Method, computer program with instructions and device for determining a packing pattern for loading a transport container, as well as loading device
The method and device use a light pattern to measure and evaluate container interiors for optimal packing, addressing inefficiencies and robot damage in automated loading by determining precise packing patterns for diverse cargo.
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Applications
- Current Assignee / Owner
- CONTINENTAL REIFEN DEUTSCHLAND GMBH
- Filing Date
- 2024-11-01
- Publication Date
- 2026-05-07
AI Technical Summary
Existing automated loading systems for transport containers face challenges with differently sized loading areas, obstacles like varying planking and tailgates, and are limited to single tire types, leading to inefficient packing and potential damage to loading robots.
A method and device that uses a light pattern to optically measure the interior of a transport container, capture and evaluate dimensions and obstacles, and determine an optimal packing pattern for cargo based on these measurements.
Enhances loading efficiency by allowing more cargo to be loaded, reduces the risk of process aborts, and minimizes robot damage by accounting for unknown dimensions and obstacles, particularly beneficial for large containers and diverse cargo loads.
Smart Images

Figure 00000000_0000_ABST
Abstract
Description
[0001] The present invention relates to a method, a computer program with instructions, and a device for determining a packing pattern for loading a transport container with cargo. The invention further relates to a loading device for loading a transport container with cargo, which utilizes a device according to the invention.
[0002] When transporting general cargo, such as tires, a recurring problem is arranging the cargo as optimally as possible within a transport container. These containers are usually loaded manually, meaning the operator determines the final position of the cargo on the loading platform.
[0003] The automation of the loading process suffers from the problem of differently sized or available loading areas. In some cases, loading areas are only slightly larger or smaller. Furthermore, there are differences in the loading area's planking, i.e., the horizontal planks or braces between the vertical support beams. At the rear of a truck, there is often a tailgate of varying length, either a piece of tarpaulin or a rigid element that limits the top of the loading hatch. When automating loading with a robot, this can restrict the robot's range of motion. Braces on the loading area's ceiling can also be problematic, as the truck should be optimally utilized, but these braces can make it lower than intended. This can lead to a robot gripper getting caught and damaged.
[0004] A herringbone packing pattern has become established for loading tires. Sometimes this fits well into the available space on the trailer, but sometimes it doesn't. Furthermore, the tires in the lower layer of this loading pattern are inclined to one side. If the outermost tire, on which the other tires partially rest, is not leaning against a horizontal support but against the tarpaulin, this causes the tarpaulin to bulge. As a result, the truck becomes unroadworthy.
[0005] Another challenge is that there is only one packing pattern per tire type. Therefore, existing automation approaches are only suitable for loads containing tires of a single type. As soon as, for example, a load with different tires needs to be shipped to a distribution center, the batch sizes of the individual items sometimes decrease to just a few pieces. This results in a highly diversified load, for which there is no packing pattern solution.
[0006] Against this background, the article by AV Puche et al.: “Online 3D Bin Packing Reinforcement Learning Solution with Buffer”, arXiv:2208.07123v1, describes a reinforcement learning framework for a solution to the 3D bin packing problem.
[0007] It is an object of the present invention to provide improved solutions for loading a transport container.
[0008] This problem is solved by a method having the features of claim 1, by a computer program with instructions according to claim 8, by a device having the features of claim 9, and by a charging device according to claim 10. Preferred embodiments of the invention are the subject of the dependent claims.
[0009] According to a first aspect of the invention, a method for determining a packing pattern for loading a transport container with cargo comprises the steps: - Illuminating the interior of the transport container with a light pattern; - Capturing the resulting light pattern with a recording device; - Determining the dimensions of the interior and of obstacles within the interior by evaluating the captured light pattern; and - Determining a packing pattern for the cargo based on the determined dimensions and obstacles.
[0010] According to another aspect of the invention, a computer program comprises instructions which, when executed by a computer, cause the computer to perform the following steps to determine a packing pattern for loading a transport container with cargo: - Illuminating the interior of the transport container with a light pattern; - Capturing the resulting light pattern with a recording device; - Determining the dimensions of the interior and of obstacles within the interior by evaluating the captured light pattern; and - Determining a packing pattern for the cargo based on the determined dimensions and obstacles.
[0011] The term "computer" is to be understood broadly. In particular, it also includes embedded or distributed systems and other processor-based data processing devices. Furthermore, the individual steps are not necessarily performed directly by the computer. It is equally possible that the computer controls or relies on external components to carry out individual steps.
[0012] The computer program can, for example, be made available for electronic retrieval or be stored on a computer-readable storage medium.
[0013] According to a further aspect of the invention, a device for determining a packing pattern for loading a transport container with cargo comprises a memory containing instructions and a processor, wherein the processor is configured to perform the following steps when the instructions are executed: - Illuminating the interior of the transport container with a light pattern; - Capturing the resulting light pattern with a recording device; - Determining the dimensions of the interior and of obstacles within the interior by evaluating the captured light pattern; and - Determining a packing pattern for the cargo based on the determined dimensions and obstacles.
