Cargo handling method, system, electronic device, and storage medium

Abstract

Embodiments of the present application disclose a cargo loading and unloading method and system, an electronic device and a storage medium, which are applied to a cargo loading and unloading system. The system comprises an unmanned forklift and a sensor module. The method comprises the following steps: determining a plurality of corresponding zero-position poses of carriers placed on a truck, wherein the carriers are used for loading cargo, and the zero-position pose is a pose of each carrier relative to a reference sensor in the sensor module; obtaining an offset of an actual pose of each carrier relative to the corresponding zero-position pose; determining an actual path of the unmanned forklift for picking up the plurality of carriers according to the offset; and controlling the unmanned forklift to complete loading and unloading of the cargo based on the actual path of picking up the plurality of carriers. The embodiments of the present application can improve the efficiency of loading and unloading the cargo.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automation, and in particular to a cargo loading and unloading method and system, an electronic device, and a storage medium. BACKGROUND

[0002] In industrial logistics, cargo loading and unloading is an important link. The existing cargo loading and unloading method is usually to load or unload cargo by manual forklifts, but this method consumes a large amount of labor, and each time the cargo is forked, it needs to be manually aligned for forking, resulting in low loading and unloading efficiency. Therefore, how to efficiently load and unload cargo has become a problem to be solved. SUMMARY

[0003] Embodiments of the present application disclose a cargo loading and unloading method and system, an electronic device, and a storage medium, which can improve the efficiency of cargo loading and unloading.

[0004] Embodiments of the present application disclose a cargo loading and unloading method applied to a cargo loading and unloading system, the system comprising an unmanned forklift and a sensor module; the method comprising:

[0005] determining a zero position pose of each of a plurality of carriers placed on a truck, the carriers being used to load cargo, the zero position pose being a pose of each of the carriers relative to a reference sensor in the sensor module;

[0006] obtaining an offset of an actual pose of each of the carriers relative to the corresponding zero position pose;

[0007] determining an actual path of the unmanned forklift for forking the plurality of carriers according to the offset;

[0008] controlling the unmanned forklift to complete the loading and unloading of the cargo based on the actual path of forking the plurality of carriers.

[0009] In one embodiment, the sensor module is located on both sides of a truck unloading area of the truck, and a detection area corresponding to the sensor module covers the unloading area. The determination of the zero position pose of each of the plurality of carriers placed on the truck comprises:

[0010] identifying a plurality of carriers placed on the truck from the truck parked in the unloading area by a target recognition algorithm;

[0011] calculating a global pose of each of the carriers relative to the reference sensor according to detection data of each sensor in the sensor module for each of the carriers, the global pose of each of the carriers relative to the reference sensor being the zero position pose of each of the carriers.

[0012] In one embodiment, after determining the zero-position poses of the plurality of vehicles placed on the truck, the method further includes:

[0013] Determine the transformed pose of the unmanned forklift relative to each of the carriers when the unmanned forklift is aligned with the center of each of the carriers for forklift insertion;

[0014] Based on the transformed pose of the unmanned forklift relative to the zero-position pose of each of the vehicles, a preset path is generated for the unmanned forklift to pick up the multiple vehicles.

[0015] Determining the actual path for the unmanned forklift to pick up the multiple vehicles based on the offset includes:

[0016] Based on the offset, the preset path for the unmanned forklift to pick up the multiple vehicles is adjusted to obtain the actual path for the unmanned forklift to pick up the multiple vehicles.

[0017] In one embodiment, determining the transformed pose of the unmanned forklift relative to each of the respective carriers when the forklift is aligned with the center of each carrier for fork insertion includes:

[0018] A reference vehicle is determined from the plurality of vehicles;

[0019] Based on the zero position pose of the reference vehicle and the pose of the unmanned forklift on the map when it is aligned with the center of the reference vehicle for forklift insertion, the transformed pose of the unmanned forklift relative to the zero position pose of the reference vehicle is determined.

[0020] Based on the transformed pose of the unmanned forklift relative to the reference vehicle, the fixed distance between the multiple vehicles, and the size of each vehicle, the transformed pose of the unmanned forklift relative to the zero pose of each vehicle is determined.

[0021] In one embodiment, before adjusting the preset path for the unmanned forklift to pick up the plurality of vehicles based on the offset to obtain the actual path for the unmanned forklift to pick up the plurality of vehicles, the method further includes:

[0022] Each of the multiple vehicles is associated with a different storage location identifier; wherein, the storage location identifier is used to indicate the storage location corresponding to the vehicle in the unloading area;

[0023] The step of adjusting the preset path for the unmanned forklift to pick up the multiple vehicles based on the offset to obtain the actual path for the unmanned forklift to pick up the multiple vehicles includes:

[0024] Based on the offset of the actual pose of each vehicle relative to the corresponding zero pose, determine the offset between the actual pose of each vehicle and the storage location indicated by the corresponding storage location identifier.

[0025] Based on the offset between the actual position of each vehicle and the storage location indicated by the corresponding storage location identifier, the preset path for the unmanned forklift to pick up the multiple vehicles is adjusted to obtain the actual path for the unmanned forklift to pick up the multiple vehicles.

[0026] In one embodiment, after determining the zero-position poses of the plurality of vehicles placed on the truck, the method further includes:

[0027] The zero-position poses corresponding to the multiple vehicles are checked, and the check results corresponding to each zero-position pose are obtained.

[0028] Based on the test results corresponding to each zero-position pose, it is determined that the zero-position pose calibration was successful.

[0029] In one embodiment, before identifying multiple vehicles placed on the trucks from the trucks parked in the unloading area using a target recognition algorithm, the method further includes:

[0030] With the truck parked in the unloading area, the vehicles in the truck are forked out at fixed intervals and placed on both sides of the truck bed.

