Method for emergency escape of a transport device and transport device

Abstract

The application discloses an emergency avoiding method of a transportation device and the transportation device, and the emergency avoiding method comprises the following steps: firstly, a data collecting step, a head camera of the transportation device is used to collect a moving direction image, and the size, speed, moving direction and relative distance of an obstacle are recognized; secondly, an evaluation and calculation step, the collision probability and the predicted collision time of the transportation device and the obstacle are calculated in combination with image information and radar data; and finally, a response step, when the collision probability exceeds a first probability threshold value and the predicted collision time is shorter than a first time threshold value, the transportation device is automatically controlled to adjust the moving direction or the moving speed to complete the emergency avoiding, and if the threshold value is not triggered, only a warning is given. The method relies on visual recognition, can recognize the transportation device without an AIS device and various obstacles, the calculation result is accurate and reliable, and can meet the requirement of being used as the basis for automatically controlling the transportation device to change the moving direction and the moving speed for emergency avoiding in the response step.

Description

Technical Field

[0001] This invention relates to the field of transportation device operation and safety technology, specifically to an emergency avoidance method for a transportation device and a transportation device. Background Technology

[0002] Ship safety protection systems are protective systems used to ensure the safe navigation of ships, and are widely used in various situations such as maritime navigation, port entry and exit, and waterway navigation. With the development of the shipping industry and the accelerating trend of larger ships, users have increasingly higher requirements for the intelligence level and emergency response capabilities of ship safety protection systems.

[0003] Existing ship avoidance systems typically rely solely on AIS (Air Traffic Regulator) data and active detection data such as radar to calculate the probability of a collision with an obstacle, taking into account factors like relative distance, relative speed, course intersection angle, and the ship's own dimensions. Alternatively, they may calculate the estimated time of collision (TTC) based on relative distance and relative approach speed. However, AIS data only provides information on ships with AIS capabilities and cannot reflect the actual situation of ships without AIS capabilities or other obstacles at sea (such as reefs). Therefore, the accuracy of the collision probability and collision time estimates calculated from AIS and radar data is insufficient to provide a basis for the system to automatically control the ship to change course for emergency avoidance. This results in current ship control systems typically only issuing audible and visual alarms when the collision probability or collision time estimate exceeds a threshold, leaving subsequent avoidance actions entirely dependent on the pilot's reaction. Especially in extreme situations of pilot negligence, there is a lack of effective technical means to ensure ship safety. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art in which the collision prediction accuracy of transportation devices is not high and the need to rely on the driver's reaction for emergency avoidance, and to provide an emergency avoidance method and transportation device for transportation devices.

[0005] The present invention solves the above-mentioned technical problems through the following technical solution:

[0006] An emergency avoidance method for a transport device includes the following steps:

[0007] Data collection stage: Images of the transport device's movement direction are captured by a camera mounted on the front of the transport device, and the size, motion state, and relative distance of obstacles are identified from the images. The motion state of the obstacles includes at least speed and direction.

[0008] Evaluation and calculation phase: Based on the size, motion state, relative distance of the obstacle and radar data of the transport device, the collision probability and estimated collision time between the transport device and the obstacle are calculated;

[0009] Response mechanism: If the collision probability is greater than the first probability threshold and the expected collision time is less than the first time threshold, then the transport device is controlled to change its direction of movement and / or speed of movement; otherwise, a warning signal is issued.

[0010] This emergency avoidance method for a transport device acquires data in the data collection phase by using images captured by a camera mounted on the front of the transport device to obtain the size, motion status, and relative distance of obstacles in the direction of the transport device's movement. This allows for the calculation of the collision probability and estimated collision time between the transport device and obstacles during the evaluation phase. The obtained collision probability and estimated collision time also cover transport devices without AIS transmission / reception capabilities and the actual situation of other obstacles, making the obtained collision probability and estimated collision time more accurate. The accuracy of this data is sufficient to serve as the basis for the system to automatically control the transport device to change its direction and speed for emergency avoidance during the response phase. This reduces reliance on the driver's reaction time in more dangerous situations, preventing collisions and other dangerous situations caused by driver negligence. In this embodiment, the transport device is a ship; in other embodiments, the transport device can also be a car, train, or aircraft, or other land or air transport vehicles.

