Cruise path planning system and method for intelligent shifting vehicle

Abstract

The invention discloses a cruise path planning system and method for an intelligent shifting vehicle, and the method comprises the steps: collecting static and dynamic obstacle information in real time through a laser sensor, a monocular camera and a depth camera, and carrying out the processing through Kalman filtering, thereby obtaining precise obstacle information; a static path planning algorithm is adopted on a known map, and an initial path is found; historical pedestrian flow information in different time periods and seasons is collected, and the predicted pedestrian density on a specific route in a future period of time is analyzed by using a convolutional neural model; and optimizing path planning according to the predicted pedestrian density and the accurate obstacle information. Static and dynamic obstacle information in the environment is collected in real time through multiple sensors, Kalman filtering is used for data fusion and processing, historical pedestrian flow information is collected, deep learning analysis is carried out through a convolutional neural network, path planning is made to be based on current obstacle information, the pedestrian high density is predicted, and path planning precision is improved. Congested road sections are avoided in advance, and the perspectiveness and rationality of path planning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path navigation, and in particular to a cruise path planning system and method for an intelligent shifting vehicle. Background Art

[0002] As an auxiliary equipment, the transfer vehicle plays an important role in helping pedestrians with limited mobility to move to another location. Ensuring that pedestrians can be safely and efficiently transferred from one location to another is a vital task, especially in complex indoor environments. The frequent demand for pedestrian transfers puts considerable pressure on staff.

[0003] In a complex indoor environment, factors such as the unique spatial layout, crowd density, and equipment distribution bring many technical challenges to the path planning of the transfer machine. Currently, the path planning of the transfer machine is based on building a map to find the optimal path, but this method is only applicable to known environments. In an environment with complex crowd flow, it often causes parking and waiting due to the large flow of people, which consumes a lot of time and delays the transfer time. Summary of the invention

[0004] The present application provides a cruise path planning system and method for an intelligent shifting vehicle, which solves the technical problem in the prior art that the shifting vehicle frequently stops and waits in an environment with complex human flow, thus wasting time.

[0005] The present application provides a cruising path planning method for an intelligent shifting vehicle, comprising the following steps:

[0006] Step S1: collecting static and dynamic obstacle information in the environment in real time through at least one laser sensor, at least one monocular camera and at least one depth camera;

[0007] Step S2: Use Kalman filtering to process static and dynamic obstacle information from the laser sensor, monocular camera and depth camera to obtain accurate obstacle information;

[0008] Step S3: Using a static path planning algorithm on a known map to find a preliminary path from the starting point to the target point;

[0009] Step S4: Collect historical pedestrian flow information in different time periods and seasons, and use the convolutional neural model to analyze the predicted pedestrian density on a specific route in the future;

[0010] Step S5: Optimize path planning based on predicted pedestrian density and accurate obstacle information.

[0011] In some embodiments, in step S2, the static and dynamic obstacle information from the laser sensor, the monocular camera and the depth camera is processed using Kalman filtering to obtain accurate obstacle information, including:

[0012] Step S21: deploying laser sensors, monocular cameras and depth cameras at different positions on the shifter to cover the maximum range of the surrounding environment, collecting static and dynamic obstacle information in the environment in real time, determining system state variables, and initializing the covariance matrix;

[0013] Step S22: performing time synchronization processing on the information collected by the laser sensor, the monocular camera and the depth camera to remove noise data;

[0014] Step S23: state prediction, at each time step, the state transfer equation is used to predict the static and dynamic obstacle information at the current moment according to the static and dynamic obstacle information at the previous moment, and converted into predicted state variables through the observation equation;

[0015] Calculate the predicted covariance matrix based on the state transfer equation and the covariance matrix of the previous moment;

[0016] Step S24: Obtain the static and dynamic obstacle information at the current moment, convert it into observation state variables, and update the observation covariance matrix according to the observation state variables;

[0017] Step S25: Calculate the Kalman gain based on the prediction covariance matrix and the observation covariance matrix;

[0018] Step S26: obtaining updated predicted state variables according to the Kalman gain, predicted state variables and observed state variables, and obtaining an updated covariance matrix. The above steps are repeated at each time step.

