Automatic recharging method for split mobile charging robot

Abstract

The invention relates to the technical field of charging robots, in particular to an automatic recharging method for a split mobile charging robot, which comprises the following steps: step 1, planning a task execution preliminary path according to a task based on an environment map of an environment where the split mobile charging robot is located in the split mobile charging robot; 2, collecting system features through an AI model, endowing the features with different weights, and outputting an optimal path or a recharging path and required charging time; and step 3, executing the task according to the optimal path. The AI model is trained according to historical data, whether recharging is needed or not is judged according to the model, and the whole process is intelligently planned. And the balance of task execution and recharging is optimized to the greatest extent, so that the whole system is more efficient.

Description

Technical Field

[0001] The present application relates to the technical field of charging robots, and in particular to an automatic recharging method for a split mobile charging robot. Background Art

[0002] With the development of robotics technology, transport robots have been widely used in logistics, warehousing, manufacturing and other fields. Automatic recharging, as an important part of the robot's operation process, can automatically recharge according to the set power threshold, avoiding shutdowns due to insufficient power and improving the robot's continuous operation capability.

[0003] However, the existing automatic recharging solution cannot meet the service operation scenario of the split mobile robot. In order to improve the operating efficiency and charging service quality of the overall system, it is an urgent problem to be solved by the present invention. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that the existing mobile charging robots have low operating efficiency.

[0005] To this end, the present invention provides an automatic recharging method for a split mobile charging robot.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] A method for automatically recharging a split mobile charging robot, comprising:

[0008] Step 1: Based on the environmental map of the environment in which the split mobile charging robot is located, a preliminary path for task execution is planned according to the task;

[0009] Step 2: The AI model collects system features, assigns different weights to each feature, and outputs the optimal path or recharging path and required charging time;

[0010] Step 3: Execute the task according to the optimal path.

[0011] Furthermore, in step 2, the system characteristics include state characteristics, power characteristics, time characteristics, path characteristics, and site characteristics.

[0012] Furthermore, the state characteristics are categorical variables, and the state characteristics include full-load standby, full-load operation, no-load standby, and no-load operation.

[0013] Furthermore, the power characteristics include the current power of the carrier vehicle and the current power of the energy vehicle.

[0014] Furthermore, the path characteristics include distance, energy consumption, and path complexity.

[0015] Furthermore, the time features include order start time, order end time, task start time, and task end time.

[0016] Furthermore, the site features include charging base location, service site location, usage, and queue time.

[0017] Furthermore, in step three, the AI model assigns different weight coefficients to each feature based on historical data, calculates the total weight of each path, and selects the path with the lowest weight as the optimal path.

[0018] Furthermore, in step three, the regression model is trained using historical data, and different weights are assigned to different model features to predict the time required to complete the task and the amount of electricity required to complete the task.

[0019] Furthermore, if the current power level meets the power required to complete the task, the optimal path is executed; if the current power level cannot meet the power required to complete the task, the split mobile charging robot is controlled to recharge.

[0020] The beneficial effect of this invention is that it comprehensively considers the various system characteristic variables during the charging robot's task execution, trains an AI model based on historical data, uses the model to determine whether recharging is necessary, and intelligently plans the overall process. This maximizes the balance between task execution and recharging, making the entire system more efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention will be further described below with reference to the accompanying drawings and examples.

[0022] Figure 1 It is a schematic diagram of the implementation process of the automatic recharging method of the split mobile charging robot in the present invention.

[0023] Figure 2 It is a schematic diagram of the system features of the present invention. DETAILED DESCRIPTION

[0024] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0025] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, features defined as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0026] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0027] A method for automatically recharging a split mobile charging robot includes the following steps:

[0028] Step 1: Environment map construction

[0029] The carrier robot in the split mobile charging robot uses binocular cameras, lidar and other sensors to build a map of the current environment and locate its current position in real time.

[0030] Step 2: Preliminary path planning

[0031] After receiving the task, multiple feasible paths are planned based on the processor in the task carrier robot.

[0032] Step 3: Optimize the path

[0033] The AI model is composed of multiple features, each of which has a certain weight. Based on historical data, different weight coefficients are assigned to each feature, and the total weight of each path is calculated. The path with the lowest weight is selected as the optimal path. The AI model construction process is as follows:

[0034] S3.1 Data Collection

[0035] The status characteristics of the mobile charging vehicle are obtained through the sensor equipment and battery management system on the mobile charging vehicle. The status characteristics of the mobile charging vehicle include the current power of the carrier vehicle, the operating status and the current power of the energy vehicle. The operating status includes full load standby, full load operation, no-load standby and no-load operation.

[0036] Obtain task characteristics, which include order start time, order end time, task start time, and task end time; obtain path characteristics, which include distance, energy consumption, and path complexity. Path characteristics can be calculated using map information and historical data; obtain site characteristics through the site management system, which include charging base location, service site location, usage, and queue time.

