AGV intelligent control system for complex dynamic environment

Abstract

The application provides an AGV intelligent control system for a complex dynamic environment, comprising: a dynamic map module, which is used for processing dynamic levels of each perception factor according to real-time heterogeneous information collected by multiple fusion sensors, thereby constructing a hierarchical dynamic map, and each perception factor in the map having a dynamic attribute; the dynamic attribute comprises: a dynamic level; a stable confidence; a trigger priority label; a path planning and reconstruction module, which judges whether the current main path needs to be reconstructed according to the information provided by the hierarchical dynamic map, calls a TEB algorithm when the path needs to be reconstructed, increases a virtual cost in a high-dynamic-weight region in a path cost map, and increases a path constraint term in a TEB optimization objective function, the path constraint term being related to the dynamic attribute; after the path is generated, stability checking is performed, if the checking fails, the dynamic map module is fed back to request to expand the map region and retry.

Description

Technical Field

[0001] This invention relates to the field of AGV technology, and more specifically to an intelligent control system for AGVs in complex dynamic environments. Background Technology

[0002] Automated Guided Vehicles (AGVs) are widely used in warehousing and logistics, manufacturing, and medical transportation, primarily relying on fixed paths or static maps for navigation. However, in real-world applications, AGVs often face dynamic environmental disturbances, such as new obstacles (pedestrians, temporary storage of goods), changes in ground conditions (slippery, vibrating, uneven surfaces), and task scheduling adjustments. Traditional controllers lack sufficient flexibility in dealing with these changes, easily leading to path planning failures, task interruptions, and even collisions.

[0003] Therefore, how to enable AGVs to operate stably in complex and real-time changing scenarios is a problem that needs to be solved. Summary of the Invention

[0004] The purpose of this invention is to propose an intelligent control system for AGVs in complex and dynamic environments, which enables AGVs to operate stably in complex and real-time changing scenarios.

[0005] To achieve the above objectives, the present invention provides an intelligent control system for AGVs in complex dynamic environments, comprising:

[0006] The dynamic map module is used to process real-time heterogeneous information collected by multiple fusion sensors to obtain the dynamic level of each sensing factor, thereby constructing a hierarchical dynamic map, and each sensing factor in the map has dynamic attributes.

[0007] The dynamic attributes include:

[0008] Dynamic level, used to characterize the probability of change of the perceived factor;

[0009] Stable confidence is used to characterize the continuity of perceptual factors within a time window;

[0010] Trigger priority flags are used to indicate whether path reconstruction or speed adjustment is triggered;

[0011] The path planning and reconstruction module determines whether the current main path needs to be reconstructed based on the information provided by the hierarchical dynamic map. When path reconstruction is required, the TEB algorithm is invoked to add virtual costs to areas with high dynamic weights in the path cost map and add path constraint terms to the TEB optimization objective function. These path constraint terms are related to the dynamic attributes. After the path is generated, a stability check is performed. If the check fails, feedback is sent to the dynamic map module to request the expansion of the map area and a retry.

[0012] In the optional scheme, the dynamic level is divided into: stable factor, semi-dynamic factor, and high dynamic factor.

[0013] In an optional approach, path reconstruction is required when the information provided by the hierarchical dynamic map meets any of the following conditions:

[0014] The obstacle high-variability index path point coverage is greater than the first threshold;

[0015] High-priority perception factors are located at the beginning of the path. Inside;

[0016] Stable confidence Frequent fluctuations.

[0017] In the optional solution, the virtual cost is:

[0018]

[0019] in: This represents the base cost value in a standard cost map. This is the dynamic weight amplification factor; is a dynamic weighting coefficient, representing the probability that the position (x,y) is disturbed by an obstacle.

[0020] In the alternative solutions, the optimized objective function is:

[0021]

[0022] in, Costs comparable to traditional TEB; The weighting coefficients for the VPI cost term;

[0023]

[0024] in, Let be the i-th candidate path point on the path; Dj(Xi) represents the distance between the i-th path point on the path and the nearest obstacle; To maintain a stable confidence level; Trigger priority; It is a dynamic weighted index; This is the time since the last occurrence; This is the time decay coefficient.

[0025] In the optional scheme, the stability verification items shall include at least one of the following three:

[0026] Does the proportion of highly dynamic areas in the path segment fall below the safety threshold?

[0027] Does the path maintain a safe margin between itself and known high-dynamic factors in the map?

[0028] Are the start and end points aligned with the current pose / target point?