[0019] In some embodiments, the static and dynamic obstacle information includes the location, size, speed and character status of the obstacle, and the character status includes the direction of the feet, the degree of leg bending, facial expression and line of sight direction.

[0020] In some embodiments, if the Kalman gain approaches 0, the reliability of the observation value at the current moment is low, and the predicted state variable is selected;

[0021] If the Kalman gain tends to 1, the reliability of the observation value at the current moment is high, and the observed state variable is selected.

[0022] In some embodiments, the step S4 collects historical pedestrian flow information in different time periods and seasons, uses a deep learning algorithm to analyze the general trend of pedestrian flow, and analyzes the predicted pedestrian density on a specific route in the future period of time, including:

[0023] Collect pedestrian flow information at different times of the day and throughout the year, build a convolutional neural network, and output predicted pedestrian density information.

[0024] In some embodiments, the step S5: optimizing the path planning according to the predicted pedestrian density and accurate obstacle information includes:

[0025] Build a deep learning model integrating Kalman filter and convolutional neural network:

[0026] Step S51: fusing the precise obstacle information output by the Kalman filter and the predicted pedestrian density information output by the convolutional neural network as input to the deep learning model;

[0027] Step S52: Based on the information fused in step S51, the Dijkstra algorithm is used for path planning.

[0028] In some embodiments, the step S51: fusing the precise obstacle information output by the Kalman filter and the predicted pedestrian density information output by the convolutional neural network includes:

[0029] Input layer: receives accurate obstacle information output by the Kalman filter and predicted pedestrian density information output by the convolutional neural network;

[0030] Middle layer: The first layer processes the accurate obstacle information output by the Kalman filter, and the second layer processes the predicted pedestrian density information output by the convolutional neural network;

[0031] Fusion layer: The output information of the intermediate layer is fused using the weighted summation method.

[0032] In some embodiments, the step S52: performing path planning using the Dijkstra algorithm based on the information fused and processed in step S51 includes:

[0033] Convert real-time dynamic obstacle information into a heat map, and determine that the high-density area in the heat map is a pedestrian concentration area;

[0034] The real-time dynamic obstacle information of individuals is converted into moving direction and speed, and individuals with slow movement speed and uncertain direction are identified as pedestrians.

[0035] The pedestrian concentration area and pedestrian labels are input into the Dijkstra algorithm for further path planning.

[0036] A path planning system for a shifting vehicle, applying any of the methods described in the above technical solutions, the system comprising:

[0037] A sensing module, including at least one laser sensor, at least one monocular camera and at least one depth camera, for collecting static and dynamic obstacle information in the environment in real time;

[0038] A data processing module, used for processing data information from the sensor module;

[0039] Data analysis module, used to collect information on passenger flow at different times of the day and throughout the year;

[0040] The fusion and decision module is used to integrate the information output by the data processing module and the data analysis module;

[0041] A path planning module is used to plan the path based on the fused information;

[0042] The control system controls the movement of the lift according to the planned path planning information.

[0043] In some embodiments, the laser sensor and the monocular camera are installed at two ends of the same side of the transfer machine, and the depth camera is installed at the head of the bed of the transfer machine.

[0044] The beneficial effects of this application are as follows:

[0045] 1. Through real-time collection of static and dynamic obstacle information in the environment by multiple sensors, historical pedestrian flow information is collected, and deep learning analysis is performed using convolutional neural networks. This allows path planning to be based not only on current obstacle information, but also on the foreseeable high-density areas that may appear in the future. This greatly reduces the risk of collisions, improves the operational safety of the shift vehicle in places with complex personnel, avoids congested roads in advance, improves the foresight and rationality of path planning, optimizes path planning, reduces delays and waiting time during transportation, enables the equipment to complete tasks more quickly, and improves the overall experience of users and pedestrians.

[0046] 2. The application of Kalman filtering enables the system to process data from multiple sensors in real time and update obstacle information in a timely manner even in a dynamically changing environment, so that the shifting vehicle can respond quickly to emergencies and adjust the path to avoid new obstacles, thereby enhancing the system's real-time and dynamic obstacle avoidance capabilities.