[0031] This application discloses a cargo loading and unloading system, which includes an unmanned forklift and a sensor module. The system includes:

[0032] The sensor module is used to determine the zero-position pose of multiple vehicles placed on the truck, the vehicles being used to load cargo, and the zero-position pose being the pose of each vehicle relative to a reference sensor in the sensor module.

[0033] The sensor module is used to acquire the offset of the actual pose of each vehicle relative to the corresponding zero pose.

[0034] The unmanned forklift is used to determine the actual path for the unmanned forklift to pick up the multiple vehicles based on the offset.

[0035] The unmanned forklift is used to control the unmanned forklift to complete the loading and unloading of the goods based on the actual path of picking up the multiple carriers.

[0036] This application discloses an electronic device, including:

[0037] Memory containing executable program code;

[0038] A processor coupled to the memory;

[0039] The processor calls the executable program code stored in the memory to execute the method described in any of the above embodiments.

[0040] This application discloses a computer-readable storage medium storing a computer program, wherein when executed by a processor, the computer program causes the processor to perform the methods described in any of the above embodiments.

[0041] The cargo loading and unloading method, system, electronic device, and storage medium disclosed in this application include an unmanned forklift and a sensor module. The system determines the zero-position pose of each carrier placed on a truck for loading cargo, wherein the zero-position pose is based on the pose of each carrier relative to a reference sensor in the sensor module. It acquires the offset of the actual pose of each carrier relative to its corresponding zero-position pose and determines the actual path for the unmanned forklift to pick up multiple carriers based on this offset. Based on this actual path, the system controls the unmanned forklift to complete the loading and unloading of cargo. This application's embodiment, based on the offset of the actual pose of each carrier relative to its corresponding zero-position pose, can accurately determine the actual path for the unmanned forklift to pick up carriers, improving the efficiency of loading and unloading cargo. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1A This is a schematic diagram illustrating an application scenario of a cargo loading and unloading method disclosed in an embodiment of this application;

[0044] Figure 1A This is a schematic diagram of a scene of an unloading area disclosed in an embodiment of this application;

[0045] Figure 2 This is a schematic flowchart of a cargo loading and unloading method disclosed in an embodiment of this application;

[0046] Figure 3 This is a schematic flowchart of another cargo loading and unloading method disclosed in the embodiments of this application;

[0047] Figure 4 This is a schematic flowchart of another cargo loading and unloading method disclosed in the embodiments of this application;

[0048] Figure 5This is a schematic diagram of the structure of a cargo loading and unloading system disclosed in an embodiment of this application;

[0049] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0051] It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0052] This application discloses a cargo loading and unloading method, system, electronic device, and storage medium, which can improve the efficiency of cargo loading and unloading.

[0053] The following will be described in detail with reference to the accompanying drawings.

[0054] like Figure 1A As shown, Figure 1A This is a schematic diagram of an application scenario for a cargo loading and unloading method disclosed in an embodiment of this application. The application scenario may include a sensor module 10 and an unmanned forklift 20.

[0055] The sensor module 10 may include multiple sensors, such as laser sensors, radar sensors, and camera sensors. The sensor module 10 may also include combinations of the above sensors; no specific limitation is made. The sensor module 10 can be used to acquire the position and orientation information of various vehicles placed on the truck.

[0056] In one embodiment, the sensors included in the sensor module 10 may be composite sensors that combine camera sensors and three-dimensional laser sensors to monitor the unloading area through a combination of vision and laser. Specifically, the camera sensor can be fixed on the three-dimensional laser sensor using a U-shaped bracket. The installation height of the sensor module 10 may be about 1.6 meters above the ground, which is about 10 centimeters higher than the height of the truck bed.

[0057] The unmanned forklift 20 is an automated guided vehicle (AGV), which may include, but is not limited to, lurking AGVs, backpack AGVs, and counterbalance AGVs.

[0058] In one embodiment, the sensor module 10 can determine the zero-position pose of multiple vehicles placed on the truck, and obtain the offset of the actual pose of each vehicle relative to the corresponding zero-position pose.

[0059] Optionally, the application scenario may also include locally deployed electronic devices, which may include, but are not limited to, mobile phones, tablets, wearable devices, laptops, PCs (Personal Computers), etc. The sensor module 10 can send the zero-position pose of each vehicle and the actual pose of each vehicle to the locally deployed electronic device, and calculate the offset of the actual pose of each vehicle relative to the corresponding zero-position pose through the locally deployed electronic device. Furthermore, the unloading program can be run through the locally deployed electronic device to control the truck to unload the goods.

[0060] In one embodiment, sensor module 10 can send the offset directly to unmanned forklift 20;

[0061] Optionally, this application scenario may also include a central controller, which may include, but is not limited to, mobile phones, tablets, wearable devices, laptops, PCs (Personal Computers), etc.; the sensor module 10 can send the offset to the central controller, and the central controller can send the offset to the unmanned forklift 20; or, the sensor module 10 can send the offset to a locally deployed electronic device, and the locally deployed electronic device can send the offset directly to the unmanned forklift, or the locally deployed electronic device can send the offset to the central controller, and the central controller can then send the offset to the unmanned forklift, the specifics are not limited; for example, the locally deployed electronic device can send the offset to the central controller via HTTP+JSONRPC communication, and then the central controller can send the offset to the unmanned forklift.

[0062] In one embodiment, the unmanned forklift 20 can determine the actual path for the unmanned forklift 20 to pick up multiple vehicles based on the offset; based on the actual path for picking up multiple vehicles, the unmanned forklift 20 can be controlled to complete the loading and unloading of goods, so as to achieve adaptive unloading of goods.