[0037] Set the operating status as a categorical variable, the current power of the carrier vehicle, the current power of the energy vehicle, the route characteristics, and the station characteristics as numerical variables, and set the task characteristics as the timestamp.

[0038] S3.2 Data Preprocessing

[0039] Each path under each task includes n features, the value of the (i)th feature is (xi), and the weight is (wi), then the total weight (W) of each path can be expressed as: W = w1x1 + w2x2 + .....wnxn, where (wi) is the weight of feature (i) and (xi) is the actual value of feature (i).

[0040] Specific calculation: For each candidate path, according to its corresponding feature value and weight, substitute it into the above formula to calculate the total weight. For example:

[0041] Assume that for a task path, the actual value of the state feature is 1 and its weight is 0.8, the actual value of the power feature is 0.7 and its weight is 0.5, and the actual value of the time feature is 2 and its weight is 0.3. Then, the calculation process of the total weight (W) is as follows: W = (0.8*times 1) + (0.5*times 0.7) + (0.3*times 2), W = 0.8 + 0.35 + 0.6 = 1.75. Therefore, the total weight of this path is 1.75.

[0042] State characteristics (full load standby, full load operation, no-load standby, no-load operation): different weights can be assigned according to the historical impact of the state.

[0043] Power characteristics (current power of the carrier vehicle, current power of the energy vehicle): The lower the power, the more likely the need for charging will increase, and the higher the weight.

[0044] Time features (order start time, order end time, task start time, task end time): Long time may cause delays and have a higher weight.

[0045] Path characteristics (distance, energy consumption, path complexity): The longer the distance, the greater the energy consumption, and the more complex the path, the higher the weight.

[0046] Site characteristics (charging base location, service station location, usage, queue time): The closer the charging base location and the shorter the queue time, the lower the weight.

[0047] S3.3 Time prediction

[0048] Use historical data to train a regression model, assign different weights to different model features, and predict the time required to complete the task.

[0049] S3.4 Power Forecast

[0050] Use historical data to train a regression model, assign different weights to different model features, and predict the amount of power required to complete the task.

[0051] Step 4: Execution path

[0052] Based on the current status of the mobile charging vehicle and the prediction results obtained in steps S3.3 and S3.4, if the remaining power can meet the task execution, the optimal path navigation is followed to execute the task, which includes sending the robot out and returning it to the warehouse.

[0053] If the remaining battery charge is insufficient to complete the task, the vehicle will return to the charging station along the route. Driving to the charging area, the vehicle will use LiDAR and binocular cameras for precise docking. During charging, the vehicle will continuously monitor the charging status until the optimal charging time output by the model is reached. Once fully charged, the vehicle will re-plan its route to execute the assigned task.

[0054] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical spirit of this invention. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A split mobile charging robot automatic recharging method, characterized in that: include, Step 1: Based on the environmental map of the environment in which the split mobile charging robot is located, a preliminary path for task execution is planned according to the task; Step 2: The AI model collects system features, assigns different weights to each feature, and outputs the optimal path or recharging path and required charging time; Step 3: Execute the task according to the optimal path.

2. The automatic recharging method of the split mobile charging robot according to claim 1 is characterized in that: In the step 2, the system characteristics include state characteristics, power characteristics, time characteristics, path characteristics and site characteristics.

3. The automatic recharging method of the split mobile charging robot according to claim 2, characterized in that: The state feature is a categorical variable, and the state feature includes full-load standby, full-load operation, no-load standby, and no-load operation.

4. The automatic recharging method of the split mobile charging robot according to claim 2, characterized in that: The power characteristics include the current power of the carrier vehicle and the current power of the energy vehicle.

5. The automatic recharging method of the split mobile charging robot according to claim 2, characterized in that: The path characteristics include distance, energy consumption, and path complexity.

6. The automatic recharging method of the split mobile charging robot according to claim 2, characterized in that: The time features include order start time, order end time, task start time, and task end time.

7. The automatic recharging method of the split mobile charging robot according to claim 2, characterized in that: The site features include charging base location, service site location, usage, and queue time.

8. The automatic recharging method of the split mobile charging robot according to claim 1, characterized in that: In step three, the AI model assigns different weight coefficients to each feature based on historical data, calculates the total weight of each path, and selects the path with the lowest weight as the optimal path.

9. The automatic recharging method of the split mobile charging robot according to claim 8, characterized in that: In step three, the regression model is trained using historical data, with different weights assigned to different model features to predict the time required to complete the task and the amount of electricity required to complete the task.

10. The automatic recharging method of the split mobile charging robot according to claim 9, characterized in that: If the current power level meets the power required to complete the task, the optimal path is executed; if the current power level cannot meet the power required to complete the task, the split mobile charging robot is controlled to recharge.

Images