[0029] In an optional configuration, the system further includes a DOB module, a self-tuning module, a PID controller, and a control actuator.

[0030] The DOB module senses external disturbances in real time, calculates the error between the actual pose and the target trajectory, and estimates the total disturbance in real time.

[0031] The DOB module outputs the total disturbance rate of change, the error, and the error rate of change to the self-tuning module.

[0032] The self-tuning module adjusts the PID parameters in real time based on the output of the DOB module and the load status.

[0033] The PID controller acts on the control actuator according to the real-time adjusted PID parameters. The control actuator forms the final input based on the total disturbance output by the DOB module and the output of the PID controller, and feeds it back to the DOB module so that the DOB module can compensate for external disturbances.

[0034] In the optional scheme, the formula for calculating the total disturbance is:

[0035] It is a low-pass filter; The system's nominal transfer function; This is the actual pose; This is the final input.

[0036] In an optional embodiment, adjusting the PID parameters includes:

[0037] Small error but oscillation: Increase;

[0038] There is a steady-state error: Increase;

[0039] The total disturbance changes rapidly: temporary Increase;

[0040] Increased load: , Increase.

[0041] The beneficial effects of this invention are as follows:

[0042] The control system of the present invention has dynamic environment perception and path reconstruction capabilities, and can achieve stable operation in complex and real-time changing scenarios. Attached Figure Description

[0043] The above and other objects, features and advantages of the present invention will become more apparent from the accompanying drawings, in which like reference numerals generally denote like parts.

[0044] Figure 1 This is an architecture diagram of an AGV intelligent control system for complex dynamic environments according to one embodiment of the present invention.

[0045] Figure 2 This is a disturbance closed-loop adaptive control mechanism in one embodiment of the present invention. Detailed Implementation

[0046] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become clearer from the following description and drawings. However, it should be noted that the concept of the technical solution of the present invention can be implemented in many different forms and is not limited to the specific embodiments described herein. The accompanying drawings are all in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0047] It should be understood that when an element or layer is referred to as "on," "adjacent to," "connected to," or "coupled to" other elements or layers, it may be directly on, adjacent to, connected to, or coupled to other elements or layers, or there may be intervening elements or layers. Conversely, when an element is referred to as "directly on," "directly adjacent to," "directly connected to," or "directly coupled to" other elements or layers, there are no intervening elements or layers. It should be understood that although the terms first, second, third, etc., may be used to describe various elements, components, areas, layers, and / or portions, these elements, components, areas, layers, and / or portions should not be limited by these terms. These terms are only used to distinguish one element, component, area, layer, or portion from another element, component, area, layer, or portion. Therefore, without departing from the teachings of this invention, the first element, component, area, layer, or portion discussed below may be referred to as the second element, component, area, layer, or portion.

[0048] Spatial relation terms such as “below,” “under,” “below,” “under,” “above,” “above,” etc., are used herein for convenience of description to describe the relationship between one element or feature shown in the figure and other elements or features. It should be understood that, in addition to the orientation shown in the figure, spatial relation terms are intended to also include different orientations of the device in use and operation. For example, if the device in the figure is flipped, then the element or feature described as “below” or “under” the other element or feature will be oriented “above” the other element or feature. Therefore, the exemplary terms “below” and “under” can include both upper and lower orientations. The device may be otherwise oriented (rotated 90 degrees or otherwise) and the spatial descriptive terms used herein will be interpreted accordingly.

[0049] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0050] Example 1

[0051] Reference Figure 1 and Figure 2 This embodiment provides an intelligent control system for AGVs in complex dynamic environments, including:

[0052] The dynamic map module is used to process real-time heterogeneous information collected by multiple fusion sensors to obtain the dynamic level of each sensing factor, thereby constructing a hierarchical dynamic map, and each sensing factor in the map has dynamic attributes.

[0053] The dynamic attributes include:

[0054] Dynamic Level , used to characterize the probability of change of the perceived factor;

[0055] Stable confidence , used to characterize the continuity of the perceived factor within the time window;

[0056] Trigger priority flag This is used to characterize whether path reconstruction or speed adjustment is triggered.

[0057] The path planning and reconstruction module determines whether the current main path needs to be reconstructed based on the information provided by the hierarchical dynamic map. When path reconstruction is required, the TEB algorithm is invoked to add virtual costs to areas with high dynamic weights in the path cost map and add path constraint terms to the TEB optimization objective function. These path constraint terms are related to the dynamic attributes. After the path is generated, a stability check is performed. If the check fails, feedback is sent to the dynamic map module to request the expansion of the map area and a retry.