[0011] Preferably, in the data collection stage, the size, motion status, and relative distance of the obstacle with AIS transmission capability are obtained through the AIS transponder of the transport device, and the size, motion status, and relative distance of other obstacles are identified from the image.

[0012] The data obtained by AIS is more accurate, but not comprehensive. Obtaining the size, motion status, and relative distance of the obstacle with AIS transmission capability from the AIS transponder makes the overall data on the size, motion status, and relative distance of the obstacle obtained by the transport device more accurate, which can further improve the accuracy of the obtained collision probability and the predicted collision time.

[0013] Preferably, in the response phase, when controlling the transport device to change its direction of movement and / or speed, if the expected collision time is less than a first time threshold and greater than or equal to a second time threshold, the direction of movement and speed of the transport device are adjusted to transfer the collision site to the high structural strength area of ​​the transport device; if the expected collision time is less than the second time threshold, the main unit of the transport device is controlled to operate at maximum reversing power.

[0014] By controlling the transport device to perform different emergency avoidance maneuvers based on the different collision times obtained, the success rate of avoidance can be improved.

[0015] Preferably, the first time threshold is 58-62 seconds, and the second time threshold is 29-31 seconds;

[0016] And / or, the first time threshold is twice the second time threshold;

[0017] And / or, the first probability threshold is 45%~65%.

[0018] Preferably, in the data collection stage, the mass of the obstacle is identified from the image based on an artificial intelligence algorithm;

[0019] In the evaluation and calculation process, the collision intensity between the transport device and the obstacle is also calculated based on the obstacle's mass, motion state, relative distance, and radar data of the transport device.

[0020] In the response phase, if the collision probability is greater than a first probability threshold, the expected collision time is less than a first time threshold, and the collision intensity is greater than a first intensity threshold, then the transport device is controlled to change its direction of movement and / or its speed of movement.

[0021] By calculating the collision intensity, we can more accurately judge the expected collision situation, and provide a more accurate basis for the system to automatically control the transportation device to change its direction and speed for emergency avoidance during the response phase.

[0022] Preferably, in the evaluation calculation step, the collision intensity is also calculated based on the status data of the transport device, wherein the status data of the transport device includes at least one or more of the following: the transport device's moving speed, moving direction, rudder angle, load capacity, draft, roll angle, and pitch angle.

[0023] By incorporating the status data of this transport device when assessing and calculating the collision intensity, the calculated collision intensity data can be made more accurate, which is more conducive to the system making correct judgments based on the collision intensity.

[0024] Preferably, in the data collection stage, at least one of the obstacle's size, motion state, and relative distance is identified from the image using an artificial intelligence algorithm;

[0025] And / or, in the response phase, issuing the warning signal includes at least one or more of the following: issuing an audible and visual warning to the driver, highlighting obstacles and / or collision points on an electronic chart.

[0026] Artificial intelligence algorithms identify the size, motion state, and relative distance of obstacles, which can further improve the accuracy of data acquisition compared to traditional image comparison and other recognition methods.

[0027] The effectiveness of warnings can be improved by issuing audible and visual warnings to the pilot, or by highlighting obstacles and / or collision points on electronic charts.

[0028] The present invention also provides a transportation device that employs the emergency avoidance method for transportation devices as described above. The transportation device includes a camera, which is disposed at the head of the transportation device and is electrically connected to the control system of the transportation device.

[0029] Preferably, the transport device further includes a steering device, which is electrically connected to the control system of the transport device. The steering device is located at the head of the transport device and is configured to generate thrust, the direction of which is preset to be perpendicular to the longitudinal section of the transport device.

[0030] The steering device is located below or above the waterline of the transport device in the height direction.

[0031] Preferably, the lens of the camera is oriented in the same direction as the movement of the transport device;

[0032] Alternatively, the number of cameras may be multiple, wherein the lens of at least one camera is oriented in the same direction as the movement of the transport device;

[0033] Alternatively, the number of cameras may be multiple, and at least some of the cameras may have lenses that are oriented at an angle to the direction of movement of the transport device, wherein the angle is at least less than or equal to 30°.

