Method and device for automatic quality detection, information extraction and simulation based on log data

Abstract

The invention belongs to the technical field of mobile robots, and relates to a method and device for automatic quality detection, information extraction and simulation based on log data, and the method comprises the steps: 1, automatically recording rosbag when a task starts; step 2, data quality inspection processing; step 3, information extraction and integrity detection; 4, performing data driving simulation; and 5, analyzing and playing back a simulation result. In the first step, when the AMR executes a transportation task, the system automatically triggers a rosbag record function of the ROS, recording of multiple key topics in the whole process of the task is automatically stopped after the task is finished, and a complete task log package is generated. The method has the effect of performing high-fidelity reproduction, quality inspection, extraction, playback and simulation execution on historical tasks to assist in judging whether the state machine design is reasonable or not.

Description

Technical Field

[0001] This invention relates to the technical field of mobile robot simulation, and in particular to a method and apparatus for automated quality inspection, information extraction and simulation based on log data. Background Technology

[0002] Currently, AMR is commonly used in logistics and warehousing scenarios, where task scheduling relies on complex conditional judgments. During delivery task execution, there is often a lack of effective task data backtracking, automated quality inspection, and simulation verification mechanisms. Although Rosbag log functionality is supported, this data is mostly used for manual analysis and cannot efficiently and automatically verify the workflow. This results in the workflow state machine's robustness not being fully verified before deployment, impacting system stability and user experience. Summary of the Invention

[0003] The purpose of this invention is to provide a method and apparatus for automated quality inspection, information extraction and simulation based on log data, in order to solve the technical problem that the workflow state machine cannot be fully verified before deployment, thus affecting system stability and user experience. The invention aims to achieve high-fidelity reproduction, quality inspection, extraction, playback and simulation of historical tasks, thereby assisting in judging whether the state machine design is reasonable.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: A method for automated quality inspection, information extraction, and simulation based on log data includes: Step 1: Automatically record rosbag when the task starts; Step 2: Data quality inspection and processing; Step 3: Information extraction and integrity check; Step 4: Data-driven simulation; Step 5: Simulation results analysis and playback.

[0005] As a preferred embodiment of the present invention, in step one, when the AMR is performing a delivery task, the system automatically triggers the ROS rosbag record function to record multiple key topics throughout the entire task process: task status, battery and equipment status, order information, odometer and radar information, etc. Recording is automatically stopped after the task is completed, and a complete task log package is generated.

[0006] As a preferred embodiment of the present invention, in step two, the recorded rosbag file is validated, including multiple dimensions such as topic completeness, time duration, and whether the task is completed normally: whether the task status is marked as completed, whether an abnormal status occurs, whether charging is completed normally, and whether the required topic is recorded. Log packets with incomplete or abnormal tasks are automatically deleted.

[0007] As a preferred embodiment of the present invention, in step three, the qualified rosbag is parsed, and key information files in JSON format are extracted and organized, including: task ID, start / end time, order number, target point, status change event and timestamp, charging and power change information. The extracted data fields are checked for integrity to ensure that the data is valid and no fields are missing.

[0008] In a preferred embodiment of the present invention, in step four, the status information in the JSON file is simulated and sent to the server in real time at 1:1 time intervals according to the timestamp order in the original task. The server injects the received information into the state machine of the target workflow and executes it, simulating the task execution process to verify the correctness of the state machine's execution.

[0009] As a preferred embodiment of the present invention, in step five, the system records the input and output results of each simulation, including the simulation success or failure status, execution path, failure node, etc., and supports replay of the failed simulation process for further determination of the cause of failure (data anomaly or state machine defect). After each round of simulation, statistical analysis is performed on this round of simulation, a report is generated, and the robustness and consistency of the current state machine are judged and verified.

[0010] Another object of the present invention is to provide an apparatus, Mobile robots, for example, employ the methods described above for automated quality inspection, information extraction, and simulation based on log data.

[0011] The beneficial effects of this invention are: 1. Task-driven automatic ROSbag data collection mechanism The rosbag data acquisition is automatically started by listening for AMR scheduling or task start signals. Avoid human intervention and achieve complete data recording at the task level.

[0012] 2. Log data quality inspection and automatic removal of invalid tasks Validity is determined using topics, states, etc., in the bag file; Failed or interrupted tasks are filtered out to ensure the reliability of simulation data.

