the multi-layer design of the convolutional neural network model (such as feature extraction, candidate box generation, bounding box regression and classification layer), key features can be quickly extracted in complex traffic scenes, including boundary information, categories and confidence values of vehicles and obstacles, and then effectively cope with diverse scenarios in dynamic traffic environments (such as multiple vehicles and sudden obstacles), thereby improving the accuracy and real-time performance of tidal robot decision-making. Secondly, in the step of pre-establishing the target detection model, the training effect of the model is ensured by dividing the traffic training data set and the verification data set, combining the regression loss function and model parameter tuning, and the verification data set evaluation further guarantees the high reliability and high precision of the model in practical applications, thereby significantly reducing the false detection rate and missed detection rate, laying a solid foundation for the subsequent tidal robot positioning and path planning. In addition, the input image is standardized , data enhancement (such as rotation, flipping, etc.) and convolution operations, which not only expand the diversity of traffic datasets, but also enhance the model's adaptability to different scenarios. Through multi-scale candidate box generation and deep feature extraction of region proposal network (RPN), the model can accurately capture the local and global features of various targets in the image, reduce detection deviations caused by lighting changes, vehicle size differences or occlusions, and then enable the tidal robot to cope with different traffic conditions more stably, further improving the intelligence level of traffic management. Finally, the candidate box layer is combined with the region proposal network to generate possible target areas, and then the position coordinates are corrected through bounding box regression and the classification layer is used to determine the category, which can effectively eliminate background noise and reduce the waste of computing resources, thereby significantly improving the efficiency of target detection. The tidal robot can quickly complete target recognition and path planning, and significantly optimize the response speed in high-traffic sections.

[0041] Specifically, the specific steps for obtaining the congestion index of each section in the set traffic road are as follows: comprehensively analyzing the vehicle three-dimensional position coordinates of each vehicle boundary box and the obstacle three-dimensional position coordinates of each obstacle boundary box in the set traffic road, as well as the length value and width value of each traffic section, by combining statistical methods, to obtain the vehicle three-dimensional position coordinates of several vehicle inflection points of several vehicle boundary boxes and the obstacle three-dimensional position coordinates of several obstacle inflection points of several obstacle boundary boxes in each traffic section in the set traffic road; reading the vehicle three-dimensional position coordinates of each vehicle inflection point of each vehicle boundary box of each traffic section in the set traffic road and the obstacle three-dimensional position coordinates of each obstacle inflection point of each obstacle boundary box, and performing comprehensive analysis to obtain the vehicle road occupied area and obstacle road occupied area of each traffic section in the set traffic road; comprehensively analyzing the vehicle road occupied area, obstacle road occupied area, width value and length value of each traffic section in the set traffic road to obtain A road utilization index is set for each traffic section within the traffic road. A statistical method is used to comprehensively analyze the three-dimensional vehicle position coordinates of each vehicle inflection point of each vehicle bounding box within each traffic section within the traffic road, as well as the three-dimensional obstacle position coordinates of each obstacle inflection point within each obstacle bounding box. The three-dimensional vehicle position coordinates of several groups of adjacent vehicle inflection points (i.e., the two closest inflection points in adjacent vehicle bounding boxes; if inflection points have the same distance, one group of inflection points is selected as the adjacent vehicle inflection points) and the three-dimensional obstacle position coordinates of several groups of adjacent obstacle inflection points within each traffic section within the traffic road are obtained. A comprehensive analysis is then performed to obtain the vehicle spacing and obstacle spacing for each traffic section within the traffic road. The road utilization index, vehicle spacing, and obstacle spacing for each traffic section within the traffic road are standardized (i.e., de-unitized), and a comprehensive analysis is performed to obtain the congestion index for each traffic section within the traffic road.

[0042] The specific process of obtaining the vehicle three-dimensional position coordinates of several vehicle inflection points of several vehicle bounding boxes and the obstacle three-dimensional position coordinates of several obstacle inflection points of several obstacle bounding boxes for each traffic section within the set traffic road is as follows: obtaining the starting point position coordinates of each traffic section within the set traffic road, and summing the length value and width value of each traffic section with the starting point position coordinates of each traffic section within the set traffic road to obtain the position coordinate interval of each traffic section; and then judging and analyzing the vehicle three-dimensional position coordinates of each vehicle bounding box and the obstacle three-dimensional position coordinates of each obstacle bounding box within the set traffic road with the position coordinate interval (i.e., vertical position coordinate value interval and horizontal position coordinate value interval) of each traffic section. If the vehicle three-dimensional vertical position coordinate value and vehicle horizontal position coordinate value of the vehicle bounding box and the obstacle three-dimensional vertical position coordinate value and obstacle horizontal position coordinate value of the obstacle bounding box all fall within the position coordinate interval of the traffic section, then marking the vehicle bounding box and the obstacle bounding box as this traffic section, and counting the number of vehicle bounding box and obstacle bounding box labels.

[0043] The specific process of obtaining the vehicle three-dimensional position coordinates of adjacent vehicle inflection points of several groups of adjacent vehicle bounding boxes and the obstacle three-dimensional position coordinates of adjacent obstacle inflection points of several groups of adjacent obstacle bounding boxes for each traffic section within a set traffic road is as follows: performing distance calculation on the vehicle three-dimensional position coordinates of each vehicle inflection point between each vehicle bounding box and the obstacle three-dimensional position coordinates of each obstacle inflection point between each obstacle bounding box to obtain the vehicle distance between each vehicle inflection point of every two vehicles and the obstacle distance between each obstacle inflection point of every two obstacles, and performing comparative analysis to obtain the two vehicle inflection points of every two vehicles with the closest vehicle distance, which are marked as adjacent vehicle inflection points. Similarly, adjacent obstacle inflection points are obtained.