[0063] Figure 1BThis is a schematic diagram of a loading / unloading area disclosed in an embodiment of this application. The loading / unloading area is used to park trucks, and goods can be loaded and unloaded from the trucks in the loading / unloading area. Sensor modules 10 are provided on both sides of the loading / unloading area 120; the number of sensors in the sensor modules 10 can be determined according to the size of the loading / unloading area, and is not specifically limited.

[0064] like Figure 1B As shown, in the unloading area 120, the installation position of each sensor can be calculated using the FOV of each sensor in the sensor module 10, ensuring that there is an overlap in the field of view between adjacent sensors and preventing missing fields of view. Optionally, a reference sensor can be determined from the multiple sensors in the sensor module 10. Using the reference sensor as the origin, the detection areas corresponding to each sensor can be stitched together through multi-sensor calibration to form a detection area sufficient to cover the unloading area, thereby achieving monitoring of the unloading area. Optionally, multi-sensor fusion technology can be used to stitch together the detection areas corresponding to each sensor into a point cloud map, and the pose information of each vehicle can be obtained from the point cloud map. Figure 1B As shown, the reference sensor 100 in the sensor module 10 corresponds to a field of view (FOV) 110.

[0065] In implementing this embodiment, the cargo loading and unloading system uses sensor modules strategically placed on both sides of the unloading area to scan multiple vehicles placed on the truck based on multi-sensor fusion technology. It then determines the zero-position pose of each vehicle, i.e., performs zero-position calibration on each vehicle, and obtains the offset of the actual pose of each vehicle relative to the corresponding zero-position pose. After the unmanned forklift receives this offset, it can determine the actual path to pick up multiple vehicles, thereby efficiently and accurately performing the unloading task and achieving adaptive unloading.

[0066] like Figure 2 As shown, Figure 2 This is a schematic flowchart of a cargo loading and unloading method disclosed in an embodiment of this application. This method can be applied to the cargo loading and unloading system described in the above embodiments. The cargo loading and unloading system may include unmanned forklifts and sensor modules. The cargo loading and unloading method may include the following steps:

[0067] 201. Determine the zero position pose of each of the multiple vehicles placed on the truck.

[0068] A vehicle is a tool used to load goods during logistics transportation; for example, it can be a pallet, a collapsible box, etc., with no specific limitation. When loading and unloading goods, an unmanned forklift can pick up goods from the vehicle, thus loading and unloading the vehicle and goods as a whole.

[0069] The truck can be a box truck, flatbed truck, container truck, or sidecar truck, etc., and there is no specific limitation; among them, the box truck can be a wing truck, which can open the side wings of the truck body when loading and unloading goods.

[0070] The sensor module can determine the zero-position pose of multiple vehicles placed on the truck, where the zero-position pose is the pose of each vehicle relative to the reference sensor in the sensor module.

[0071] The reference sensor can be any one of the multiple sensors included in the sensor module; for ease of calculation, the reference sensor can also be the sensor located in the lower left position among the multiple sensors included in the sensor module, such as... Figure 1B As shown, no specific limitations are specified.

[0072] Specifically, the xOy coordinate axis can be established with the reference sensor as the origin, and the x-axis coordinate value and y-axis coordinate value of each vehicle relative to the coordinate system with the reference sensor as the origin can be obtained as the pose of each vehicle relative to the reference sensor, i.e., the zero pose.

[0073] 202. Obtain the offset of the actual pose of each vehicle relative to the corresponding zero pose.

[0074] When a fully loaded truck enters the unloading area, the sensor module acquires the actual pose of each vehicle and calculates the offset of each vehicle's actual pose relative to its corresponding zero-position pose. Therefore, the position of the truck at each stop in the unloading area and the position of the goods placed on the truck each time will have deviations. Thus, if the route for the automated forklift to pick up goods is planned strictly according to the pre-set zero-position pose, the automated forklift will be unable to accurately pick up the loaded vehicles. Therefore, during the actual loading and unloading process, the sensor module acquires the actual pose of each vehicle and calculates the offset of each vehicle's actual pose relative to its corresponding zero-position pose.

[0075] 203. Based on the offset, determine the actual path for the unmanned forklift to pick up multiple vehicles.

[0076] The unmanned forklift determines the actual path for picking up multiple vehicles based on the offset.

[0077] Specifically, the sensor module can send the zero-position poses of multiple vehicles placed on the truck to the unmanned forklift. The unmanned forklift can first generate a preset path based on the zero-position poses of each vehicle. After the unmanned forklift obtains the offset of the actual pose of each vehicle relative to the corresponding zero-position pose, the unmanned forklift can adjust the preset path according to the offset to obtain the actual path for picking up multiple vehicles.

[0078] Alternatively, the unmanned forklift does not need to generate a preset path in advance. It can directly generate the actual path for the unmanned forklift to pick up multiple vehicles based on the zero position pose of each vehicle and the offset of the actual pose of each vehicle relative to the corresponding zero position pose.

[0079] In this embodiment, the unmanned forklift generates an actual path for picking up multiple vehicles by obtaining the zero offset of each vehicle, thereby improving the accuracy of the actual path planned by the unmanned forklift and increasing the efficiency of loading and unloading goods.

[0080] 204. Based on the actual path of picking up multiple carriers, control the unmanned forklift to complete the loading and unloading of goods.

[0081] The unmanned forklift is controlled to complete the loading and unloading of goods based on the actual path of picking up multiple carriers; the actual path may include the actual positions of multiple carriers; the unmanned forklift accurately goes to each carrier according to the actual path to complete the unloading of the carriers, thereby realizing the loading and unloading of goods.

