Airport tractor cargo falling detection system and method based on LTE-V
Through the LTE-V-based airport tractor cargo drop detection system, the combination of road testing equipment and vehicle-end equipment is used to monitor and process image data in real time, and the problem of cargo drop detection when the autonomous tractor is towed full load is solved. The safety of goods and transportation efficiency have been improved.
Patent Information
- Application Number
- CN202411027753.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-15
AI Technical Summary
The autonomous tractor cannot effectively detect the drop of goods when towed full load. The sensor's perception range and accuracy are insufficient, resulting in the inability to identify and handle the drop of goods in a timely manner, increasing economic losses and safety risks.
Adopt the LTE-V-based airport tractor cargo drop detection system, through the combination of road testing equipment, vehicle-end equipment and dispatching platform, using cameras, RSU units, vehicle-mounted OBU equipment, domain controllers, high-precision maps and radars in real time Collect and process image data, judge the drop of goods, and issue alarms and processing instructions.
Real-time monitoring and rapid response to cargo drops are achieved, driving safety and transportation efficiency are improved, costs and risks are reduced, and the integrity of cargo is ensured.
Smart Images

Figure CN118966947A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent transportation technology, and in particular to an airport tractor cargo drop detection system and method based on LTE-V. Background Art
[0002] With the continuous advancement of artificial intelligence, computer vision and sensor technology, driverless technology has made great progress in the automotive field. Autonomous driving technology can be applied not only to passenger cars and commercial vehicles, but also to autonomous driving of traction vehicles.
[0003] Towing vehicles play an important role in the field of logistics and transportation, and are often used to move goods between factories, warehouses, ports, etc. Autonomous driving technology can improve the efficiency and safety of towing vehicles and reduce the risk of human error and accidents.
[0004] When implementing autonomous driving tractor technology, it is often necessary to consider the collaborative work between multiple vehicles. Through communication and collaborative control between vehicles, collaborative operation between multiple tractor vehicles can be achieved, improving traction efficiency and safety.
[0005] The logistics and transportation industries are important application areas for autonomous tractor technology. These industries are facing problems such as shortage of human resources, low transportation efficiency and high safety risks. Autonomous tractor technology can effectively solve these problems and improve the industry's operational efficiency and competitiveness.
[0006] Although the technology of autonomous driving tractor is very mature now, and many cities now have unmanned driving, which has solved some problems, it is still difficult for many companies to make profits through unmanned vehicles. Compared with open roads, closed airport environments are more suitable for unmanned vehicle technology. Therefore, the technology of autonomous driving tractor in airport environment was born. Autonomous driving tractor in airport environment is easier to achieve, but this is only limited to the case where the tractor does not load cargo on a trailer. When the autonomous driving tractor is driving with a fully loaded trailer, many problems will arise, and the problem of cargo falling will follow. Ordinary autonomous driving tractor technology cannot solve this problem. Generally speaking, various sensors are installed on autonomous driving tractors, but these sensors have a sensing range and a sensing blind spot. They cannot sense the fallen cargo when there are a large number of trailers, nor can they identify the cargo that is very close to the trailer or under the trailer. In addition, it is not only difficult to achieve the detection of cargo falling by installing sensors only on the tractor, but the sensors required are also relatively expensive. The cost of sensors with higher accuracy will also increase accordingly.
[0007] With the development of communication technology, a communication technology called LTE-V has been rapidly developed. It is applied to autonomous driving technology, which can connect vehicles to various surrounding devices, including other vehicles, infrastructure and pedestrians. Based on this, the present invention proposes an airport tractor cargo drop detection system and method based on LTE-V, which can ensure the integrity of cargo in the airport tractor automatic driving. Summary of the invention
[0008] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an airport tractor cargo drop detection system and method based on LTE-V, which can reduce the time loss caused by cargo dropping, avoid secondary damage and economic compensation caused by cargo dropping, and ensure the integrity of the cargo.
[0009] The purpose of the present invention is achieved through the following technical solutions:
[0010] An airport tractor cargo drop detection system based on LTE-V includes a road test device, a vehicle-side device and a dispatching platform, wherein:
[0011] The road test equipment is installed above the working road of the tractor; the vehicle-side equipment is installed on the tractor;
[0012] The road test equipment collects the running status of the tractor and sends the collected image data to the vehicle-side equipment and the dispatching platform through LTE-V technology;
[0013] The vehicle-side device and the dispatching platform receive the image data and determine whether cargo has fallen, and issue an alarm when cargo has fallen.