[0034] Alternatively, the transport device may be a ship.

[0035] The positive and progressive effects of this invention are as follows: In the data collection stage, the emergency avoidance method for this transport device uses images captured by a camera mounted at the head of the transport device to obtain the size, movement status, and relative distance of obstacles in the direction of the transport device's movement. This allows for the calculation of the collision probability and estimated collision time between the transport device and obstacles based on this data during the evaluation and calculation stage. Furthermore, the obtained collision probability and estimated collision time also cover transport devices without AIS transmission and reception capabilities, as well as the actual situation of other obstacles, making the obtained collision probability and estimated collision time more accurate. The accuracy of this data is sufficient to serve as the basis for the system to automatically control the transport device to change its direction and speed for emergency avoidance during the response stage. This reduces reliance on the driver's reaction time in more dangerous situations, preventing dangerous situations such as collisions caused by driver negligence. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating an emergency avoidance method for a transportation device according to an embodiment of the present invention. Detailed Implementation

[0037] The present invention will be further illustrated by way of embodiments below, but the present invention is not limited to the scope of the embodiments described herein.

[0038] like Figure 1 As shown, this invention provides an emergency avoidance method for transportation devices, specifically an emergency avoidance method for ships, which includes the following steps: Data collection step: an image of the ship's course is captured by a camera installed at the bow of the ship, and the size, motion state, and relative distance of the obstacle are identified from the image. The motion state of the obstacle includes speed and direction; Evaluation and calculation step: the collision probability and expected collision time between the ship and the obstacle are calculated based on the size, motion state, relative distance of the obstacle, and ship radar data; Response step: if the collision probability is greater than a first probability threshold (50%) and the expected collision time is less than a first time threshold (60s), the ship is controlled to change its course and speed; otherwise, a warning signal is issued.

[0039] In this embodiment, the ship emergency avoidance method acquires the size, motion status, and relative distance of obstacles in the ship's navigation direction by capturing images from a camera mounted on the bow of the ship during the data collection phase. This enables the calculation of the collision probability and estimated collision time between the ship and the obstacle during the evaluation phase. The obtained collision probability and estimated collision time also cover ships without AIS transmission and reception capabilities, as well as the actual situation of other obstacles at sea, making the obtained collision probability and estimated collision time more accurate. The accuracy of the data is sufficient to serve as the basis for the system to automatically control the ship to change course and speed for emergency avoidance during the response phase. This reduces the reliance on the pilot's reaction speed in more dangerous situations and avoids dangerous situations such as ship collisions caused by pilot negligence.

[0040] In this embodiment, during the data collection phase, the size, motion status, and relative distance of obstacles with AIS transmission capabilities are obtained through the ship's AIS transponder. Specifically, the unique identifier, ship type, main dimensions (such as overall length, beam, and depth), displacement, draft, speed, heading, and destination of surrounding ships are obtained through the AIS system. The size, motion status, and relative distance of other obstacles are also obtained from the images. In this embodiment, the precise location, size, outline features, and motion status of obstacles without AIS signals, such as small fishing boats, floating objects, islands, and docks, are obtained through detectors such as high-definition cameras.

[0041] In this embodiment, the data obtained by AIS is more accurate but not comprehensive. The size, motion status and relative distance of obstacles with AIS transmission capability are obtained from the AIS transponder, making the overall data on the size, motion status and relative distance of obstacles obtained by the ship more accurate, which can further improve the accuracy of the obtained collision probability and the predicted collision time.

[0042] In this embodiment, during the response phase, when controlling the ship to change its course and speed, if the expected collision time is less than a first time threshold and greater than or equal to a second time threshold, the ship's course and speed are adjusted to transfer the collision site to a high structural strength area of ​​the ship; if the expected collision time is less than the second time threshold, the ship's main engine is controlled to operate at maximum reversing power.

[0043] In this embodiment, controlling the ship to perform different emergency avoidance maneuvers based on different obtained collision times can improve the success rate of avoidance.

[0044] In this embodiment, the first time threshold is 60 seconds, the second time threshold is 30 seconds, the first time threshold is twice the second time threshold, and the first probability threshold is 50%. In other embodiments, the first time threshold and the second time threshold can be taken in the range of 58~62 seconds and 29~31 seconds, respectively, and the first probability threshold can be taken in the range of 45%~65%.