[0044] The calculation formulas for the vehicle road occupancy area, road utilization index, vehicle spacing, and congestion index for each traffic section within the set traffic road are as follows: ; in, To set the first The vehicle road area occupied by each traffic section, To set the first The first traffic section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The first traffic section The vehicle bounding box The three-dimensional horizontal position coordinate value of the vehicle turning point, To set the first The first traffic section The vehicle bounding box The three-dimensional horizontal position coordinate value of the vehicle turning point, To set the first The first traffic section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The first section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The first section The three-dimensional horizontal position coordinate value of the first vehicle inflection point of the vehicle bounding box, To set the first The first section The vehicle bounding box The three-dimensional horizontal position coordinate value of the vehicle turning point, To set the first The first section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The road utilization index of each traffic section, To set the first The area of obstacles on the road in each traffic section is To set the first The length of the traffic section, To set the first The width of the traffic section, To set the first The vehicle spacing of a traffic section, To set the first The first traffic section The 3D vertical position coordinate value of the first inflection point of the adjacent vehicle inflection points of the group of adjacent vehicle bounding boxes, To set the first The first traffic section The 3D vertical position coordinate value of the second inflection point among the adjacent vehicle inflection points of the group of adjacent vehicle bounding boxes. To set the first The first traffic section The three-dimensional horizontal position coordinate value of the first inflection point of the adjacent vehicle inflection points of the group of adjacent vehicle bounding boxes, To set the first The first traffic section The three-dimensional horizontal position coordinate value of the second inflection point of the adjacent vehicle inflection point of the group of adjacent vehicle bounding boxes, To set the first The congestion index of a traffic section, The first set of traffic roads after standardization The road utilization index of each traffic section, The road coefficient of the set traffic road stored in the database, The first set of traffic roads after standardization The vehicle spacing of a traffic section, The vehicle coefficients within the set traffic roads stored in the database, The first set of traffic roads after standardization The obstacle distance of each traffic section, is the obstacle coefficient of the set traffic road stored in the database, and , = +1, =1,2,3,…, , is the number of traffic sections, =1,2,3,…, , is the number of vehicle bounding boxes, =1,2,3,…, , is the number of vehicle inflection points, =1,2,3,…, , is the number of adjacent vehicle bounding box groups.

[0045] What needs to be explained is that 、 、 The specific acquisition process is as follows: read the road utilization index, vehicle spacing, and obstacle spacing of each section in the set traffic road after standardization, perform mean analysis, obtain the mean value of the road utilization index, the mean value of the vehicle spacing, and the mean value of the obstacle spacing in the set traffic road, and perform sum analysis to obtain the congestion sum value in the set traffic road, perform proportion analysis on the mean value of the road utilization index, the mean value of the vehicle spacing, and the mean value of the obstacle spacing in the set traffic road and the congestion sum value, and use the proportion analysis results as the corresponding coefficients.

[0046] The calculation logic of the obstacle road occupation area and the vehicle road occupation area for each road section in the traffic road are consistent, and the calculation steps are also consistent.

[0047] The calculation logic and formula for setting the obstacle spacing and vehicle spacing for each road section within the traffic road are consistent.

[0048] A specific implementation example of calculating the congestion index of a certain road section within a set traffic road, with the following data:

[0049] The length of this road section is 30 meters and the width is 9 meters.

[0050] This road section includes 5 vehicle boundary boxes and 2 obstacle boundary boxes, and each of the 5 vehicle boundary boxes includes 4 vehicle inflection points. The obstacle inflection points of the 2 obstacle boundary boxes are 3 and 5 respectively. Here, the vehicle three-dimensional height value of each vehicle inflection point and the obstacle three-dimensional height value of each vehicle inflection point obstacle inflection point are both set to 0.

[0051] The coordinates of the four inflection points of the first vehicle bounding box are: (0, 4, 0), (5, 4, 0), (5, 6, 0), (0, 6, 0).

[0052] The coordinates of the four inflection points of the second vehicle bounding box are: (6, 3, 0), (10, 3, 0), (10, 5, 0), (6, 5, 0).

[0053] The coordinates of the four inflection points of the third vehicle bounding box are: (12, 4, 0), (17, 4, 0), (17, 6, 0), (12, 6, 0).

[0054] The coordinates of the four inflection points of the fourth vehicle bounding box are: (18, 2, 0), (23, 2, 0), (23, 4, 0), (17, 4, 0).

[0055] The coordinates of the four inflection points of the fifth vehicle bounding box are: (24, 4, 0), (28, 4, 0), (28, 6, 0), (24, 6, 0).

[0056] The coordinates of the three inflection points of the first obstacle bounding box are: (3, 7, 0), (3.5, 7.5, 0), and (4, 7.2, 0).

[0057] The coordinates of the five inflection points of the second obstacle bounding box are: (7, 7.2, 0), (7, 7.5, 0), (7.3, 7.6, 0), (7.2, 6, 0), (7, 6.9, 0).

[0058] Then the adjacent inflection points of the first group of adjacent vehicle bounding boxes are (5, 4, 0) and (10, 3, 0).

[0059] The coordinates of the adjacent inflection points of the second group of adjacent vehicle bounding boxes are (6, 3, 0), (12, 4, 0).

[0060] The coordinates of the adjacent inflection points of the third group of adjacent vehicle bounding boxes are (12, 4, 0) and (18, 2, 0).

[0061] The coordinates of the adjacent inflection points of the fourth group of adjacent vehicle bounding boxes are (12, 4, 0) and (24, 4, 0).

[0062] The adjacent inflection points of the obstacle bounding box are (4,7.2,0), (7,7.2,0).

[0063] Substitute the above data into the calculation formula of vehicle road occupation area, road utilization index, vehicle spacing, congestion index of each traffic section in the set traffic road, obstacle road occupation area, obstacle spacing, and congestion index of each road section in the set traffic road, and obtain: vehicle road occupation area of a certain road section in the set traffic road (square meters) = (1 / 2)*[|(0*4-4*5)+(5*6-4*6)+(5*0-6*6)+(0*4-6*0)|+|(6*3-10*3)+(10 *5-6*5)+(5*6-0*6)+(0*4-6*0)|+|(12*4-4*17)+(17*6-6*17)+(17*6-6*12)+(12*4-6*12)|+|(18*2-2*23)+(23*4-2*23)+(23*4-17*4)+(17*2-4*18)|+|(24*4-4*28)+(28*6-4*28)+(28*6-6*24)+(24*4-6*24)|]=29.

[0064] Set the obstacle road area (square meters) of a certain section of the traffic road = (1 / 2)*[|(0*4-4*5)+(3*7.5-7.5*4)+(4*7-7.2*3)|+|(7*7.5-7.2*7)+(7*7.3-7.5*7.6)+(7.3*6-7.6*7.0)+(7.2*6.9-6*7)+(7*7.2-6.9*7)|]≈0.4.

[0065] Set the road utilization index of a certain section of the traffic road = (29+0.4) / (30*9)≈0.1

[0066] Set the vehicle spacing (meters) of a certain section of the traffic road = ( 1 / 2 (5-10) 2+ (4-3) 2 ))+( 1 / 2 (6-12) 2 + (3-4) 2 ))+( 1 / 2 (12-18) 2 + (4-2) 2 ))+( 1 / 2 (12-24) 2 + (4-4) 2 ))≈29.5.

[0067] Set the obstacle distance (meters) of a certain section of the traffic road = 1 / 2 (4-7) 2 + (7.2-7.2) 2 )=3.