[0082] In this embodiment, the cargo loading and unloading system can determine the zero-position pose of each carrier placed on a truck for loading cargo, wherein the zero-position pose is based on the pose of each carrier relative to a reference sensor in the sensor module; obtain the offset of the actual pose of each carrier relative to the corresponding zero-position pose, and determine the actual path for the unmanned forklift to pick up multiple carriers based on the offset; and control the unmanned forklift to complete the loading and unloading of cargo according to the actual path. This embodiment, based on the offset of the actual pose of each carrier relative to the corresponding zero-position pose, can accurately determine the actual path for the unmanned forklift to pick up the carriers, improving the efficiency of loading and unloading cargo.

[0083] like Figure 3 As shown, Figure 3 This is a schematic flowchart of another cargo loading and unloading method disclosed in an embodiment of this application. This cargo loading and unloading method can be applied to the cargo loading and unloading system in the above embodiments, and the cargo loading and unloading method may include the following steps:

[0084] 301. With the truck parked in the unloading area, forklifts from the truck at fixed intervals and place them on both sides of the truck bed.

[0085] When a truck is parked in the unloading area, an unmanned forklift can pick up the loads from the truck and place them on both sides of the truck bed at fixed intervals. By regularly picking up the loads and placing them on both sides of the truck bed, the efficiency of unloading the goods can be improved.

[0086] The sensor module can identify whether a truck is parked in the unloading area using a target recognition algorithm. When the sensor module detects a truck in the unloading area, it can send a prompt signal to the unmanned forklift. Upon receiving the prompt signal, the unmanned forklift can proceed to the truck and fork the containers from the truck at fixed intervals to both sides of the truck bed until the container is full. For example, the fixed interval can be 2 centimeters, but the specific interval is not limited.

[0087] 302. Using a target recognition algorithm, identify multiple vehicles placed on the trucks from the trucks parked in the unloading area.

[0088] The target recognition algorithm can be R-CNN, Faster R-CNN, YOLO, etc., and there is no specific limitation.

[0089] In this embodiment, the sensor module is located on both sides of the unloading area of ​​the truck, and the detection area corresponding to the sensor module covers the unloading area. The sensor module may include multiple sensors, and the detection areas of each sensor can be combined to form a complete detection area covering the unloading area, which serves as the detection area corresponding to the sensor module. Specifically, among the multiple sensors included in the sensor module, there is an overlap in the field of view between adjacent sensors to prevent missing fields of view. By fusing multiple sensors, the sensor module can monitor the complete unloading area.

[0090] 303. Based on the detection data of each sensor for each vehicle in the sensor module, calculate the global pose of each vehicle relative to the reference sensor. The global pose of each vehicle relative to the reference sensor is the zero pose of each vehicle.

[0091] The detection data of each sensor for each vehicle can be the vehicle's orientation data, distance data, and image data, etc., without any specific limitation; for example, when the sensor is a three-dimensional laser sensor, the laser can be shone on the surface of the vehicle, and the orientation data and distance data of the vehicle can be obtained based on the reflected laser; when the sensor is a depth camera sensor, the depth image data of the vehicle can be obtained.

[0092] Optionally, the sensor module can stitch together the detection areas corresponding to each sensor into a point cloud map to monitor the unloading area based on the detection data of each sensor for each vehicle in the sensor module. The point cloud map is a data matrix composed of the point cloud information of all points captured by the sensor module, generating a point cloud map covering the unloading area. Based on the point cloud map, the global pose of each vehicle relative to the reference sensor is calculated. The reference sensor can be used as the origin of the coordinate system of the point cloud map, and the global pose of each vehicle relative to the reference sensor can be the coordinate values ​​of each vehicle on the x, y, and z axes in the point cloud map, which can be positive or negative.

[0093] By implementing the above steps, a point cloud map is obtained through multi-sensor fusion and stitching, and the global pose of each vehicle relative to the reference sensor is acquired, thereby improving the accuracy of zero-point calibration for each vehicle.

[0094] 304. Verify the zero-position poses of multiple vehicles respectively, and obtain the verification results for each zero-position pose.

[0095] The sensor module can directly inspect the zero-position poses of multiple vehicles respectively and obtain the inspection result for each zero-position pose; or, the sensor module can send the zero-position poses of multiple vehicles respectively to a locally deployed electronic device, and the electronic device can inspect the zero-position poses of multiple vehicles respectively and obtain the inspection result for each zero-position pose.

[0096] Specifically, the sensor module can acquire the offset of each vehicle relative to the corresponding zero pose, as the test result for each zero pose; if the test result shows that the offset is greater than 0, it is determined that the zero pose calibration has failed and recalibration is performed; if the test result shows that the offset is equal to 0, it is determined that the zero pose calibration has been successful.

[0097] Optionally, each vehicle can be kept stationary, and the log value of the offset of each vehicle relative to the zero pose can be viewed. The log value of the offset of each vehicle relative to the zero pose can be used as the test result corresponding to each zero pose.

[0098] 305. Based on the test results corresponding to each zero pose, the zero pose calibration is confirmed to be successful.

[0099] If the offset of each vehicle relative to the zero pose is determined to be 0 by using the log value, it means that the vehicle is at the zero pose, and the zero pose calibration of the vehicle is confirmed to be successful.

[0100] In this embodiment of the application, the zero-position pose of multiple vehicles is checked respectively, which can further improve the accuracy of the zero-position calibration of the vehicles.

[0101] 306. Determine the pose transformation of the unmanned forklift relative to each carrier when the forklift is aligned with the center of each carrier for forklift insertion.

[0102] The unmanned forklift determines the pose transformation of the unmanned forklift relative to the zero position pose of each carrier when the forklift is aligned with the center of each carrier for forklift insertion.

[0103] In step 301, the unmanned forklift first picks up the vehicles from the truck and places them on both sides of the truck bed at fixed intervals. The truck bed is generally rectangular, and the length of one side of the truck is a fixed value. Given the length of each vehicle and the fixed interval between each vehicle, the pose offset between two adjacent vehicles can be determined as the sum of the length of the vehicle and the fixed interval.