[0014] Optionally or preferably, the road test equipment includes a camera and an RSU unit; the camera monitors the operating status of the tractor in real time, and the collected image data is shared by the RSU unit in real time to the vehicle-side equipment and the dispatching platform through LTE-V technology.
[0015] Optionally or preferably, the vehicle-side device includes an on-board OBU device and a domain controller; the on-board OBU device is used to receive image data from the road test equipment and transmit the image data to the domain controller; the domain controller uses a deep learning model to process the image data to determine the operating status of the tractor; when cargo falls off the tractor, the domain controller controls the tractor to issue an alarm.
[0016] Optionally or preferably, the vehicle-side device also includes a high-precision map and a radar; the domain controller performs fusion perception of the image data, high-precision map data and radar data, determines whether the tractor is traveling on the running track, and calculates the falling distance of the fallen cargo.
[0017] Optionally or preferably, the dispatching platform receives image data from the road test equipment, integrates, analyzes and processes the image data, determines the operating status of the tractor, and issues an alarm to ground staff when cargo falls from the tractor.
[0018] The present invention also discloses a cargo drop detection method, which is based on the above-mentioned LTE-V airport tractor cargo drop detection system, comprising the following steps:
[0019] S1. Road test equipment collects image data on the working road in real time;
[0020] S2. The road test equipment shares the image data with the vehicle-side equipment and the dispatching platform in real time through the RSU unit;
[0021] S3, the vehicle-mounted OBU device and the dispatching platform in the vehicle-side device both receive the image data and perform cargo drop detection respectively;
[0022] S4. If the on-board OBU device detects that cargo has fallen, the domain controller will control the tractor to stop and enter the alarm state, and make light and horn alarms; if no cargo has fallen, the task will continue;
[0023] S5. When the tractor enters the alarm state, the domain controller integrates the high-precision map and radar data to calculate the drop distance of the dropped goods and determine whether the tractor is running on the running track. If the tractor is running on the running track, the dispatching platform will send ground staff to deal with the dropped goods; if it is not running on the running track, the platform will continue to issue tasks, execute the current tasks, and notify the ground staff to deal with the problem; when the vehicle is abnormal, the vehicle will stop, and if other vehicles have other routes to travel, the dispatching platform will issue tasks to avoid obstacles through different routes. If there are no other routes to travel, the remaining vehicles will all stop where they are;
[0024] S6. If the dispatching platform detects that cargo has fallen, it will issue tasks to the ground staff. After receiving the tasks, the ground staff will deal with the cargo falling problem. After the problem is solved, the dispatching platform will continue to issue tasks.
[0025] Based on the above technical solution, the present invention provides an airport tractor cargo drop detection system and method based on LTE-V, which can produce the following technical effects:
[0026] (1) The road test equipment, vehicle-side equipment and dispatching platform of the present invention transmit and communicate data through LTE-V technology to form a closed loop for cargo drop detection;
[0027] (2) The present invention can ensure the real-time and accuracy of monitoring the running status of the tractor;
[0028] (3) The present invention can improve driving safety, increase traffic efficiency, reduce costs, and reduce risks. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.
[0030] Figure 1 It is a schematic diagram of the system installation of the present invention;
[0031] Figure 2 It is a schematic diagram of the system structure of the present invention;
[0032] Figure 3 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION
[0033] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0035] Embodiment 1:
[0036] This embodiment provides an airport tractor cargo drop detection system based on LTE-V, including: a road test device, a vehicle-side device and a dispatching platform; Figure 1 As shown, the road test equipment is installed above the working road of the tractor; the vehicle-side equipment is installed on the tractor;
[0037] like Figure 2 As shown, the road test equipment includes a roadside camera and an RSU unit; the vehicle-side equipment includes an on-board OBU device, a domain controller, a high-precision map and a radar, wherein:
[0038] The roadside camera monitors the running status of the tractor in real time, and sends the collected image data to the vehicle-side equipment and the dispatching platform through the RSU unit via LTE-V technology;
[0039] The vehicle-side device receives the image data from the road test device, and the vehicle-mounted OBU device transmits the image data to the domain controller;
[0040] The domain controller uses a deep learning model to process the image data, judge the operating status of the tractor, and control the tractor to issue an alarm when cargo falls off the tractor;
[0041] Specifically, the domain controller is the Tianhuai GEACX1 domain controller; the vehicle-mounted OBU device is the Jinyi CB-LS20 vehicle-mounted OBU device.