[0014] According to another aspect of the invention, a loading device for loading a transport container with cargo comprises: - a lighting device for illuminating the interior of the transport container with a light pattern; - a recording device for capturing the resulting light pattern; and - a device according to the invention for determining a packing pattern for loading the transport container with the cargo.
[0015] In the solution according to the invention, the interior of the transport container to be loaded is first optically measured. For this purpose, a light pattern with known properties is projected into the interior using a lighting device, e.g., a projector. The resulting light pattern is captured by a recording device, e.g., a camera. The captured light pattern is evaluated to determine the dimensions of the interior and the position and dimensions of any obstacles. Based on this information, an optimal packing pattern can then be calculated. This has the advantage over existing solutions that more cargo can be loaded into a given transport container. In addition, the probability of a loading process having to be aborted or reversed due to faulty packing is reduced. Because the position of obstacles is now known, the risk of damage is reduced.
[0016] According to one aspect of the invention, a loading device for loading the transport container with the cargo is controlled based on a specific packing pattern. The packing pattern determined according to the invention can be used immediately to control the loading process by a loading device. Alternatively, it is also possible to determine the packing pattern independently of a pending loading process and to use it at a later time. This requires that the cargo to be loaded at this later time, or its dimensions, are already known.
[0017] According to one aspect of the invention, the light pattern is a striped pattern. Such a striped pattern can be easily projected using a striped light projector. Alternatively, the stripes can be replaced by a random but unambiguous pattern.
[0018] According to one aspect of the invention, the dimensions are determined from the spacing of the stripes in the stripe pattern and from creases in the stripes. The distance between the stripes can be used, for example, to determine the distance to a tarpaulin or the distance to obstacles inside the transport container. Furthermore, creases or angles form at the edges of the transport container in the stripe projection, which are visible in the image. The width of the transport container can then be calculated from this.
[0019] According to one aspect of the invention, the dimensions of the interior and any obstacles within it are determined by successively evaluating the captured light pattern during a loading process for different areas of the transport container's interior. This approach is particularly advantageous for large transport containers. As a mobile loading device gradually loads the transport container, it successively moves out of the container and continuously measures the available space. As soon as a new batch of cargo is to be loaded, an optimal packing pattern can be calculated based on the available space and the next batch of cargo to be loaded, and the cargo can then be loaded accordingly by the loading device.
[0020] According to one aspect of the invention, the transport container is a truck, a trailer, or a container. The solution according to the invention is particularly advantageous for large transport containers that can be accessed by a mobile loading device and where the exact dimensions and any obstacles are not known in advance.
[0021] According to one aspect of the invention, the cargo consists of tires for a means of transportation. Automated loading devices are already used today for loading vehicle tires, and their functionality can be further optimized by the solution according to the invention.
[0022] Further features of the present invention will become apparent from the following description and the attached claims in conjunction with the figures. Figure overview Fig. Figure 1 schematically shows a method for determining a packing pattern for loading a transport container with cargo; Fig. Figure 2 shows an embodiment of a device for determining a packing pattern for loading a transport container with cargo; Fig. Figure 3 shows, by way of example, the use of a light pattern for measuring a transport container; and Fig. Figure 4 schematically shows a charging device in which a solution according to the invention is implemented. Character description
[0023] To better understand the principles of the present invention, embodiments of the invention are explained in more detail below with reference to the figures. The same reference numerals are used in the figures for identical or equivalently acting elements and are not necessarily described again for each figure. It is understood that the invention is not limited to the embodiments shown and that the described features can also be combined or modified without departing from the scope of protection of the invention as defined in the appended claims.
[0024] Fig. Figure 1 schematically shows a method for determining a packing pattern for loading a transport container with cargo. The transport container could be, for example, a truck, a trailer, or a container. The cargo could be, for example, a tire for a vehicle. In a first step, the interior of the transport container is illuminated with a light pattern S1. Preferably, the light pattern is a striped pattern. The resulting light pattern is captured by a recording device S2. By evaluating the captured light pattern, the dimensions of the interior and any obstacles within it are determined S3. For this purpose, for example, the distances between stripes of the striped pattern and kinks in the stripes can be evaluated.Preferably, the determination S3 of the interior dimensions and obstacles within the interior is carried out by evaluating the captured light pattern successively for different areas of the interior of the transport container during a loading process. Based on the determined dimensions and obstacles, a packing pattern for the cargo is determined S4. Based on the determined packing pattern, a loading device for loading the transport container with the cargo can be controlled S5.
[0025] Fig. Figure 2 shows a simplified schematic representation of an embodiment of a device 10 for determining a packing pattern PM for loading a transport container with cargo. The device 10 has a memory 11 and a processor 12. For example, the device 10 is a computer or a workstation. Instructions are stored in the memory 11 which, when executed by the processor 12, cause the device 10 to perform the steps according to one of the described methods. The instructions stored in the memory 11 thus embody a program executable by the processor 12, which implements the method according to the invention. The device 10 has an input 13 for receiving information. Data generated by the processor 12, e.g., a specific packing pattern PM, is provided via an output 14. Furthermore, it can be stored in the memory 11.Input 13 and output 14 can be combined into a bidirectional interface.