[0047] 3. By converting real-time dynamic obstacle information into a heat map and combining it with the predicted pedestrian density information, pedestrians and pedestrian concentration areas can be dynamically identified. The real-time updated information enables the path planning algorithm to respond quickly to environmental changes and adjust the path in time to avoid high-density areas, thereby improving the real-time and dynamic adaptability of path planning; incorporating pedestrian concentration areas and pedestrian labels as input into the Dijkstra algorithm can more accurately avoid potential risk areas and ensure that the shift vehicle does not conflict with pedestrians when performing tasks, thereby improving the safety and accuracy of path planning; the system can predict the pedestrian density in the future and optimize the path planning accordingly, so it can effectively reduce the delay caused by temporary obstacles or high-density areas and improve the work efficiency of the shift vehicle in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention.

[0049] Figure 1 A flow chart of a cruising path planning method for an intelligent shifting vehicle provided in this application;

[0050] Figure 2 A schematic diagram of the module connection relationship of a path planning system for a shifting vehicle provided in this application. DETAILED DESCRIPTION

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

[0052] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0053] In addition, the descriptions of "first", "second", etc. in this application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0054] The embodiments of the present application provide a cruise path planning system and method for an intelligent shifting vehicle, thereby solving the technical problem in the prior art that a shifting vehicle frequently stops and waits in an environment with complex human flow, which wastes time.

[0055] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0056] like Figure 1 As shown, the present application provides a cruising path planning method for an intelligent shifting vehicle, comprising the following steps:

[0057] Step S1: Use at least one laser sensor, at least one monocular camera, and at least one depth camera to collect static and dynamic obstacle information in the environment in real time. The laser sensors are deployed at different positions of the lift to detect obstacles in the surrounding environment, especially obstacles at a long distance. The monocular camera is used to capture image information in the environment, which can assist in identifying the shape, color and other visual features of the obstacles. The depth camera provides three-dimensional depth information to help accurately measure the distance and height of the obstacles. Specifically, static obstacle information includes the location and size of the obstacles, dynamic obstacle information includes the location, speed and moving direction of the obstacles, and character status information includes the direction of the feet, the degree of leg bending, facial expressions and line of sight, which helps to judge the character's behavioral intentions.

[0058] Step S2: Use Kalman filtering to process static and dynamic obstacle information from the laser sensor, monocular camera and depth camera to obtain accurate obstacle information;

[0059] Step S3: Using a static path planning algorithm on a known map, in this embodiment, using the Dijkstra algorithm, to find a preliminary path from the starting point to the target point;

[0060] Step S4: Collect historical pedestrian flow information in different time periods and seasons, including changes in pedestrian flow at different times of the day and throughout the year, such as morning peak, noon, evening peak, night, etc., and pedestrian flow information in spring, summer, autumn, and winter, and use the convolutional neural model to analyze the predicted pedestrian density on a specific route in the future.

[0061] Step S5: Optimize path planning based on predicted pedestrian density and accurate obstacle information.

[0062] Through real-time collection of static and dynamic obstacle information in the environment by multiple sensors, and through the collection of historical pedestrian flow information and deep learning analysis using convolutional neural networks, path planning is not only based on current obstacle information, but can also foresee high-density areas that may appear in the future, greatly reducing the risk of collisions, improving the operational safety of the shift vehicle in a complex environment with people, avoiding congested roads in advance, improving the foresight and rationality of path planning, optimizing path planning, reducing delays and waiting time of the shift vehicle during transportation, enabling the equipment to complete tasks more quickly, and improving the overall experience of users and pedestrians.