[0068] The road utilization index of a certain section of the set traffic road after standardization is ≈0.25.

[0069] The vehicle distance of a certain section of the set traffic road after standardization is ≈0.71.

[0070] The obstacle spacing of a certain section of the set traffic road after standardization is ≈0.21.

[0071] The road coefficient within the traffic road is set to ≈0.31.

[0072] The vehicle coefficient within the traffic road is set to ≈0.45.

[0073] The obstacle coefficient within the traffic road is set to ≈0.34.

[0074] Set the congestion index of a certain section of the traffic road = ln (1 + 0.31 * 0.25 + 0.45 * (1 / (0.71 + 1)) + 0.34 * (1 / (0.21 + 1))) ≈ 0.49.

[0075] In this implementation plan, the road occupancy area is calculated by the three-dimensional position coordinates of vehicles and obstacles, and then combined with parameters such as road length and width to accurately evaluate the road utilization rate of each road section. At the same time, by analyzing the distance between adjacent vehicles or obstacles, congestion hotspots in local areas can be identified, thereby greatly improving the accuracy of the congestion index and being able to more realistically reflect the actual congestion situation of the road. Secondly, the road utilization index, vehicle spacing and obstacle spacing are standardized to eliminate the differences in data scales of different road sections, making the congestion index of different road sections more comparable, so that the road conditions (such as width, Even when there are inconsistencies in the congestion index (such as the distribution of obstacles), objective congestion evaluation results can be obtained, which facilitates the tidal robot to make dynamic decisions between multiple road sections. In addition, through mean analysis and proportion analysis in the congestion index calculation process, weight coefficients of roads, vehicles, and obstacles are dynamically generated, which can flexibly adapt to the actual traffic characteristics of different road sections. Finally, the congestion index of each road section integrates information such as road utilization, vehicle spacing, and obstacle distribution, providing the tidal robot with a refined road section traffic capacity assessment, which in turn helps to optimize the current movement path and provide reliable data support for long-term traffic forecasts.

[0076] Specifically, the specific steps for obtaining several moving trajectories of the tidal robot within the set traffic road are as follows: comprehensively analyzing the initial position coordinates of the tidal robot and the target diversion position coordinates within the set traffic road using the interpolation method to obtain the potential position coordinates of several potential moving points of the tidal robot within the set traffic road; and comprehensively analyzing the vehicle three-dimensional position coordinates of each vehicle boundary box between the initial position coordinates of the tidal robot and the target diversion position coordinates within the set traffic road and the obstacle three-dimensional position coordinates of each obstacle boundary box with the potential position coordinates of each adjacent potential moving point to obtain the position coordinates of several moving points of the tidal robot within the set traffic road, that is, the moving three-dimensional vertical position coordinates. Value, moving three-dimensional horizontal position coordinate value, moving three-dimensional height position coordinate value (and in this embodiment, all three-dimensional height position coordinate values are set to 0); mark every two adjacent moving points of the tidal robot in the set traffic road as the starting point and end point of a group of trajectory segments (that is, the moving point close to the tidal robot is the starting point, and the moving point far away is the end point), and read the starting point position coordinates and the end point position coordinates of each group of trajectory segments in the set traffic road; and conduct a comprehensive analysis of the starting point position coordinates and the end point position coordinates of each group of trajectory segments of the tidal robot in the set traffic road, and obtain the path position coordinates of several path moving points of the tidal robot in each group of trajectory segments in the set traffic road (compared with the obtained path position coordinates of the tidal robot in The steps for setting the position coordinates of several moving points in the traffic road are consistent), namely, the three-dimensional vertical position coordinate value of the path, the three-dimensional horizontal position coordinate value of the path, and the three-dimensional height position coordinate value of the path; the three-dimensional position coordinates of the vehicle bounding box of each vehicle in the set traffic road, the three-dimensional position coordinates of the obstacle of each obstacle bounding box, and the trajectory position coordinates of each path moving point are comprehensively analyzed by combining the statistical method to obtain the three-dimensional position coordinates of the trajectory vehicle bounding box (i.e., the vehicle bounding box closest to each path moving point) and the three-dimensional position coordinates of the obstacle of each trajectory obstacle bounding box (i.e., the obstacle bounding box closest to each path moving point) of each group of trajectory sections in the set traffic road; for each group of trajectory sections in the set traffic road, the three-dimensional position coordinates of the obstacle of each trajectory obstacle bounding box (i.e., the obstacle bounding box closest to each path moving point) are obtained; for each group of trajectory sections in the set traffic road, the three-dimensional position coordinates of the vehicle bounding box of each path moving point are obtained. A comprehensive analysis is performed on the trajectory position coordinates of each path moving point of the group trajectory section, the vehicle three-dimensional position coordinates of the trajectory vehicle boundary box, the obstacle three-dimensional position coordinates of the trajectory obstacle boundary box, and the preset safety distance of the tidal robot to obtain the offset distance of each path moving point of the tidal robot in each group of trajectory sections within the set traffic road; a comprehensive analysis is performed on the trajectory position coordinates and offset distance of each path moving point of the tidal robot in each group of trajectory sections within the set traffic road to obtain the offset position coordinates of several deviated moving points (corresponding to each path moving point) of the tidal robot in each group of trajectory sections within the set traffic road, namely, the offset three-dimensional vertical position coordinate value, the offset three-dimensional horizontal position coordinate value, and the offset three-dimensional height position coordinate value;Connect each deviation point and each path point of the tidal robot in each set of track sections within the set traffic road to generate multiple movement tracks for each set of track sections of the tidal robot in the set traffic road. Each deviation point and each path point in each movement track of each set of track sections of the tidal robot in the set traffic road are uniformly labeled as a track point, and the offset position coordinates of each deviation point and the path position coordinates of each path point are uniformly labeled as track position coordinates, i.e., three-dimensional vertical position coordinate values, three-dimensional horizontal position coordinate values, and three-dimensional height position coordinate values of the track.

[0077] Among them, the interpolation method is to estimate the value at the unknown position through known data points (i.e., the initial position coordinates and the target reserved position coordinates), and in this embodiment, spline interpolation is adopted. Spline interpolation is an interpolation method that uses piecewise polynomials to smooth over data points. It uses cubic polynomials for interpolation, and the derivative (rate of change) between every two adjacent data points is continuous.

[0078] The statistical method of nearest neighbor matching selected in this embodiment is as follows: for each path moving point, by calculating its distance to all vehicles and obstacles, the nearest one (or the one with the smallest distance) is selected as the closest bounding box.