[0104] Therefore, by aligning the unmanned forklift with the center of each carrier for forklift entry, one can first manually control the unmanned forklift to align with a reference carrier among multiple carriers on one side of the truck bed. Then, based on the pose offset between two adjacent carriers, the unmanned forklift can be automatically driven to each carrier and aligned with the center of each carrier for forklift entry. Alternatively, a marker corresponding to the center of each carrier can be determined, the unmanned forklift can be aligned with the marker corresponding to the center of each carrier, and then the unmanned forklift can be manually adjusted until it is aligned with the center of each carrier for forklift entry.

[0105] As an optional implementation, determining the transformed pose of the unmanned forklift relative to each carrier when the forklift is aligned with the center of each carrier for forklift entry can include the following steps: determining a reference carrier from multiple carriers; determining the transformed pose of the unmanned forklift relative to the reference carrier's zero-position pose based on the reference carrier's zero-position pose and the unmanned forklift's pose on the map when the forklift is aligned with the center of the reference carrier for forklift entry; and determining the transformed pose of the unmanned forklift relative to each carrier's zero-position pose based on the transformed pose of the unmanned forklift relative to the reference carrier's zero-position pose, the fixed spacing between the multiple carriers, and the dimensions of each carrier.

[0106] The reference vehicle can be the first vehicle placed on one side of the truck bed at the starting point of the truck bed, and there is no specific limitation.

[0107] The unmanned forklift can receive the zero-position pose of the reference vehicle sent by the sensor module, or the unmanned forklift can receive the zero-position pose of the reference vehicle sent by the sensor module through the central controller.

[0108] Unmanned forklifts can collect environmental information through sensors, draw maps based on the environmental information, and determine the pose of the unmanned forklift on the map based on the navigation system; for example, unmanned forklifts can achieve map building and localization through visual navigation (VSLAM) to obtain the pose of the unmanned forklift on the map.

[0109] The unmanned forklift determines its pose transformation relative to the zero pose of the reference vehicle based on the zero pose of the reference vehicle and the pose of the unmanned forklift on the map when it is aligned with the center of the reference vehicle for forklift insertion.

[0110] Since the pose offset between two adjacent vehicles is the sum of the vehicle's length and the fixed distance, after determining the transformed pose of the unmanned forklift relative to the reference vehicle's zero pose, the pose offset between two adjacent vehicles, and the pose of the unmanned forklift on the map when it is aligned with the center of each vehicle for fork entry, the transformed pose of the unmanned forklift relative to each vehicle's zero pose can be determined.

[0111] In this embodiment, when the unmanned forklift enters the center of a vehicle, the unmanned forklift can use its pose on the map and the zero-position pose of the vehicle to obtain the transformed pose of the unmanned forklift relative to the zero-position pose of the vehicle; wherein, the transformed pose is the pose of the unmanned forklift relative to the zero-position pose of each vehicle. Therefore, the zero-position poses of each vehicle can be converted into the transformed poses of the unmanned forklift relative to the zero-position poses of each vehicle, completing the zero-position calibration of each vehicle, which is beneficial for the unmanned forklift to accurately and efficiently plan the preset path for picking up multiple vehicles.

[0112] 307. Based on the transformation pose of the unmanned forklift relative to the zero position pose of each carrier, generate a preset path for the unmanned forklift to pick up multiple carriers.

[0113] Specifically, the unmanned forklift can generate a preset path for picking up multiple vehicles based on the transformation of the unmanned forklift's zero-position pose relative to each vehicle and the surrounding environmental information of the unloading area; the unmanned forklift can receive environmental information of the unloading area sent by the sensor module, or it can obtain surrounding environmental information through sensors such as laser scanners set on the unmanned forklift; the preset path for picking up multiple vehicles generated by the unmanned forklift can adapt to the surrounding environment, avoid obstacles in time, and accurately pick up each vehicle.

[0114] Because the truck stops at different locations in the unloading area each time and the vehicle is placed on the truck each time there is a deviation, the pre-planned path of the unmanned forklift cannot accurately pick up the vehicle loaded with goods. To solve this problem, this application embodiment calibrates the zero position of the vehicle, so that the unmanned forklift can accurately pick up each vehicle according to the zero position offset of the vehicle, complete the loading and unloading of goods, and improve the efficiency of loading and unloading goods.

[0115] 308. Obtain the offset of the actual pose of each vehicle relative to the corresponding zero pose.

[0116] The implementation method of step 308 can be referred to the above embodiments, and will not be described in detail here.

[0117] 309. Based on the offset, adjust the preset path for the unmanned forklift to pick up multiple vehicles to obtain the actual path for the unmanned forklift to pick up multiple vehicles.

[0118] After the unmanned forklift generates a preset path for picking up multiple vehicles based on the zero-position pose of multiple vehicles, it only needs to make adjustments based on the preset path after obtaining the offset. This improves the efficiency of determining the actual path for the unmanned forklift to pick up multiple vehicles, thereby improving the efficiency of loading and unloading goods.

[0119] 310. Based on the actual path of picking up multiple carriers, control the unmanned forklift to complete the loading and unloading of goods.

[0120] In this embodiment, the cargo loading and unloading system can, upon recognizing a truck parked in the unloading area, systematically forklift the loads from the truck to both sides of the truck bed, thereby improving the efficiency of subsequent unloading. Furthermore, by using the detection data of each load from each sensor in the sensor module, the global pose of each load relative to the reference sensor is determined as the zero-position pose, improving the accuracy of zero-position calibration of the loads. The zero-position pose of the loads is converted into a transformed pose of the unmanned forklift relative to the zero-position pose of the loads, thereby generating a preset path for the unmanned forklift to pick up multiple loads. Based on the offset of the actual pose of each load relative to the corresponding zero-position pose, the preset paths of multiple loads are adjusted, accurately determining the actual path for the unmanned forklift to pick up the loads, thus improving the efficiency of loading and unloading goods.