[0063] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0064] In step S2, the static and dynamic obstacle information from the laser sensor, the monocular camera and the depth camera are processed using Kalman filtering to obtain accurate obstacle information, including:

[0065] Step S21: Deploy laser sensors, monocular cameras and depth cameras at different positions on the shifter to cover the maximum range of the surrounding environment, collect static and dynamic obstacle information in the environment in real time, determine the system state variables, and initialize the covariance matrix P 0 , represents the uncertainty of the estimate of the initial state;

[0066] Step S22: performing time synchronization processing on the information collected by the laser sensor, the monocular camera and the depth camera to ensure that the data from different sensors are synchronized in time, eliminate time deviation, remove noise data, and retain useful information;

[0067] Step S23: state prediction, at each time step, the state transfer equation is used to predict the static and dynamic obstacle information at the current moment according to the static and dynamic obstacle information at the previous moment, and converted into predicted state variables through the observation equation;

[0068] The state transfer equation is:

[0069]

[0070] in, is the state estimate at the current moment, A is the state transfer matrix, B is the control input matrix, u t is the control input, w t is the process noise.

[0071] According to the state transfer equation and the covariance matrix P of the previous moment t , calculate the prediction covariance matrix P t+1 ;

[0072] P t+1 =AP t A T +Q

[0073] where Q is the covariance matrix of the process noise.

[0074] Step S24: Obtain the static and dynamic obstacle information at the current moment, convert it into observation state variables, and update the observation covariance matrix according to the observation state variables;

[0075] The observation equation is:

[0076]

[0077] Where H is the observation matrix, v t is the observation noise.

[0078] According to the observed state variable z t Update the observation covariance matrix R t :

[0079] R t =HP t H T +V

[0080] where V is the covariance matrix of the observation noise.

[0081] Step S25: According to the prediction covariance matrix P t+1 and the observation covariance matrix R t The Kalman gain K is calculated t ;

[0082] K t =P t+1 H T (HP t+1 H T +R) -1

[0083] If the Kalman gain tends to 0, the reliability of the observation value at the current moment is low, and the predicted state variable is selected;

[0084] If the Kalman gain tends to 1, the reliability of the observation value at the current moment is high, and the observed state variable is selected.

[0085] Step S26: According to the Kalman gain K t , predict state variables and the observed state variable z t The updated predicted state variables are obtained, and the updated covariance matrix is ​​obtained. The above steps are repeated at each time step.

[0086] Update the predicted state variables:

[0087]

[0088] Update the covariance matrix:

[0089]

[0090] In a crowded environment, a cart that suddenly appeared in front was detected by the laser sensor. The monocular camera and depth camera provided the shape and distance information of the cart. The Kalman filter integrated this information and predicted the future position of the cart. The lift adjusted the path in time according to the predicted information, successfully avoided the cart and ensured safe passage.

[0091] Furthermore, the step S5: optimizing the path planning according to the predicted pedestrian density and accurate obstacle information includes:

[0092] Build a deep learning model integrating Kalman filter and convolutional neural network:

[0093] Step S51: fusing the precise obstacle information output by the Kalman filter and the predicted pedestrian density information output by the convolutional neural network as input to the deep learning model;

[0094] Specifically, step S51 includes:

[0095] Input layer: receives accurate obstacle information output by the Kalman filter and predicted pedestrian density information output by the convolutional neural network;

[0096] Middle layer: The first layer processes the accurate obstacle information output by the Kalman filter, and the second layer processes the predicted pedestrian density information output by the convolutional neural network;

[0097] Fusion layer: The output information of the intermediate layer is fused using the weighted summation method.

[0098] Step S52: Based on the information fused and processed in step S51, the Dijkstra algorithm is used for path planning. Specifically, a graph structure is constructed according to the fused information, in which nodes represent locations on the map and edges represent accessibility between two points. Weights are defined for edges in the graph according to the fused information. Areas with higher pedestrian density can be given higher weights, and obstacle areas can be set to have infinite weights.

[0099] The Dijkstra algorithm is used to find the shortest path from the starting point to the target point. The distance from the starting point to each node is continuously updated according to the weight until the target point is found. It can not only avoid static obstacles, but also optimize the path according to the dynamic crowd density information, ensuring that the shifting vehicle can reach the destination safely and efficiently.