[0079] The specific process of obtaining the position coordinates of several moving points of the tidal robot in the set traffic road is as follows: the three-dimensional position coordinates of the vehicle of each vehicle boundary box within the initial position coordinates of the tidal robot in the set traffic road and the target diversion position coordinates, and the three-dimensional position coordinates of the obstacles of each obstacle boundary box are comprehensively analyzed with the potential position coordinates of each adjacent potential moving point, and the vehicle moving distance (i.e., the distance between the vehicle and the adjacent potential moving point) of each vehicle boundary box within the initial position coordinates of the tidal robot in the set traffic road and the target diversion position coordinates, and the three-dimensional position coordinates of each obstacle boundary box are obtained. The obstacle moving distance of the frame (i.e., the distance between the obstacle and the adjacent potential moving point) is calculated and compared with the preset safety distance. If the moving distance of the vehicle boundary frame and the obstacle boundary frame within the initial position coordinates and the target diversion position coordinates of the tidal robot in the set traffic road are higher than the preset safety distance, the potential moving point is marked as a path moving point. If the moving distance of the vehicle boundary frame and the obstacle boundary frame within the initial position coordinates and the target diversion position coordinates of the tidal robot in the set traffic road are lower than the preset safety distance, the potential moving point is eliminated.

[0080] The specific process of obtaining the offset distance of each path moving point of the tidal robot in each group of trajectory sections within the set traffic road is as follows: comprehensively analyzing the vehicle three-dimensional position coordinates of the trajectory vehicle boundary box of each path moving point in each group of trajectory sections within the set traffic road, the obstacle three-dimensional position coordinates of the trajectory obstacle boundary box, and the preset safety distance of the tidal robot, and obtaining the vehicle trajectory distance (i.e., the distance between the trajectory vehicle boundary box and the adjacent path moving point) and the obstacle trajectory distance (i.e., the distance between the trajectory obstacle boundary box and the adjacent path moving point) of each path moving point in each group of trajectory sections within the set traffic road, and comparing the vehicle trajectory distance and the obstacle trajectory distance of each path moving point in each group of trajectory sections within the set traffic road. If the vehicle trajectory distance is higher than the obstacle trajectory distance, the vehicle trajectory distance is marked as the offset distance; if the obstacle trajectory distance is higher than the vehicle trajectory distance, the obstacle trajectory distance is marked as the offset distance.

[0081] The formula for calculating the vehicle trajectory distance of each path moving point in each set of trajectory sections within the set traffic road is as follows: ;in, To set the first The first segment of the group trajectory The vehicle trajectory distance of each path moving point, To set the first The first segment of the group trajectory The three-dimensional vertical position coordinate value of the vehicle's bounding box of the trajectory vehicle of the path moving point, To set the first The first segment of the group trajectory The three-dimensional vertical position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional horizontal position coordinate value of the vehicle's bounding box of the trajectory vehicle of the path moving point, To set the first The first segment of the group trajectory The three-dimensional horizontal position coordinate value of the path moving point, The preset safety distance for the Tide Robot within the set traffic road, =1,2,3,…, , is the number of trajectory segment groups, =1,2,3,…, , The number of points to move along the path.

[0082] The calculation logic of the obstacle trajectory distance and the vehicle trajectory distance of each trajectory moving point of each group of trajectory sections in the traffic road are consistent, and the calculation formula is also consistent.

[0083] The specific formula for calculating the offset position coordinates of each deviation moving point of the tidal robot in each set of trajectory sections within the set traffic road is as follows: ;in, To set the first The first segment of the group trajectory The offset three-dimensional vertical position coordinate value of the moving point, To set the first The first segment of the group trajectory The three-dimensional vertical position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional vertical position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional horizontal position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional horizontal position coordinate value of the path moving point, To set the first The first segment of the group trajectory The vehicle path distance of each path moving point, To set the first The first segment of the group trajectory The offset three-dimensional horizontal position coordinate value of the moving point, =1,2,3,…, , is the number of trajectory segment groups, =1,2,3,…, , The number of points to move along the path.

[0084] In this embodiment, by analyzing the position coordinates of the potential moving points between the initial position coordinates of the tidal robot and the target diversion position coordinates, the path points that the robot may pass through can be accurately calculated, thereby ensuring that the robot can travel smoothly and accurately between each moving point in the set traffic road, and ensuring the feasibility and safety of the path. Secondly, the distance between the three-dimensional bounding box of each vehicle and obstacle and the potential moving point will be calculated and compared. If the distance is lower than the preset safety distance, the potential point will be eliminated to prevent the robot from colliding with the obstacle. In this way, the robot can adaptively adjust its own path in a complex traffic environment and reduce accidents. The robot can avoid external collisions and dangers, especially in the presence of multiple obstacles or heavy traffic, to ensure that the robot's driving is safer. By calculating the offset position coordinates of each path point, the robot can adjust its trajectory in time when encountering obstacles or changing traffic conditions, thereby generating multiple paths to ensure safe and efficient arrival at the target location. Finally, by combining statistical analysis methods, the robot can evaluate the distance between vehicles and obstacles at each path point in real time and respond to environmental changes in a timely manner, so that the robot can adapt to dynamically changing traffic environments, such as dealing with uncertain factors such as vehicle lane changes and pedestrians crossing, greatly improving the robot's environmental adaptability.

[0085] Specifically, the specific steps for obtaining the reliability index of each moving section of each moving trajectory of the tidal robot in the set traffic road are as follows: each moving trajectory of the tidal robot in the set traffic road is divided based on a preset moving distance, and the trajectory position coordinates of several trajectory moving points of each moving section of each moving trajectory of the tidal robot in the set traffic road are obtained; the trajectory image data of each moving section of each moving trajectory of the tidal robot in the set traffic road are comprehensively analyzed to obtain the real-time vehicle position coordinates of several real-time trajectory vehicle boundary boxes of each moving section of each moving trajectory of the tidal robot in the set traffic road, and the real-time vehicle position coordinates are the real-time trajectory three-dimensional vertical position coordinate value, the real-time trajectory three-dimensional horizontal position coordinate value, and the real-time trajectory three-dimensional height position coordinate value; and the speed value of the tidal robot in the set traffic road is obtained; the initial position coordinates, speed value, and trajectory position coordinates of each trajectory moving point of each moving section of each moving trajectory of the tidal robot in the set traffic road are predicted and analyzed to obtain the reliability index of the tidal robot in the set traffic road The predicted time value of each moving trajectory of each group of trajectory sections within the road (i.e., the predicted travel time required for the tidal robot to pass through the moving trajectory); the predicted time value of each moving trajectory of each group of trajectory sections of the tidal robot within the set traffic road is divided to obtain several predicted time points of each moving section of each moving trajectory of the tidal robot within the set traffic road (the interval between time points is the same as the interval between each real-time trajectory vehicle boundary box); and the predicted three-dimensional vertical position coordinate value, predicted three-dimensional horizontal position coordinate value, and predicted three-dimensional height position coordinate value of each moving section of each moving trajectory of the tidal robot within the set traffic road (within the prediction time) are obtained, that is, the predicted real-time position coordinates; and the preset safety distance of the tidal robot within the set traffic road and the position coordinates of each real-time trajectory vehicle boundary box of each moving section of each moving trajectory and the predicted real-time position coordinates at each prediction time point are comprehensively analyzed to obtain the predicted collision distance of each moving trajectory of the tidal robot in each group of trajectory sections within the set traffic road, which is marked as the reliability index.