[0042] In this embodiment, the deep learning model is a convolutional neural network, including a convolutional layer, a pooling layer, and a fully connected layer.
[0043] When the tractor issues an alarm, the domain controller integrates the image data, high-precision map data and radar data to determine whether the tractor is on the running track and calculate the distance between the dropped cargo and the tractor's front and trailer;
[0044] The dispatching platform receives the image data from the road test equipment, integrates, analyzes and processes the image data, determines the running status of the tractor, and issues an alarm to the ground staff when cargo falls off the tractor;
[0045] When cargo falls off the tractor, the tractor stops and sounds an alarm, and the dispatching platform sounds an alarm and displays the specific location of the cargo, enabling a quick response.
[0046] like Figure 3 As shown, a cargo drop detection method provided by the present invention is based on the above-mentioned LTE-V airport tractor cargo drop detection system, comprising the following steps:
[0047] S1. Road test equipment collects image data on the working road in real time;
[0048] S2. The road test equipment shares the image data with the vehicle-side equipment and the dispatching platform in real time through the RSU unit;
[0049] S3, the vehicle-mounted OBU device and the dispatching platform in the vehicle-side device both receive the image data and perform cargo drop detection respectively;
[0050] S4. If the on-board OBU device detects that cargo has fallen, the domain controller will control the tractor to stop and enter the alarm state, and make light and horn alarms; if no cargo has fallen, the task will continue;
[0051] S5. When the tractor enters the alarm state, the domain controller integrates the high-precision map and radar data to calculate the drop distance of the dropped goods and determine whether the tractor is running on the running track. If the tractor is running on the running track, the dispatching platform will send ground staff to deal with the dropped goods; if it is not running on the running track, the platform will continue to issue tasks, execute the current tasks, and notify the ground staff to deal with the problem; when the vehicle is abnormal, the vehicle will stop, and if other vehicles have other routes to travel, the dispatching platform will issue tasks to avoid obstacles through different routes. If there are no other routes to travel, the remaining vehicles will all stop where they are;
[0052] S6. If the dispatching platform detects that cargo has fallen, it will issue a task to the ground staff. After receiving the task, the ground staff will deal with the cargo falling problem. After the problem is solved, the dispatching platform will continue to issue tasks. Specifically, after handling the fallen cargo, the ground staff will update and report the vehicle status to the dispatching platform through the task tablet.
[0053] This embodiment can achieve the following effects:
[0054] (1) It can monitor the operating status of the autonomous tractor with trailer in real time;
[0055] (2) It can determine in real time whether the autonomous tractor is currently unloaded or fully loaded;
[0056] (3) The current driving direction of the autonomous driving traction can be determined in real time;
[0057] (4) Can detect in real time whether there are abnormal conditions on the road;
[0058] (5) Can quickly detect whether any cargo has fallen in real time;
[0059] (6) The platform can quickly issue alerts and issue processing tasks;
[0060] (7) The vehicle can quickly sound an alarm and attract the attention of staff through lights and sounds;
[0061] (8) The self-driving tractor can be stopped in time to prevent secondary damage to the cargo;
[0062] (9) Transportation work can continue without affecting the safety of the goods, thereby improving work efficiency and reducing unnecessary stop time.
[0063] The above is only a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art shall not deviate from the spirit and scope of the present invention, and shall be within the scope of protection of the claims attached to the present invention.
Claims
1. The airport tractor cargo drop detection system based on LTE-V is characterized by: include: Road test equipment, vehicle-side equipment and dispatching platform, including: The road test equipment is installed above the working road of the tractor; The vehicle-end equipment is installed on the tractor; The road test equipment collects the running status of the tractor and sends the collected image data to the vehicle-side equipment and the dispatching platform through LTE-V technology; The vehicle-side device and the dispatching platform receive the image data and determine whether cargo has fallen, and issue an alarm when cargo has fallen.