[0100] Preferably, step S52 includes:

[0101] Convert real-time dynamic obstacle information into a heat map, and determine that the high-density area in the heat map is a pedestrian concentration area;

[0102] The real-time dynamic obstacle information of individuals is converted into moving direction and speed, and individuals with slow movement speed and uncertain direction are identified as pedestrians.

[0103] The pedestrian concentration area and pedestrian labels are input into the Dijkstra algorithm for further path planning.

[0104] By converting real-time dynamic obstacle information into a heat map and combining it with predicted pedestrian density information, pedestrians and pedestrian concentration areas can be dynamically identified. The real-time updated information enables the path planning algorithm to respond quickly to environmental changes and adjust the path in time to avoid high-density areas, thereby improving the real-time and dynamic adaptability of path planning; incorporating pedestrian concentration areas and pedestrian labels as input into the Dijkstra algorithm can more accurately avoid potential risk areas and ensure that the shift vehicle does not conflict with pedestrians when performing tasks, thereby improving the safety and accuracy of path planning; the system can predict the pedestrian density in the future and optimize the path planning accordingly, so it can effectively reduce the delay caused by temporary obstacles or high-density areas and improve the work efficiency of the shift vehicle in complex environments.

[0105] like Figure 2 As shown, a path planning system for a shifting vehicle is applied using any one of the methods described in the above technical solutions, and the system includes:

[0106] A sensing module, including at least one laser sensor, at least one monocular camera and at least one depth camera, for collecting static and dynamic obstacle information in the environment in real time;

[0107] A data processing module, used for processing data information from the sensor module;

[0108] Data analysis module, used to collect information on passenger flow at different times of the day and throughout the year;

[0109] The fusion and decision module is used to integrate the information output by the data processing module and the data analysis module;

[0110] A path planning module is used to plan the path based on the fused information;

[0111] The control system controls the movement of the lift according to the planned path planning information.

[0112] Specifically, the laser sensor and the monocular camera are installed at two ends of the same side of the transfer machine, and the depth camera is installed at the head of the bed of the transfer machine.

[0113] The path planning system of the shift vehicle integrates multiple sensors such as laser sensors, monocular cameras and depth cameras to collect static and dynamic obstacle information in the environment in real time, and uses Kalman filtering technology to fuse and process these data to obtain accurate obstacle information; at the same time, the system collects pedestrian flow information in different time periods and seasons, and uses convolutional neural networks to predict the pedestrian density on a specific route in the future; by fusing the processed obstacle information and pedestrian density prediction data, the system uses path planning algorithms such as the Dijkstra algorithm to optimize the path from the starting point to the target point, and adjusts the movement of the shift machine in real time according to the planned path information through the control system to ensure that it can reach the destination safely and efficiently in a complex environment, thereby significantly improving the operating efficiency and safety of the shift machine.

[0114] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other 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.

[0115] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A cruising path planning method for an intelligent shifting vehicle, characterized in that: The following steps are involved: Step S1: collecting static and dynamic obstacle information in the environment in real time through at least one laser sensor, at least one monocular camera and at least one depth camera; Step S2: Use Kalman filtering to process static and dynamic obstacle information from the laser sensor, monocular camera and depth camera to obtain accurate obstacle information; Step S3: Using a static path planning algorithm on a known map to find a preliminary path from the starting point to the target point; Step S4: Collect historical pedestrian flow information in different time periods and seasons, and use the convolutional neural model to analyze the predicted pedestrian density on a specific route in the future; Step S5: Optimize path planning based on predicted pedestrian density and accurate obstacle information.

2. The cruising path planning method of the intelligent shifting vehicle according to claim 1, characterized in that: In step S2, the static and dynamic obstacle information from the laser sensor, the monocular camera and the depth camera are processed using Kalman filtering to obtain accurate obstacle information, including: Step S21: deploying laser sensors, monocular cameras and depth cameras at different positions on the shifter to cover the maximum range of the surrounding environment, collecting static and dynamic obstacle information in the environment in real time, determining system state variables, and initializing the covariance matrix; Step S22: performing time synchronization processing on the information collected by the laser sensor, the monocular camera and the depth camera to remove noise data; Step S23: state prediction, at each time step, the state transfer equation is used to predict the static and dynamic obstacle information at the current moment according to the static and dynamic obstacle information at the previous moment, and converted into predicted state variables through the observation equation; Calculate the predicted covariance matrix based on the state transfer equation and the covariance matrix of the previous moment; Step S24: Obtain the static and dynamic obstacle information at the current moment, convert it into observation state variables, and update the observation covariance matrix according to the observation state variables; Step S25: Calculate the Kalman gain based on the prediction covariance matrix and the observation covariance matrix; Step S26: obtaining updated predicted state variables according to the Kalman gain, predicted state variables and observed state variables, and obtaining an updated covariance matrix. The above steps are repeated at each time step.