[0086] Among them, the steps of obtaining the real-time vehicle position coordinates of each real-time track vehicle boundary box of each moving section of each moving track of the tidal robot in the set traffic road are consistent with the vehicle three-dimensional position coordinates of each vehicle boundary box.

[0087] The specific steps for obtaining the predicted real-time position coordinates of the tidal robot at each predicted time point (within the predicted time) of each moving section of each moving trajectory within the set traffic road are: dividing the predicted time value of each moving section of each moving trajectory of the tidal robot within the set traffic road into several time points, and comprehensively analyzing the speed value, initial position coordinates and interval length values of adjacent times of the tidal robot within the set traffic road to obtain the predicted real-time position coordinates of the tidal robot at each predicted time point of each moving section of each moving trajectory within the set traffic road.

[0088] The specific formula for calculating the predicted time value and predicted collision distance of each moving section of each moving trajectory of the tidal robot within the set traffic road is as follows: ;

[0089] in, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The predicted time value of the moving section, is the initial three-dimensional vertical position coordinate value of the tidal robot in the set traffic road, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The three-dimensional vertical position coordinate value of the first moving point of the moving section, is the initial three-dimensional horizontal position coordinate value of the tidal robot in the set traffic road, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The three-dimensional horizontal position coordinate value of the first moving point of the moving section, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional vertical position coordinate value of the trajectory moving point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional vertical position coordinate value of the trajectory moving point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional horizontal position coordinate value of the trajectory moving point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional horizontal position coordinate value of the trajectory moving point, is the speed value of the tidal robot in the set traffic road, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The reliability index of the moving segment, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The predicted three-dimensional vertical position coordinate value at the prediction time point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The real-time trajectory three-dimensional vertical position coordinate value of the real-time trajectory vehicle boundary box, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The predicted three-dimensional horizontal position coordinate value at the prediction time point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The real-time trajectory three-dimensional horizontal position coordinate value of the real-time trajectory vehicle boundary box, The preset safety distance for the Tide Robot within the set traffic road, =1,2,3,…, , is the number of moving trajectories, =1,2,3,…, , is the number of moving sections, =1,2,3,…, , is the number of trajectory segments, =1,2,3,…, , is the number of predicted time points, =1,2,3,…, , is the number of vehicle bounding boxes in real-time trajectory.

[0090] In this implementation scheme, by performing real-time analysis on each moving trajectory of the tidal robot, the predicted three-dimensional position coordinate value of the tidal robot at each predicted time point can be accurately obtained, and the collision risk with surrounding obstacles can be evaluated in real time. By predicting the position coordinates of each trajectory point at a certain moment in the future, as well as the distance from the obstacle, collisions can be effectively avoided, and the path can be adjusted in real time to ensure the safe driving of the robot within the set traffic road, thereby improving the safety of the robot in a dynamic environment and reducing the occurrence of accidental collisions. Secondly, by performing a detailed analysis of the three-dimensional position coordinates of each trajectory point and combining it with the position coordinates of the real-time vehicle boundary box, the system can judge the collision risk between the current path and the obstacle in real time. By calculating the "predicted collision distance" and comparing it with the preset safety distance, it can evaluate the current Whether the previous path is safe, if the collision risk is too great, adjustment measures will be taken immediately, thereby effectively reducing the accident risk of the robot in complex traffic environments. In addition, by accurately predicting the time and position coordinates of each trajectory point, the tidal robot can optimize its driving speed and route, thereby improving driving efficiency. By analyzing the robot's initial position, speed and moving trajectory, the system can more reasonably arrange the passage time of each moving point, so as to ensure that the robot passes through the set road section in the best way, saving time and reducing unnecessary energy consumption. Finally, by setting a "reliability index" to evaluate the safety of each moving trajectory, the tidal robot can respond in time when encountering complex traffic conditions, so that the system can still maintain stability in unpredictable complex environments and reduce the occurrence of system failures or accidents.

[0091] Specifically, the specific steps of taking trajectory adjustment measures based on the analysis results are as follows: comparative analysis is performed on the reliability index of the first moving section of each moving trajectory of the tidal robot in the set traffic road, and the corresponding moving trajectory of the first moving section of the tidal robot in the set traffic road is selected as the optimal moving trajectory of the first moving section according to the analysis results (that is, the moving trajectory corresponding to the moving section with the largest reliability index is selected); after the tidal robot in the set traffic road reaches the end point of the first moving section on the selected optimal moving trajectory of the first moving section, a discriminant analysis is performed on the reliability index of the second moving section on the optimal moving trajectory of the first moving section of the tidal robot in the set traffic road and the reliability index of the second moving section of each remaining moving trajectory, and the corresponding moving trajectory of the second moving section of the tidal robot in the set traffic road is selected as the optimal moving trajectory of the second moving section according to the discriminant analysis; after the tidal robot in the set traffic road reaches the end point of the second moving section on the selected optimal moving trajectory of the second moving section, the discriminant analysis and the optimal moving trajectory selection steps are repeated until the tidal robot reaches the target diversion position coordinates in the set traffic road.

[0092] The specific process of selecting the corresponding moving trajectory of the tidal robot in the second moving section within the set traffic road as the optimal moving trajectory of the second moving section according to the discriminant analysis is as follows:

[0093] If the reliability index of the second section of the current moving trajectory is lower than the reliability index of the second moving section of each remaining moving trajectory, the reliability index of the second moving section of each remaining moving trajectory is analyzed in combination with a statistical method to obtain the second moving section of the optimal path (i.e., the section with the largest reliability index), and the position coordinates of the second section starting point of the second section of the current moving trajectory and the position coordinates of the second section end point of the second moving section of the optimal path are read, and a comprehensive analysis is performed to obtain several second section moving points of the corrected second moving section, and a corrected second section trajectory is generated.