[0121] like Figure 4 As shown, Figure 4 This is a schematic flowchart of another cargo loading and unloading method disclosed in an embodiment of this application. This cargo loading and unloading method can be applied to the cargo loading and unloading system in the above embodiments, and the cargo loading and unloading method may include the following steps:

[0122] 401. Determine the zero position pose of each of the multiple vehicles placed on the truck.

[0123] The vehicle is used to load cargo, and the zero pose is the pose of each vehicle relative to the reference sensor in the sensor module.

[0124] 402. Determine the transformation pose of the unmanned forklift relative to each carrier when the forklift is aligned with the center of each carrier for forklift insertion.

[0125] 403. Based on the transformation pose of the unmanned forklift relative to the zero position pose of each carrier, generate a preset path for the unmanned forklift to pick up multiple carriers.

[0126] 404. Obtain the offset of the actual pose of each vehicle relative to the corresponding zero pose.

[0127] The implementation methods for steps 401 to 404 can be referred to the above embodiments, and will not be described in detail here.

[0128] 405. Bind multiple vehicles to different storage location identifiers.

[0129] Unmanned forklifts can bind multiple vehicles to different warehouse location identifiers.

[0130] The storage location identifier is used to indicate the corresponding storage location of the vehicle in the truck compartment.

[0131] Among them, a storage space is an area in the cargo compartment of a truck where vehicles are placed; it is a manually planned area. For example, the cargo compartment can be divided into two rows, and each row can be divided into 10 areas for placing vehicles.

[0132] For example, a base vehicle is determined from multiple vehicles and bound to the storage location identifier 0; other vehicles can be bound to storage location identifiers 1, 2, 3, etc. in sequence, without any specific restrictions.

[0133] 406. Based on the offset of the actual pose of each vehicle relative to the corresponding zero pose, determine the offset between the actual pose of each vehicle and the storage location indicated by the corresponding storage location identifier.

[0134] The unmanned forklift determines the offset between the actual pose of each carrier and the storage location indicated by the corresponding storage location marker based on the offset of the actual pose of each carrier relative to the corresponding zero pose. By binding the carrier with the storage location marker, the zero pose of the carrier can be converted into the pose of the storage location corresponding to the carrier. Based on the offset between the actual pose of each carrier and the storage location indicated by the corresponding storage location marker, the actual storage location to be placed for each carrier can be determined more accurately. This allows the unmanned forklift to adjust the preset path for picking up multiple carriers based on the actual storage location to be placed for each carrier, thereby accurately picking up each carrier to the actual storage location to be placed.

[0135] 407. Based on the offset between the actual position of each vehicle and the corresponding storage location indicated by the storage location identifier, the preset path for the unmanned forklift to pick up multiple vehicles is adjusted to obtain the actual path for the unmanned forklift to pick up multiple vehicles.

[0136] As an optional implementation, the unmanned forklift determines the offset between the actual pose of each vehicle and the storage location indicated by the corresponding storage location identifier, based on the offset of the actual pose of each vehicle relative to the corresponding zero pose. This can include the following steps:

[0137] Based on the offset of each vehicle's actual pose relative to its corresponding zero pose, the actual pose of the target vehicle is determined from multiple vehicles; the offset of the target vehicle's actual pose relative to the storage location indicated by the corresponding storage location identifier is determined; wherein, the offset of the target vehicle's actual pose relative to its corresponding zero pose is greater than 0.

[0138] The unmanned forklift adjusts the preset path for picking up multiple containers based on the offset between the actual pose of each container and the corresponding container location indicated by the location marker, thus obtaining the actual path for the unmanned forklift to pick up multiple containers. This can include the following steps:

[0139] Based on the offset between the actual position of the target vehicle and the corresponding storage location indicated by the storage location marker, the unmanned forklift adjusts the preset path for the unmanned forklift to pick up multiple vehicles, thus obtaining the actual path for the unmanned forklift to pick up multiple vehicles.

[0140] By performing the above steps, the target vehicle whose actual pose is offset from the corresponding zero pose can be determined from multiple vehicles. This helps to quickly filter out the target storage location with zero offset. Based on the offset between the actual pose of the target vehicle and the storage location indicated by the corresponding storage location identifier, the preset path for the unmanned forklift to pick up multiple vehicles can be locally adjusted, thereby improving the efficiency of loading and unloading goods.

[0141] 408. Based on the actual path of picking up multiple carriers, control the unmanned forklift to complete the loading and unloading of goods.

[0142] In this embodiment, the cargo loading and unloading system can obtain the zero-position pose of each vehicle relative to the reference sensor through the sensor module, thereby improving the accuracy of zero-position calibration of the vehicle. The zero-position pose of the vehicle is converted into the transformed pose of the unmanned forklift relative to the zero-position pose of the vehicle, thereby generating a preset path for the unmanned forklift to pick up multiple vehicles. By binding the vehicle with the storage location identifier, the zero-position pose of the vehicle can be converted into the pose of the storage location corresponding to the vehicle. Based on the offset between the actual pose of each vehicle and the storage location indicated by the corresponding storage location identifier, the actual storage location to be placed for each vehicle can be determined more accurately. This is beneficial for the unmanned forklift to adjust the preset path for picking up multiple vehicles based on the actual storage location to be placed for each vehicle, thereby accurately picking up each vehicle to the actual storage location to be placed, and improving the efficiency of loading and unloading goods.