[0013] 3. Information structuring and integrity verification for simulation purposes The raw log data is abstracted into an ordered event stream and standardized into JSON format. And validate key information (such as event time and status fields).

[0014] 4. Reconstruct the task process according to the time scale and drive the state machine simulation. Reconstruct the task execution process at a 1:1 or multiplier based on the original event timestamp; Simulate the running state machine to verify its logical integrity and practicality.

[0015] 5. Automatic archiving of simulation results and analysis of abnormal tasks. Automatically record simulation logs, results, and anomalies; Supports visual replay of failed tasks to help pinpoint the source of problems (data vs. state machine). Attached Figure Description

[0016] Figure 1 This is a diagram showing the execution result of the simulation end state machine of the method and apparatus for automated quality detection, information extraction and simulation based on log data according to the present invention - execution passed. Figure 2 This is a simulation end state machine execution result of the method and apparatus for automated quality detection, information extraction and simulation based on log data of the present invention - execution failed display diagram; Figure 3 This is a statistical chart of the simulation results for each round of this invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1: like Figures 1 to 3 As shown, a method for automated quality inspection, information extraction, and simulation based on log data includes: Step 1: Automatically record rosbag when the task starts; When the AMR performs a delivery mission, the system automatically triggers the ROS rosbag record function to record multiple key items throughout the mission process, such as mission status, battery and equipment status, order information, odometer and radar information, etc. Recording will automatically stop after the mission is completed and a complete mission log package will be generated.

[0019] In this process, a listening node is deployed in the ROS system. After capturing the start task command, the rosbag record is automatically invoked to record the specified topic.

[0020] Example topics include: / task_status (task execution status) / mqtt_info (Device Information) / charge_info (charging information and order information) / odom (odometer information) / cmd_vel (motion commands), etc.

[0021] Name the task by binding it with a task ID and time information. Determine if the task is complete by monitoring its status and automatically stop recording.

[0022] Step 2: Data quality inspection and processing; The recorded rosbag files are validated for validity, including multiple dimensions such as topic completeness, duration, and whether the task is completed normally: whether the task status is marked as completed, whether there are any abnormal states, whether charging is completed normally, and whether the required topic is recorded. Log packets with incomplete or abnormal tasks are automatically deleted.

[0023] Simultaneously, the rosbag API in Python is used for reading. First, the topic list in the bag is read to see if it contains the required target topic. If it does not, the recording is missing or the data sending end is abnormal. Second, the topics in the bag are compared sequentially according to the set task status change rules. If they do not match, the task execution is abnormal. Finally, the task completion marker is checked. If it is not detected, the task is not completed. Through the above process, unqualified data packets are automatically deleted.

[0024] Step 3: Information extraction and integrity check; Parse the qualified rosbag, extract and organize it into a key information file in JSON format, including: task ID, start / end time, order number, target point, status change events and timestamps, charging and power change information, and perform integrity checks on the extracted data fields to ensure that the data is valid and no fields are missing.

[0025] For bag data that passes quality inspection, a Python script will call the rosbag.Bag() interface to parse each message, extracting information such as navigation events, charging actions, task nodes, failures / interruptions, and task IDs. This information will then be saved in a unified JSON format, as shown in the example below. { "task_id": MA1JKEM2X191244885665893990", "start_time": 1744798101, "events": [ {"task_status": "move_to_body", "timestamp": 1744798101}, {"task_status": "reach_goal", "timestamp": 1744798167}, {"charge_info": *************", "timestamp": 1744798142}, {"order_info": "******************", "timestamp": 1744798142} ] } Each event is validated before being sent to avoid issues such as empty values ​​or incorrect formats.

[0026] Step 4: Data-driven simulation; The status information in the JSON file is sent to the server in real time, following the timestamp order in the original task, at 1:1 time intervals. The server injects the received information into the state machine of the target workflow and executes it, simulating the task execution process to verify the correctness of the state machine's execution.

[0027] like Figure 1 As shown, after the system starts the simulation, it sends the data in the JSON file to the MQTT server in real time at 1:1 time intervals according to the timestamp in the JSON. Each event is sent to the workflow server via HTTP POST. After receiving the event, the workflow engine advances its internal process. The state machine system will simulate the task execution trajectory. Each transition of the state machine will be recorded in the log, including the current state, the next state, the action name, and whether it was successful.