[0045] In this embodiment, during the data collection phase, the mass of obstacles can be identified from images using artificial intelligence algorithms; during the evaluation and calculation phase, the collision intensity between the ship and the obstacle is calculated based on the obstacle's mass, motion state, relative distance, and ship radar data.

[0046] In the response phase, if the collision probability is greater than a first probability threshold, the expected collision time is less than a first time threshold, and the collision intensity is greater than a first intensity threshold, then the vessel's course and speed will be changed. Specifically, in this embodiment, the collision intensity can be divided into four levels, where the first intensity is defined as minor intensity, with a threshold of no structural damage and only surface paint scratches; the second intensity is defined as moderate intensity, with a threshold of local structural deformation and no water ingress; the third intensity is severe intensity, with a threshold of hull damage and water ingress into one or more compartments; and the fourth intensity is catastrophic intensity, with a threshold of risk of hull breakage, capsizing, or sinking.

[0047] In this embodiment, by calculating the collision intensity, the expected collision situation can be judged more accurately, providing a more accurate basis for the system to automatically control the ship to change course and speed for emergency avoidance during the response phase.

[0048] In this embodiment, during the evaluation and calculation phase, the collision intensity is also calculated based on the ship's own condition data. This data includes one or more of the ship's speed, heading, rudder angle, deadweight tonnage, draft, roll angle, and pitch angle. In this embodiment, artificial intelligence algorithms are used to identify images and derive the specific structure of obstacles from them to participate in the collision intensity calculation. Based on the ship's structural strength database and the other vessel's parameters, combined with a pre-trained collision result simulation database, the collision impact force, energy absorption, hull deformation degree, and damage range are calculated and predicted.

[0049] In this embodiment, by incorporating the vessel's own state data when assessing and calculating the collision intensity, the calculated collision intensity data becomes more accurate, making it easier for the system to make correct judgments based on the collision intensity. Specifically, in this embodiment, the collision intensity can be pre-assessed using the kinetic energy parameter calculation formula, while simultaneously calculating the instantaneous kinetic energy of both the vessel and the other vessel in real time. The instantaneous kinetic energy is 0.5 × displacement × speed × speed. Furthermore, the relative collision kinetic energy can be derived from calculating the instantaneous kinetic energy of both the vessel and the other vessel to assess and calculate the collision intensity.

[0050] In this embodiment, during the data collection phase, at least one of the following is obtained from the image: the size, motion state, and relative distance of the obstacle, based on an artificial intelligence algorithm.

[0051] In this embodiment, the early warning signal issuance during the response phase includes issuing an audible and visual warning to the driver, highlighting obstacles and collision points on the electronic nautical chart.

[0052] In this embodiment, the size, movement state, and relative distance of obstacles are identified using artificial intelligence algorithms, which can further improve the accuracy of data acquisition compared to traditional image comparison and other identification methods. The warning effect can be enhanced by issuing audible and visual warnings to the driver, or by highlighting obstacles and collision points on electronic charts.

[0053] The present invention also provides a transportation device, specifically a ship, which employs the emergency avoidance method for transportation devices as described above. The ship includes a camera, which is located at the bow of the ship and electrically connected to the ship's control system.

[0054] In this embodiment, the vessel also includes a steering device electrically connected to the vessel's control system. The steering device is located at the bow of the vessel and configured to generate thrust, the direction of which is preset to be perpendicular to the longitudinal section of the vessel's hull. The steering device is located both below and above the waterline in the vertical direction. Specifically, in this embodiment, both an below-waterline steering device and an above-waterline steering device are provided. The below-waterline steering device is a hydraulic propulsion device, such as a commonly used ship's bow thruster, while the above-waterline steering device is a gas propulsion device. In other embodiments, only the below-waterline steering device or the above-waterline steering device may be selected. Users can reasonably select and combine different types of steering devices according to actual usage needs. This part belongs to the prior art in this field and will not be elaborated further here.