[0026] The processor 12 can comprise one or more processor units, such as microprocessors, digital signal processors, or combinations thereof.
[0027] Memory 11 can contain both volatile and non-volatile memory areas and can include a wide variety of storage devices and media, such as hard disks, optical storage media, or semiconductor memory.
[0028] Fig. Figure 3 shows an example of the use of a light pattern LM for measuring the interior space 41 of a transport container 40. The transport container 40 is a loading platform of a truck. The light pattern LM is a striped pattern that can be detected by a recording device and evaluated by a specially designed device. For example, the distance D between the stripes S of the striped pattern can be used to determine the distance to a tarpaulin P or the distance to obstacles H inside the transport container 40. It is also clearly visible that kinks K or angles form in the striped projection at the edges E of the transport container 40. The width of the transport container 40 can be determined from these angles.
[0029] Fig.Figure 4 schematically shows a loading device 30 in which a solution according to the invention is implemented. In the illustrated example, the loading device 30 is a mobile robot 300 with a robot arm 301. The mobile robot 300 is configured to enter the cargo space of a truck, trailer, or container and load cargo LG, in the illustrated example tires, from a flexible conveyor belt. The loading device 30 has a lighting device 31 for illuminating the interior of the transport container with a light pattern LM. For example, the lighting device 31 could be a strip light projector. The loading device 30 also has a receiving device 32 for capturing the resulting light pattern, for example, a camera.Using a device 10 integrated into the robot 300 or connected to it via a data link, a packing pattern for loading the transport container with the cargo LG is determined based on the acquired data and information about the cargo LG. The cargo LG is then loaded by the robot arm 301 according to the packing pattern. Since the robot 300 loads the transport container step by step and successively moves out of it, the available space can be continuously measured. As soon as a new row of cargo LG is to be loaded, an optimal packing pattern can be calculated based on the available space and the next cargo LG to be loaded, and the cargo LG can be loaded accordingly by the loading device 30. Reference symbol list 10 Device 11 storage 12 processor 13 Entrance 14 Exit 30 Charging device 300 Mobile Robots 301 robot arm 31 Lighting device 32 Recording device 40 transport containers 41 Interior Dimensions D distance E edge H obstacle K bend LG cargo LM light pattern P Plane PM Packing Pattern S stripes S1 Illuminating the interior with a light pattern S2 Capturing the light pattern S3 Determining dimensions and obstacles S4 Determining a packing pattern S5 Controlling a charging device QUOTES INCLUDED IN THE DESCRIPTION
[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited non-patent literature
[0000] AV Puche et al.: “Online 3D Bin Packing Reinforcement Learning Solution with Buffer”, arXiv:2208.07123v1, a Reinforcement Learning Framework for a Solution of the 3D Bin Packing Problem
[0006]
Claims
[1] Method for determining a packing pattern (PM) for loading a transport container (40) with a load (LG), comprising the steps: - Illuminating (S1) an interior (41) of the transport container (40) with a light pattern (LM); - Capturing (S2) the resulting light pattern (LM) with a recording device (32); - Determining (S3) the dimensions (A) of the interior (41) and of obstacles (H) in the interior (41) by evaluating the detected light pattern (LM); and - Determining (S4) a packing pattern (PM) for the cargo (LG) based on the determined dimensions (A) and the determined obstacles (H). [2] Method according to claim 1, wherein a loading device (30) for loading the transport container (40) with the cargo (LG) is controlled on the basis of the specified packing pattern (PM) (S5). [3] Method according to claim 1 or 2, wherein the light pattern (LM) is a stripe pattern. [4] Method according to claim 3, wherein the dimensions (A) are determined from the distances (D) of strips (S) of the strip pattern as well as creases (K) in the strips (S) (S3). [5] Method according to one of the preceding claims, wherein the determination (S3) of dimensions (A) of the interior (41) and of obstacles (H) in the interior (41) is carried out successively for areas of the interior (41) of the transport container (40) by evaluating the detected light pattern (LM) during a loading process. [6] Method according to any of the preceding claims, wherein the transport container (40) is a truck, a trailer or a container. [7] Method according to one of the preceding claims, wherein the load (LG) is tires for a means of transport. [8] Computer program with instructions which, when executed by a computer, cause the computer to perform the steps of a method according to one of the preceding claims for determining a packing pattern (PM) for loading a transport container (40) with a cargo (LG). [9] Device (10) for determining a packing pattern (PM) for loading a transport container (40) with a load (LG), comprising a memory (11) in which instructions are stored, and a processor (12), wherein the processor (12) is configured to execute the steps of a method according to any one of claims 1 to 8 for determining a packing pattern (PM) when the instructions are executed. [10] Loading device (30) for loading a transport container (40) with a load (LG), comprising: - a lighting device (31) for illuminating (S1) an interior (41) of the transport container (40) with a light pattern (LM); - a recording device (32) for capturing (S2) the resulting light pattern (LM); and - a device (10) according to claim 9 for determining a packing pattern (PM) for loading the transport container (40) with the cargo (LG).