[0094] The specific process of the comprehensive analysis is: acquiring the image data between the second section of the current moving trajectory and the second moving section of the optimal path in real time, obtaining the real-time position coordinates of several vehicles, and the real-time position coordinates of several obstacles, and combining the spline interpolation method with the second section starting point position coordinates of the second section of the current moving trajectory and the second section end point position coordinates of the second moving section of the optimal path for analysis, obtaining the second moving position coordinates of several second section moving points (consistent with the steps of obtaining the position coordinates of several moving points of the tidal robot in the set traffic road), and generating a corrected second section trajectory.

[0095] In this embodiment, by selecting the optimal path according to the reliability index at each stage, priority is given to road sections that are safe and unobstructed under the current traffic conditions, thereby effectively avoiding traffic congestion, obstacles or other potential risks, thereby improving the reliability of the path. Secondly, by performing discriminant analysis and selecting the optimal path after the end of each road section, the robot's driving trajectory is adjusted in real time to avoid the dilemma of being unable to respond in time when encountering emergencies, thereby enabling the robot to adaptively adjust the path in a complex and dynamic traffic environment. In addition, by performing statistical analysis on the moving trajectory of each road section and combining the reliability indexes of multiple candidate paths for selection, the optimal path is accurately identified. At the same time, during the path adjustment process, the path is corrected by methods such as spline interpolation, which can smoothly connect the difference between the current trajectory and the optimal path, thereby helping to reduce path errors and ensuring that the robot does not deviate drastically or change the path suddenly during driving, avoiding excessive turning radius and unnecessary adjustments, and improving the smoothness and naturalness of the path.

[0096] In summary, this application has at least the following effects:

[0097] By analyzing the road data and initial traffic image data of the road where the tidal robot is located, and combining it with the route planning algorithm, the optimal path of the robot from the initial position coordinates to the target diversion position coordinates is dynamically planned, so that the planning of moving points and trajectory sections can be automatically adjusted according to different road conditions. This overcomes the defect of traditional path planning that relies on static paths, ensures the scientific nature and real-time nature of trajectory planning, and improves the robot's adaptability to complex traffic scenarios.

[0098] By acquiring trajectory image data in real time and calculating the reliability index of the trajectory, the safety and effectiveness of each moving trajectory can be evaluated from multiple dimensions, so that potential risks and obstacles can be effectively identified, and inappropriate paths can be eliminated based on the reliability assessment, ensuring that the tidal robot always chooses the optimal path to operate, thereby improving the accuracy of trajectory evaluation, significantly reducing the risk of path failure, and ensuring the operational stability of the tidal robot.

[0099] By formulating a control strategy based on the reliability index analysis results of each mobile trajectory, the operating status of the tidal robot can be managed in a refined manner. By dynamically adjusting the control strategy, it can effectively respond to sudden traffic conditions or trajectory obstacles, ensuring that the robot is always in the optimal operating state. In addition, through real-time feedback adjustment strategy, the tidal robot can efficiently complete diversion tasks in complex traffic roads, comprehensively improving task execution effects and resource utilization.

[0100] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0101] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for controlling the movement trajectory of a tidal robot, characterized in that: The following steps are involved: Obtain road data, initial traffic image data, and initial position coordinates of the tidal robot within a set traffic road, and perform preprocessing. The road data specifically includes the road width value, road length value, starting point position coordinates, and end point position coordinates of each traffic section. The initial traffic image data specifically includes the pixel value and two-dimensional position coordinates of each pixel point in the traffic image. The initial position coordinates specifically include the initial three-dimensional vertical position coordinate value, the initial three-dimensional horizontal position coordinate value, and the initial three-dimensional height position coordinate value. The pre-processed road data and initial traffic image data within the set traffic road are analyzed to obtain the target diversion position coordinates of the tidal robot within the set traffic road. Combined with the route planning algorithm, the initial position coordinates of the tidal robot and the target diversion position coordinates within the set traffic road are comprehensively analyzed to obtain several movement trajectories of the tidal robot within the set traffic road. Each moving trajectory of the tidal robot in the set traffic road is divided into sections to obtain a plurality of moving sections of each moving trajectory of the tidal robot in the set traffic road; Real-time acquisition of trajectory image data of each moving section of each moving trajectory of the tidal robot within the set traffic road, and comprehensive analysis to obtain the reliability index of each moving section of each moving trajectory of the tidal robot within the set traffic road, wherein the trajectory image data specifically includes the trajectory pixel value and the trajectory two-dimensional position coordinates of each trajectory pixel point; The reliability index of each moving section of each moving trajectory of the tidal robot within the set traffic road is comprehensively analyzed in real time, and trajectory adjustment measures are taken based on the analysis results.

2. The method for controlling the movement trajectory of a tidal robot according to claim 1, wherein: The specific steps to obtain the target diversion position coordinates of the tidal robot within the set traffic road are as follows: The pixel value and two-dimensional position coordinates of each pixel point in the image within the set traffic road are input into a pre-established target detection model for comprehensive analysis to obtain the two-dimensional position coordinates of vehicles and vehicle confidences of several vehicle prediction bounding boxes within the set traffic road, as well as the two-dimensional position coordinates of obstacles and obstacle confidences of several obstacle prediction bounding boxes; Comprehensively analyzing the vehicle predicted two-dimensional position coordinates and vehicle prediction confidence of each vehicle prediction bounding box within the set traffic road, as well as the obstacle predicted two-dimensional position coordinates and obstacle prediction confidence of each obstacle prediction bounding box, to obtain the vehicle two-dimensional position coordinates of several vehicle bounding boxes within the set traffic road and the obstacle two-dimensional position coordinates of several obstacle bounding boxes; Performing position coordinate conversion processing on the two-dimensional position coordinates of each vehicle bounding box within the set traffic road and the two-dimensional position coordinates of each obstacle bounding box to obtain the three-dimensional position coordinates of each vehicle bounding box within the set traffic road and the three-dimensional position coordinates of each obstacle bounding box within the set traffic road, wherein the three-dimensional position coordinates of the vehicle include the three-dimensional vertical position coordinate value of the vehicle, the three-dimensional horizontal position coordinate value of the vehicle, and the three-dimensional height position coordinate value of the vehicle, and the three-dimensional position coordinates of the obstacle include the three-dimensional vertical position coordinate value of the obstacle, the three-dimensional horizontal position coordinate value of the obstacle, and the three-dimensional height position coordinate value of the obstacle; Comprehensively analyzing the three-dimensional position coordinates of each vehicle bounding box within the set traffic road, the three-dimensional position coordinates of each obstacle bounding box within the set traffic road, and the road width and road length values of each traffic section to obtain a congestion index for each traffic section within the set traffic road; The congestion index of each traffic section in the set traffic road is arranged in descending order to generate a congestion arrangement section table, and the starting point position coordinates of the first sequence of sections are marked as target diversion position coordinates.