[0055] In this embodiment, the camera lens is oriented in the same direction as the ship's navigation; there are multiple cameras, with their lenses oriented in the same direction as the ship's navigation. The lenses of these multiple cameras are at an angle of 30° to the ship's navigation. In other embodiments, the angle between the camera lens and the ship's navigation can be less than 30°.

[0056] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.

Claims

1. An emergency avoidance method for a transportation device, characterized in that, It includes the following steps: Data collection stage: Images of the transport device's movement direction are captured by a camera mounted on the front of the transport device, and the size, motion state, and relative distance of obstacles are identified from the images. The motion state of the obstacles includes at least speed and direction. Evaluation and calculation phase: Based on the size, motion state, relative distance of the obstacle and radar data of the transport device, the collision probability and estimated collision time between the transport device and the obstacle are calculated; Response mechanism: If the collision probability is greater than the first probability threshold and the expected collision time is less than the first time threshold, then the transport device is controlled to change its direction of movement and / or speed of movement; otherwise, a warning signal is issued.

2. The emergency avoidance method for a transport device as described in claim 1, characterized in that, In the data collection phase, the size, motion status, and relative distance of the obstacles with AIS transmission capability are obtained through the AIS transponder of the transport device, and the size, motion status, and relative distance of other obstacles are identified from the image.

3. The emergency avoidance method for a transport device as described in claim 1, characterized in that, In the response phase, when controlling the transport device to change its direction of movement and / or speed, if the expected collision time is less than a first time threshold and greater than or equal to a second time threshold, the direction of movement and speed of the transport device are adjusted to transfer the collision site to the high structural strength area of ​​the transport device; if the expected collision time is less than the second time threshold, the main unit of the transport device is controlled to operate at maximum reversing power.

4. The emergency avoidance method for a transport device as described in claim 3, characterized in that, The first time threshold is 58-62 seconds, and the second time threshold is 29-31 seconds; And / or, the first time threshold is twice the second time threshold; And / or, the first probability threshold is 45%~65%.

5. The emergency avoidance method for a transport device as described in claim 1, characterized in that, In the data collection phase, the mass of obstacles is identified from the image using an artificial intelligence algorithm; In the evaluation and calculation process, the collision intensity between the transport device and the obstacle is also calculated based on the obstacle's mass, motion state, relative distance, and radar data of the transport device. In the response phase, if the collision probability is greater than a first probability threshold, the expected collision time is less than a first time threshold, and the collision intensity is greater than a first intensity threshold, then the transport device is controlled to change its direction of movement and / or its speed of movement.

6. The emergency avoidance method for a transport device as described in claim 5, characterized in that, In the assessment and calculation phase, the collision intensity is also calculated based on the status data of the transport device. The status data of the transport device includes at least one or more of the following: the transport device's speed, direction of movement, rudder angle, load capacity, draft, roll angle, and pitch angle.

7. The emergency avoidance method for a transport device as described in any one of claims 1-6, characterized in that, In the data collection phase, at least one of the obstacle's size, motion state, and relative distance is identified from the image using an artificial intelligence algorithm; And / or, in the response phase, issuing the warning signal includes at least one or more of the following: issuing an audible and visual warning to the driver, highlighting obstacles and / or collision points on an electronic chart.

8. A transport device, characterized in that, It employs the emergency avoidance method for a transport device as described in any one of claims 1-7, wherein the transport device includes a camera, the camera is disposed at the head of the transport device, and the camera is electrically connected to the control system of the transport device.

9. The transport device as claimed in claim 8, characterized in that, The transport device also includes a steering device, which is electrically connected to the control system of the transport device. The steering device is located at the head of the transport device and is configured to generate thrust, the direction of which is preset to be perpendicular to the longitudinal section of the transport device. The steering device is located below or above the waterline of the transport device in the height direction.

10. The transport device as claimed in claim 8, characterized in that, The camera lens is oriented in the same direction as the movement of the transport device; Alternatively, the number of cameras may be multiple, wherein the lens of at least one camera is oriented in the same direction as the movement of the transport device; Alternatively, the number of cameras may be multiple, and at least some of the cameras may have lenses that are oriented at an angle to the direction of movement of the transport device, the angle being at least less than or equal to 30°. Alternatively, the transport device may be a ship.

Images