2. The LTE-V-based airport tractor cargo drop detection system according to claim 1 is characterized by: The road test equipment includes a camera and an RSU unit; the camera monitors the operating status of the tractor in real time, and the RSU unit shares the collected image data with the vehicle-side equipment and the dispatching platform in real time through the LTE-V technology.
3. The LTE-V-based airport tractor cargo drop detection system according to claim 1, characterized in that: The vehicle-side device includes an on-board OBU device and a domain controller; the on-board OBU device is used to receive image data from the road test equipment and transmit the image data to the domain controller; the domain controller uses a deep learning model to process the image data to determine the operating status of the tractor; when cargo falls off the tractor, the domain controller controls the tractor to issue an alarm.
4. The LTE-V-based airport tractor cargo drop detection system according to claim 3 is characterized by: The vehicle-side equipment also includes a high-precision map and a radar; the domain controller integrates the image data, the high-precision map data and the radar data to determine whether the tractor is traveling on the running track and calculate the distance between the dropped cargo and the tractor's front and trailer.
5. The LTE-V-based airport tractor cargo drop detection system according to claim 1 is characterized by: The dispatching platform receives the image data from the road test equipment, integrates, analyzes and processes the image data, determines the operating status of the tractor, and issues an alarm to the ground staff when cargo falls off the tractor.
6. A cargo drop detection method, characterized in that: The airport tractor cargo drop detection system based on any one of claims 1 to 6, comprising the following steps: S1. Road test equipment collects image data on the working road in real time; S2. The road test equipment shares the image data with the vehicle-side equipment and the dispatching platform in real time through the RSU unit; S3, the vehicle-mounted OBU device and the dispatching platform in the vehicle-side device both receive the image data and perform cargo drop detection respectively; S4. If the on-board OBU device detects that cargo has fallen, the domain controller will control the tractor to stop and enter the alarm state, and make light and horn alarms; if no cargo has fallen, the task will continue; S5. When the tractor enters the alarm state, the domain controller integrates the high-precision map and radar data to calculate the drop distance of the dropped goods and determine whether the tractor is running on the running track. If the tractor is running on the running track, the dispatching platform will send ground staff to deal with the dropped goods; if it is not running on the running track, the ground staff will be notified to deal with the problem; when the vehicle is abnormal, the vehicle will stop, and other vehicles will be assigned tasks by the dispatching platform if there are other routes to travel, and avoid obstacles through different routes. If there are no other routes to travel, the remaining vehicles will all stop where they are; S6. If the dispatching platform detects that cargo has fallen, the dispatching platform will issue a command and a task to the ground staff. After receiving the task, the ground staff will deal with the cargo falling problem. After the problem is solved, the dispatching platform will continue to issue tasks.
7. A cargo drop detection method according to claim 6, characterized in that: The Kalman filter is used to calculate the drop distance of the goods, including the following steps: A1. Obtain the current state prediction value h(k) and error covariance matrix [P(k)]: [P(k)]=[F K ]·[P(k-1)]·[F K ] T +[Q K ] Where k represents time; h(k) is the state prediction value at time k; h(k-1) is the state prediction value at time k-1; [F K ] is the state transition matrix, which describes how the state changes over time; [B K ] is the control input matrix; [U K ] is the control input; [P(k)] is the error covariance matrix predicted at time k; [P(k-1)] is the error covariance matrix predicted at time k-1; [Q K ] is the process noise covariance matrix; A2. Update the state prediction value h(k) and the error covariance matrix [P(k)] to obtain the updated state prediction value h(k') and the updated error covariance matrix [P(k')]: [K K ]=[P(k-1)]·[H K ] T ·([H K ]·[P(k)]·[H K ] T +[R K ]) -1 h(k′)=h(k)+[K K ]·([Z K ]-[H K ]·h(k)) [P(k')]=([I]-[K K ]·[H K ])·[P(k)] Among them, [K K ] is the Kalman gain; [H K ] is the observation matrix, describing how measurements are associated with states; [R K ] is the measurement noise covariance matrix; [Z K ] is the measured value at time k; h(k') is the updated state prediction value at time k [P(k')] is the updated error covariance matrix at time k; [I] is the identity matrix.
Citation Information
Cited By
Highway automatic driving risk identification system based on multi-mode AI model
CN121084404A