[0143] like Figure 5 As shown, Figure 5 This is a modular schematic diagram of a cargo loading and unloading system disclosed in an embodiment of this application. The cargo loading and unloading system 500 includes a sensor module 10 and an unmanned forklift 20. The system includes:

[0144] The sensor module 10 is used to determine the zero position pose of multiple vehicles placed on the truck. The vehicles are used to load goods. The zero position pose is the pose of each vehicle relative to the reference sensor in the sensor module 10.

[0145] The sensor module 10 is used to acquire the offset of the actual pose of each vehicle relative to the corresponding zero pose.

[0146] The unmanned forklift 20 is used to determine the actual path for the unmanned forklift 20 to pick up multiple vehicles based on the offset.

[0147] The unmanned forklift 20 is used to control the unmanned forklift 20 to complete the loading and unloading of goods based on the actual path of picking up multiple carriers.

[0148] In one embodiment, the sensor module 10 is located on both sides of the unloading area of ​​the truck, and the detection area corresponding to the sensor module 10 covers the unloading area. The sensor module 10 is also used to identify multiple vehicles placed on the truck from the truck parked in the unloading area through a target recognition algorithm; and to calculate the global pose of each vehicle relative to the reference sensor based on the detection data of each vehicle by each sensor in the sensor module 10. The global pose of each vehicle relative to the reference sensor is the zero pose of each vehicle.

[0149] In one embodiment, the unmanned forklift 20 is further configured to, after the sensor module 10 determines the zero-position poses corresponding to the multiple vehicles placed on the truck, determine the transformed pose of the unmanned forklift 20 relative to the zero-position poses of each vehicle when the forklift 20 is aligned with the center of each vehicle for forking; and generate a preset path for the unmanned forklift 20 to pick up the multiple vehicles based on the transformed pose of the unmanned forklift 20 relative to the zero-position poses of each vehicle.

[0150] The unmanned forklift 20 is also used to adjust the preset path for the unmanned forklift 20 to pick up multiple vehicles according to the offset, so as to obtain the actual path for the unmanned forklift 20 to pick up multiple vehicles.

[0151] In one embodiment, the unmanned forklift 20 is further configured to determine a reference vehicle from a plurality of vehicles; determine a transformed pose of the unmanned forklift 20 relative to the reference vehicle's zero-position pose based on the reference vehicle's zero-position pose and the pose of the unmanned forklift 20 on a map when it is aligned with the center of the reference vehicle for forklift; and determine a transformed pose of the unmanned forklift 20 relative to each vehicle's zero-position pose based on the transformed pose of the unmanned forklift 20 relative to the reference vehicle's zero-position pose, the fixed spacing between the plurality of vehicles, and the size of each vehicle.

[0152] In one embodiment, the unmanned forklift 20 is further configured to bind multiple vehicles to different storage location identifiers before adjusting the preset path for the unmanned forklift 20 to pick up multiple vehicles according to the offset to obtain the actual path for the unmanned forklift 20 to pick up multiple vehicles; wherein, the storage location identifier is used to indicate the storage location corresponding to the vehicle in the unloading area.

[0153] The unmanned forklift 20 is also used to determine the offset between the actual pose of the target vehicle and the storage location indicated by the storage location identifier of the target vehicle, based on the offset between the actual pose of each vehicle and the zero pose of the corresponding vehicle; the offset between the actual pose of the target vehicle and the zero pose of the target vehicle is greater than the offset threshold; based on the offset between the actual pose of the target vehicle and the storage location indicated by the storage location identifier of the corresponding vehicle, the preset path for the unmanned forklift to pick up multiple vehicles is adjusted to obtain the actual path for the unmanned forklift to pick up multiple vehicles.

[0154] In one embodiment, the sensor module 10 can be used to verify the zero-position poses of the multiple vehicles placed on the truck after determining the zero-position poses of the multiple vehicles respectively, and obtain the verification result corresponding to each zero-position pose; and determine that the zero-position pose calibration is successful based on the verification result corresponding to each zero-position pose.

[0155] In one embodiment, the unmanned forklift 20 can be used to fork the vehicles in the truck at fixed intervals to both sides of the truck bed, while the truck is parked in the unloading area, before identifying multiple vehicles placed in the truck from the truck parked in the unloading area by using a target recognition algorithm.

[0156] In this embodiment, the cargo loading and unloading system includes an unmanned forklift and a sensor module. The system determines the zero-position pose of each carrier placed on a truck for loading cargo, wherein the zero-position pose is based on the pose of each carrier relative to a reference sensor in the sensor module. It acquires the offset of the actual pose of each carrier relative to its corresponding zero-position pose and determines the actual path for the unmanned forklift to pick up multiple carriers based on this offset. Based on this actual path, the system controls the unmanned forklift to complete the loading and unloading of cargo. This embodiment, based on the offset of the actual pose of each carrier relative to its corresponding zero-position pose, can accurately determine the actual path for the unmanned forklift to pick up the carriers, improving the efficiency of loading and unloading cargo.

[0157] like Figure 6 As shown, in one embodiment, an electronic device is provided, which may include:

[0158] Memory 610 storing executable program code;

[0159] Processor 620 coupled to memory 610;

[0160] The processor 620 can call the executable program code stored in the memory 610 to implement the cargo loading and unloading methods provided in the above embodiments.

[0161] The memory 610 may include random access memory (RAM) or read-only memory (ROM). The memory 610 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 610 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created during the use of the electronic device.

[0162] Processor 620 may include one or more processing cores. Processor 620 connects to various parts of the electronic device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 610, and by calling data stored in memory 610. Optionally, processor 620 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 620 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 620 and may be implemented separately using a communication chip.