[0028] Step 5: Simulation Result Analysis and Replay The system records the input and output results of each simulation, including the simulation success or failure status, execution path, failure nodes, etc., and supports replaying the failed simulation process to further determine the cause of the failure (data anomaly or state machine defect). At the end of each simulation round, statistical analysis is performed on the simulation, reports are generated, and the robustness and consistency of the current state machine are judged and verified.

[0029] like Figure 3 As shown, after the simulation is completed, the system generates the following information table: Simulation task ID, corresponding data source ID, state machine / workflow ID used, and state machine information. If the simulation fails, e.g. Figure 1 and 2 As shown, the state machine system highlights failure points, allowing developers to diagnose problems using the saved information table. At the end of each simulation round, statistical analysis is performed, reports are generated, and the robustness and consistency of the current state machine are assessed and verified.

[0030] Example 2: An apparatus including a mobile robot, which employs the method described above for automated quality inspection, information extraction and simulation based on log data.

[0031] In summary, the advantages of this application are as follows: 1. Task-driven automatic ROSbag data collection mechanism The rosbag data acquisition is automatically started by listening for AMR scheduling or task start signals. Avoid human intervention and achieve complete data recording at the task level.

[0032] 2. Log data quality inspection and automatic removal of invalid tasks Validity is determined using topics, states, etc., in the bag file; Failed or interrupted tasks are filtered out to ensure the reliability of simulation data.

[0033] 3. Information structuring and integrity verification for simulation purposes The raw log data is abstracted into an ordered event stream and standardized into JSON format. And validate key information (such as event time and status fields).

[0034] 4. Reconstruct the task process according to the time scale and drive the state machine simulation. Reconstruct the task execution process at a 1:1 or multiplier based on the original event timestamp; Simulate the running state machine to verify its logical integrity and practicality.

[0035] 5. Automatic archiving of simulation results and analysis of abnormal tasks. Automatically record simulation logs, results, and anomalies; Supports visual replay of failed tasks to help pinpoint the source of problems (data vs. state machine).

[0036] All the devices selected in this application are general standard parts or components known to those skilled in the art. Their structures and principles can be learned by those skilled in the art through technical manuals or conventional experimental methods.

[0037] In the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0038] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0039] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. 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 method for automated quality inspection, information extraction, and simulation based on log data, characterized in that, include: Step 1: Automatically record rosbag when the task starts; Step 2: Data quality inspection and processing; Step 3: Information extraction and integrity check; Step 4: Data-driven simulation; Step 5: Simulation results analysis and playback.

2. The method for automated quality detection, information extraction, and simulation based on log data as described in claim 1, characterized in that, In step one, when the AMR is performing a delivery task, the system automatically triggers the ROS rosbag record function to record multiple key topics throughout the entire task process: task status, battery and equipment status, order information, odometer and radar information, etc. Recording will automatically stop after the task is completed and a complete task log package will be generated.

3. The method for automated quality detection, information extraction, and simulation based on log data as described in claim 2, characterized in that, In step two, the recorded rosbag files are validated for validity, including multiple dimensions such as topic completeness, duration, and whether the task is completed normally: whether the task status is marked as completed, whether there are any abnormal states, whether charging is completed normally, and whether the required topic is recorded. Log packages with incomplete or abnormal tasks are automatically deleted.

4. The method for automated quality detection, information extraction, and simulation based on log data as described in claim 3, characterized in that, In step three, the qualified rosbag is parsed, and key information files in JSON format are extracted and organized, including: task ID, start / end time, order number, target point, status change events and timestamps, charging and power change information. The extracted data fields are checked for integrity to ensure that the data is valid and no fields are missing.

5. The method for automated quality detection, information extraction, and simulation based on log data as described in claim 4, characterized in that, In step four, the status information in the JSON file is simulated and sent to the server in real time at 1:1 time intervals, following the timestamp order in the original task. The server injects the received information into the state machine of the target workflow and executes it, simulating the task execution process to verify the correctness of the state machine's execution.

6. The method for automated quality detection, information extraction, and simulation based on log data as described in claim 5, characterized in that, In step five, the system records the input and output results of each simulation, including the state of success or failure, execution path, failure node, etc., and supports replay of the failed simulation process to further determine the cause of failure (data anomaly or state machine defect). At the end of each simulation round, statistical analysis is performed on the simulation, reports are generated, and the robustness and consistency of the current state machine are judged and verified.

7. An apparatus, characterized in that, The method, including mobile robots, employs the automated quality inspection, information extraction, and simulation method based on log data as described in any one of claims 1-6.

Images