3. The cruising path planning method of the intelligent shifting vehicle according to claim 2, characterized in that: Static and dynamic obstacle information includes the location, size, speed and character status of the obstacle. The character status includes the direction of the foot, the degree of leg bending, facial expression and line of sight direction.

4. The cruising path planning method of the intelligent shifting vehicle according to claim 2, characterized in that: If the Kalman gain tends to 0, the reliability of the observation value at the current moment is low, and the predicted state variable is selected; If the Kalman gain tends to 1, the reliability of the observation value at the current moment is high, and the observed state variable is selected.

5. The cruising path planning method of the intelligent shifting vehicle according to claim 1, characterized in that: In step S4, historical pedestrian flow information in different time periods and seasons is collected, and the general trend of pedestrian flow is analyzed using a deep learning algorithm. The predicted pedestrian density on a specific route in the future period is analyzed, including: Collect pedestrian flow information at different times of the day and throughout the year, build a convolutional neural network, and output predicted pedestrian density information.

6. The method for cruising path planning of an intelligent shifting vehicle according to claim 5, characterized in that: The step S5: optimizing the path planning according to the predicted pedestrian density and accurate obstacle information includes: Build a deep learning model integrating Kalman filter and convolutional neural network: Step S51: fusing the precise obstacle information output by the Kalman filter and the predicted pedestrian density information output by the convolutional neural network as input to the deep learning model; Step S52: Based on the information fused and processed in step S51, the Dijkstra algorithm is used for path planning.

7. The cruising path planning method of the intelligent shifting vehicle according to claim 6, characterized in that: The step S51: fusing the precise obstacle information output by the Kalman filter and the predicted pedestrian density information output by the convolutional neural network includes: Input layer: receives accurate obstacle information output by the Kalman filter and predicted pedestrian density information output by the convolutional neural network; Middle layer: The first layer processes the accurate obstacle information output by the Kalman filter, and the second layer processes the predicted pedestrian density information output by the convolutional neural network; Fusion layer: The output information of the intermediate layer is fused using the weighted summation method.

8. The method for cruising path planning of an intelligent shifting vehicle according to claim 6, characterized in that: The step S52: based on the information fused and processed in step S51, using the Dijkstra algorithm to perform path planning includes: Convert real-time dynamic obstacle information into a heat map, and determine that the high-density area in the heat map is a pedestrian concentration area; The real-time dynamic obstacle information of individuals is converted into moving direction and speed, and individuals with slow movement speed and uncertain direction are identified as pedestrians. The pedestrian concentration area and pedestrian labels are input into the Dijkstra algorithm for further path planning.

9. A cruise path planning system for an intelligent shifting vehicle, characterized in that: The method according to any one of claims 1 to 8 is applied, wherein the system comprises: A sensing module, including at least one laser sensor, at least one monocular camera and at least one depth camera, for collecting static and dynamic obstacle information in the environment in real time; A data processing module, used for processing data information from the sensor module; Data analysis module, used to collect information on passenger flow at different times of the day and throughout the year; The fusion and decision module is used to integrate the information output by the data processing module and the data analysis module; A path planning module is used to plan a path based on the fused information; The control system controls the movement of the lift according to the planned path planning information.

10. The cruise path planning system of the intelligent shifting vehicle according to claim 9, characterized in that: The laser sensor and the monocular camera are installed at two ends of the same side of the transfer machine, and the depth camera is installed at the head of the bed of the transfer machine.

Images