3. The method for controlling the movement trajectory of a tidal robot according to claim 2, wherein: The target detection model is specifically a convolutional neural network model, and the steps for pre-establishing the target detection model are as follows: Acquire several sets of initial traffic image data within a set traffic road, establish a traffic dataset, and divide the traffic dataset into a traffic training dataset and a traffic verification dataset; Initialize the convolutional neural network model; Train the initialized convolutional neural network model based on the traffic training dataset and calculate the traffic regression loss function; The target detection model performance is evaluated based on the traffic validation dataset, and the model parameters are adjusted according to the validation results until the model prediction results meet the expected standards.

4. The method for controlling the movement trajectory of a tidal robot according to claim 2, wherein: The specific steps to obtain the congestion index of each road section within the set traffic road are: Comprehensively analyzing the three-dimensional vehicle position coordinates of each vehicle bounding box and the three-dimensional obstacle position coordinates of each obstacle bounding box within the set traffic road, as well as the length and width values of each traffic section, to obtain the three-dimensional vehicle position coordinates of a plurality of vehicle inflection points of a plurality of vehicle bounding boxes and the three-dimensional obstacle position coordinates of a plurality of obstacle inflection points of a plurality of obstacle bounding boxes within each traffic section within the set traffic road; Reading the three-dimensional position coordinates of each vehicle inflection point of each vehicle bounding box of each traffic section within the set traffic road and the three-dimensional position coordinates of each obstacle inflection point of each obstacle bounding box, and performing comprehensive analysis to obtain the vehicle road occupation area and obstacle road occupation area of each traffic section within the set traffic road; Comprehensively analyze the vehicle road occupation area, obstacle road occupation area, width value, and length value of each traffic section within the set traffic road to obtain the road utilization index of each traffic section within the set traffic road; Comprehensively analyzing the three-dimensional vehicle position coordinates of each vehicle inflection point of each vehicle bounding box of each traffic section within the set traffic road and the three-dimensional obstacle position coordinates of each obstacle inflection point of each obstacle bounding box to obtain the three-dimensional vehicle position coordinates of adjacent vehicle inflection points of several groups of adjacent vehicle bounding boxes and the three-dimensional obstacle position coordinates of adjacent obstacle inflection points of several groups of adjacent obstacle bounding boxes for each traffic section within the set traffic road, and performing comprehensive analysis to obtain the vehicle spacing and obstacle spacing for each road section within the set traffic road; The road utilization index, vehicle spacing, and obstacle spacing of each traffic section within the set traffic road are standardized, and a comprehensive analysis is performed to obtain the congestion index of each traffic section within the set traffic road.

5. The method for controlling the movement trajectory of a tidal robot according to claim 4, characterized in that: The calculation formulas for the vehicle road occupancy area, road utilization index, vehicle spacing, and congestion index for each traffic section within the set traffic road are as follows: ； in, To set the first The road area occupied by vehicles in each traffic section, To set the first The first traffic section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The first traffic section The vehicle bounding box The three-dimensional horizontal position coordinate value of the vehicle turning point, To set the first The first traffic section The vehicle bounding box The three-dimensional horizontal position coordinate value of the vehicle turning point, To set the first The first traffic section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The first section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The first section The three-dimensional horizontal position coordinate value of the first vehicle inflection point of the vehicle bounding box, To set the first The first section The vehicle bounding box The three-dimensional horizontal position coordinate value of the vehicle turning point, To set the first The first section The vehicle bounding box The three-dimensional vertical position coordinate value of the vehicle turning point, To set the first The road utilization index of each traffic section, To set the first The area of obstacles on the road in each traffic section is To set the first The length of the traffic section, To set the first The width of the traffic section, To set the first The vehicle spacing of a traffic section, To set the first The first traffic section The 3D vertical position coordinate value of the first inflection point of the adjacent vehicle inflection points of the group of adjacent vehicle bounding boxes, To set the first The first traffic section The 3D vertical position coordinate value of the second inflection point among the adjacent vehicle inflection points of the group of adjacent vehicle bounding boxes. To set the first The first traffic section The three-dimensional horizontal position coordinate value of the first inflection point of the adjacent vehicle inflection points of the group of adjacent vehicle bounding boxes, To set the first The first traffic section The three-dimensional horizontal position coordinate value of the second inflection point of the adjacent vehicle inflection point of the group of adjacent vehicle bounding boxes, To set the first The congestion index of a traffic section, The first set of traffic roads after standardization The road utilization index of each traffic section, The road coefficient of the set traffic road stored in the database, The first set of traffic roads after standardization The vehicle spacing of a traffic section, The vehicle coefficients within the set traffic roads stored in the database, The first set of traffic roads after standardization The obstacle distance of each traffic section, is the obstacle coefficient of the set traffic road stored in the database, and , = +1, =1,2,3,…, , is the number of traffic sections, =1,2,3,…, , is the number of vehicle bounding boxes, =1,2,3,…, , is the number of vehicle inflection points, =1,2,3,…, , is the number of adjacent vehicle bounding box groups.