[0163] Understandably, electronic devices may include more or fewer structural elements than those shown in the block diagram above, such as power modules, physical buttons, WiFi (Wireless Fidelity) modules, speakers, Bluetooth modules, sensors, etc., and are not limited thereto.

[0164] This application discloses a computer-readable storage medium storing a computer program that causes a computer to perform the methods described in the above embodiments.

[0165] Furthermore, this application further discloses a computer program product that, when run on a computer, enables the computer to execute all or part of the steps in any of the cargo loading and unloading methods described in the above embodiments.

[0166] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0167] The above provides a detailed description of a cargo loading and unloading method, system, electronic device, and storage medium disclosed in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for loading and unloading goods, characterized in that, The method is applied to a cargo loading and unloading system, the system including an unmanned forklift and a sensor module; the method includes: Determine the zero-position pose of each of the multiple vehicles placed on the truck, the vehicles being used to load cargo, and the zero-position pose being the pose of each vehicle relative to the reference sensor in the sensor module; Obtain the offset of the actual pose of each vehicle relative to the corresponding zero pose; Based on the offset, the actual path for the unmanned forklift to pick up the multiple vehicles is determined; Based on the actual path of picking up the multiple carriers, the unmanned forklift is controlled to complete the loading and unloading of the goods; After determining the zero-position poses of the multiple vehicles placed on the truck, the method further includes: The zero-position poses corresponding to the multiple vehicles are checked, and the check results corresponding to each zero-position pose are obtained. Based on the test results corresponding to each zero-position pose, it is determined that the zero-position pose calibration was successful.

2. The method according to claim 1, characterized in that, The sensor modules are located on both sides of the unloading area of ​​the truck, and the detection area corresponding to the sensor modules covers the unloading area. Determining the zero-position pose of the multiple vehicles placed on the truck includes: Using a target recognition algorithm, multiple vehicles placed inside the trucks are identified from the trucks parked in the unloading area; Based on the detection data of each vehicle by each sensor in the sensor module, the global pose of each vehicle relative to the reference sensor is calculated, and the global pose of each vehicle relative to the reference sensor is the zero-position pose of each vehicle.

3. The method according to claim 1 or 2, characterized in that, After determining the zero-position poses of the multiple vehicles placed on the truck, the method further includes: Determine the transformed pose of the unmanned forklift relative to each of the carriers when the unmanned forklift is aligned with the center of each of the carriers for forklift insertion; Based on the transformed pose of the unmanned forklift relative to the zero-position pose of each of the vehicles, a preset path is generated for the unmanned forklift to pick up the multiple vehicles. Determining the actual path for the unmanned forklift to pick up the multiple vehicles based on the offset includes: Based on the offset, the preset path for the unmanned forklift to pick up the multiple vehicles is adjusted to obtain the actual path for the unmanned forklift to pick up the multiple vehicles.

4. The method according to claim 3, characterized in that, The determination of the transformed pose of the unmanned forklift relative to each of the respective carriers when the forklift is aligned with the center of each carrier for fork insertion includes: A reference vehicle is determined from the plurality of vehicles; Based on the zero position pose of the reference vehicle and the pose of the unmanned forklift on the map when it is aligned with the center of the reference vehicle for forklift insertion, the transformed pose of the unmanned forklift relative to the zero position pose of the reference vehicle is determined. Based on the transformed pose of the unmanned forklift relative to the reference vehicle, the fixed distance between the multiple vehicles, and the size of each vehicle, the transformed pose of the unmanned forklift relative to the zero pose of each vehicle is determined.

5. The method according to claim 3, characterized in that, Before adjusting the preset path for the unmanned forklift to pick up the multiple vehicles based on the offset to obtain the actual path for the unmanned forklift to pick up the multiple vehicles, the method further includes: Each of the multiple vehicles is associated with a different storage location identifier; wherein, the storage location identifier is used to indicate the storage location corresponding to the vehicle in the unloading area of ​​the truck; The step of adjusting the preset path for the unmanned forklift to pick up the multiple vehicles based on the offset to obtain the actual path for the unmanned forklift to pick up the multiple vehicles includes: Based on the offset of the actual pose of each vehicle relative to the corresponding zero pose, determine the offset between the actual pose of each vehicle and the storage location indicated by the corresponding storage location identifier. Based on the offset between the actual position of each vehicle and the storage location indicated by the corresponding storage location identifier, the preset path for the unmanned forklift to pick up the multiple vehicles is adjusted to obtain the actual path for the unmanned forklift to pick up the multiple vehicles.

6. The method according to claim 2, characterized in that, Before identifying multiple vehicles placed on the trucks from the trucks parked in the unloading area using a target recognition algorithm, the method further includes: With the truck parked in the unloading area, the vehicles in the truck are forked out at fixed intervals and placed on both sides of the truck bed.

7. A cargo loading and unloading system, characterized in that, The cargo loading and unloading system includes unmanned forklifts and sensor modules. The system includes: The sensor module is used to determine the zero-position pose of multiple vehicles placed on the truck, the vehicles being used to load cargo, and the zero-position pose being the pose of each vehicle relative to a reference sensor in the sensor module. The sensor module is used to acquire the offset of the actual pose of each vehicle relative to the corresponding zero pose. The unmanned forklift is used to determine the actual path for the unmanned forklift to pick up the multiple vehicles based on the offset. The unmanned forklift is used to control the unmanned forklift to complete the loading and unloading of the goods based on the actual path of picking up the multiple carriers; The sensor module is used to inspect the zero-position poses corresponding to the multiple vehicles respectively, obtain the inspection result corresponding to each zero-position pose, and determine that the zero-position pose calibration is successful based on the inspection result corresponding to each zero-position pose.

8. An electronic device, characterized in that, include: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein, when executed by a processor, the computer program causes the processor to perform the method according to any one of claims 1 to 6.

Images