6. The method for controlling the movement trajectory of a tidal robot according to claim 1, wherein: The specific steps to obtain several moving trajectories of the tidal robot within the set traffic road are: Comprehensively analyze the initial position coordinates of the tidal robot and the target diversion position coordinates within the set traffic road to obtain the potential position coordinates of several potential moving points of the tidal robot within the set traffic road; The three-dimensional position coordinates of each vehicle boundary box between the initial position coordinates of the tidal robot and the target diversion position coordinates within the set traffic road, as well as the three-dimensional position coordinates of each obstacle boundary box, are comprehensively analyzed with the potential position coordinates of each adjacent potential moving point to obtain the position coordinates of several moving points of the tidal robot within the set traffic road, namely, the moving three-dimensional vertical position coordinate value, the moving three-dimensional horizontal position coordinate value, and the moving three-dimensional height position coordinate value; Mark every two adjacent moving points of the tidal robot within the set traffic road as the starting point and end point of a set of trajectory segments, and read the starting point position coordinates and the end point position coordinates of each set of trajectory segments within the set traffic road; A comprehensive analysis is performed on the starting point position coordinates and the end point position coordinates of each set of trajectory sections of the tidal robot within the set traffic road, and the path position coordinates of several path movement points of each set of trajectory sections of the tidal robot within the set traffic road are obtained, namely, the three-dimensional vertical position coordinate value of the path, the three-dimensional horizontal position coordinate value of the path, and the three-dimensional height position coordinate value of the path; Comprehensively analyzing the vehicle three-dimensional position coordinates of each vehicle bounding box within the set traffic road, the obstacle three-dimensional position coordinates of each obstacle bounding box, and the trajectory position coordinates of each path moving point, to obtain the vehicle three-dimensional position coordinates of the trajectory vehicle bounding box of each path moving point for each group of trajectory sections within the set traffic road, and the obstacle three-dimensional position coordinates of each trajectory obstacle bounding box; Comprehensively analyzing the vehicle three-dimensional position coordinates of the trajectory vehicle bounding box of the trajectory position coordinates of each path moving point of each set of trajectory sections within the set traffic road, the obstacle three-dimensional position coordinates of the trajectory obstacle bounding box, and the preset safety distance of the tidal robot, to obtain the offset distance of each path moving point of each set of trajectory sections within the set traffic road; Comprehensively analyze the trajectory position coordinates and offset distances of each path moving point of the tidal robot in each set of trajectory sections within the set traffic road, and obtain the offset position coordinates of several deviated moving points of the tidal robot in each set of trajectory sections within the set traffic road, namely, the offset three-dimensional vertical position coordinate value, the offset three-dimensional horizontal position coordinate value, and the offset three-dimensional height position coordinate value; Each deviated moving point and each path moving point of each group of trajectory sections of the tidal robot in the set traffic road are connected and processed to generate several moving trajectories of each group of trajectory sections of the tidal robot in the set traffic road, and each deviated moving point and each path moving point in each moving trajectory of each group of trajectory sections of the tidal robot in the set traffic road are uniformly marked as trajectory moving points, and the offset position coordinates of each deviated moving point and the path position coordinates of each path moving point are uniformly marked as trajectory position coordinates, that is, the three-dimensional vertical position coordinate value of the trajectory, the three-dimensional horizontal position coordinate value of the trajectory, and the three-dimensional height position coordinate value of the trajectory.

7. The method for controlling the movement trajectory of a tidal robot according to claim 6, wherein: The specific formula for calculating the offset position coordinates of each deviation moving point of the tidal robot in each set of trajectory sections within the set traffic road is as follows: ； in, To set the first The first segment of the group trajectory The offset three-dimensional vertical position coordinate value of the moving point, To set the first The first segment of the group trajectory The three-dimensional vertical position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional vertical position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional horizontal position coordinate value of the path moving point, To set the first The first segment of the group trajectory The three-dimensional horizontal position coordinate value of the path moving point, To set the first The first segment of the group trajectory The vehicle path distance of each path moving point, To set the first The first segment of the group trajectory The offset three-dimensional horizontal position coordinate value of the moving point, =1,2,3,…, , is the number of trajectory segment groups, =1,2,3,…, , The number of points to move along the path.

8. The method for controlling the movement trajectory of a tidal robot according to claim 1, wherein: The specific steps for obtaining the reliability index of each moving section of each moving trajectory of the tidal robot within the set traffic road are as follows: Dividing each moving trajectory of the tidal robot within the set traffic road based on a preset moving distance, and obtaining the trajectory position coordinates of a plurality of trajectory moving points of each moving section of each moving trajectory of the tidal robot within the set traffic road; Comprehensively analyzing the trajectory image data of each moving section of each moving trajectory of the tidal robot within the set traffic road, and obtaining real-time vehicle position coordinates of a plurality of real-time trajectory vehicle boundary boxes of each moving section of each moving trajectory of the tidal robot within the set traffic road, wherein the real-time vehicle position coordinates include a real-time trajectory three-dimensional vertical position coordinate value, a real-time trajectory three-dimensional horizontal position coordinate value, and a real-time trajectory three-dimensional height position coordinate value; And obtain the speed value of the tidal robot within the set traffic road; Perform prediction analysis on the initial position coordinates, speed value, and trajectory position coordinates of each moving point of each moving section of each moving trajectory of the tidal robot within the set traffic road, and obtain the predicted time value of each moving trajectory of each group of trajectory sections of the tidal robot within the set traffic road; The predicted time value of each moving trajectory of each group of trajectory sections of the tidal robot in the set traffic road is divided to obtain a number of predicted time points of each moving section of each moving trajectory of the tidal robot in the set traffic road; and obtain the predicted three-dimensional vertical position coordinate value, the predicted three-dimensional horizontal position coordinate value, and the predicted three-dimensional height position coordinate value of each moving section of each moving trajectory of the tidal robot within the set traffic road at each predicted time point, that is, the predicted real-time position coordinates; A comprehensive analysis is performed on the preset safety distance of the tidal robot within the set traffic road, the position coordinates of each real-time trajectory vehicle boundary box of each moving section of each moving trajectory, and the predicted real-time position coordinates of each predicted time point, to obtain the predicted collision distance of each moving trajectory of the tidal robot in each group of trajectory sections within the set traffic road, which is marked as the reliability index.

9. The method for controlling the movement trajectory of a tidal robot according to claim 8, characterized in that: The specific formula for calculating the predicted time value and predicted collision distance of each moving section of each moving trajectory of the tidal robot within the set traffic road is as follows: ; in, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The predicted time value of the moving section, is the initial three-dimensional vertical position coordinate value of the tidal robot in the set traffic road, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The three-dimensional vertical position coordinate value of the first moving point of the moving section, is the initial three-dimensional horizontal position coordinate value of the tidal robot in the set traffic road, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The three-dimensional horizontal position coordinate value of the first moving point of the moving section, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional vertical position coordinate value of the trajectory moving point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional vertical position coordinate value of the trajectory moving point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional horizontal position coordinate value of the trajectory moving point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The three-dimensional horizontal position coordinate value of the trajectory moving point, is the speed value of the tidal robot in the set traffic road, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The reliability index of the moving segment, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The predicted three-dimensional vertical position coordinate value at the prediction time point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The real-time trajectory three-dimensional vertical position coordinate value of the real-time trajectory vehicle boundary box, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The predicted three-dimensional horizontal position coordinate value at the prediction time point, The first time for the Tidal Robot to move within the set traffic path The first moving trajectory The first moving segment The real-time trajectory three-dimensional horizontal position coordinate value of the real-time trajectory vehicle boundary box, The preset safety distance for the Tide Robot within the set traffic road, =1,2,3,…, , is the number of moving trajectories, =1,2,3,…, , is the number of moving sections, =1,2,3,…, , is the number of trajectory segments, =1,2,3,…, , is the number of predicted time points, =1,2,3,…, , is the number of vehicle bounding boxes in real-time trajectory.

Images