[0058] Specifically, traditional AGV perception layers focus only on obstacle detection and basic map building. This embodiment innovatively introduces a "hierarchical dynamic map" on top of this. By fusing heterogeneous information collected by LiDAR, visual SLAM, and infrared array modules, it dynamically updates the categories of each factor during map construction, thus building a hierarchical dynamic map. Each factor in the map not only records its spatial location but also carries the following dynamic attributes:

[0059] (1) Dynamic level (Reflecting its probability of change); (2) Stability confidence (Reflecting the continuity of the target within the time window); (3) Trigger priority flag (Whether it triggers path reconstruction or speed adjustment).

[0060] Referring to Table 1, the perceptual factors are divided into three categories according to their dynamic characteristics:

[0061] Table 1

[0062]

[0063] The hierarchical dynamic map provides the following three trigger signals to determine whether the current main path needs to be reconstructed:

[0064] If the obstacle high volatility index path point coverage is greater than or equal to the first threshold, it means that the area traversed by the path is likely to be disturbed.

[0065] High-priority perception factors are located at the beginning of the path. Within (meters);

[0066] Stable confidence Frequent fluctuations: If there are two consecutive declines, the area is considered no longer passable;

[0067] If any condition is met, proceed to the path reconstruction phase.

[0068] When reconstructing the path, the TEB (Timed Elastic Band) algorithm is invoked, and the following perceptual map guidance information is added:

[0069] Cost map updated:

[0070] In the path cost map, regions with high dynamic weights are given a virtual cost Cost(x,y):

[0071]

[0072] in: This represents the base cost value in a standard cost map. Dynamic weight amplification factor; is a dynamic weighting coefficient, representing the probability that the position (x,y) is disturbed by an obstacle.

[0073] Add a path constraint term to the TEB optimization objective function:

[0074] By adding the VPI (path constraint) term to the TEB optimization objective function, the path can actively avoid the "hotspot dynamic zone".

[0075] in: Costs comparable to traditional TEB; The weighting coefficients for the VPI cost term are used to adjust the importance of predicting obstacle avoidance.

[0076]

[0077] in, Let be the i-th candidate path point on the path; Dj(Xi) represents the distance between the i-th path point on the path and the nearest obstacle; To maintain a stable confidence level; Trigger priority; It is a dynamic weighted index; This is the time since the last occurrence; This represents the time decay factor. VPI is based not only on the obstacle movement history but also on the obstacle type and stability confidence level.

[0078] After path generation, the following checks are performed: whether the proportion of high-dynamic areas in the path segment is less than a safety threshold; whether a safe margin (e.g., ≥0.5 meters) is maintained between the path and known high-frequency disturbance factors in the map; and whether the start and end points are accurately aligned with the current pose / target point. If the conditions are not met, feedback is sent to the perception layer to request map area expansion and retry.

[0079] Traditional AGV controllers (such as fixed-parameter PID / MPC) suffer from parameter rigidity and lack of active disturbance rejection capability when faced with dynamic disturbances (such as slope, load fluctuations, and changes in ground friction), leading to decreased trajectory tracking accuracy and unstable operation. Therefore, this embodiment proposes a disturbance-based closed-loop adaptive control mechanism.

[0080] The system also includes a DOB (Disturbance Observer) module, a self-tuning module, a PID controller, and a control actuator. The DOB module senses external disturbances in real time, calculates the error between the actual pose and the target trajectory, and estimates the total disturbance in real time. The DOB module outputs the total disturbance change rate, the error, and the error change rate to the self-tuning module. The self-tuning module adjusts the PID parameters in real time based on the output of the DOB module and the load status. The PID controller acts on the control actuator based on the real-time adjusted PID parameters. The control actuator forms the final input based on the total disturbance output by the DOB module and the output of the PID controller, and feeds it back to the DOB module, enabling the DOB module to compensate for external disturbances.

[0081] The DOB module senses and compensates for external disturbances (such as slope, load changes, and minor collisions) in real time, integrates IMU and encoder data, and calculates the error between the actual pose and the target trajectory.

[0082] The formula for calculating the total disturbance is: .

[0083] It is a low-pass filter to suppress noise and ensure stability; The system's nominal transfer function; The actual pose is obtained from each sensor. For the final input, Actively eliminate the effects of disturbances.

[0084] The self-tuning module introduces self-adjustment rules, which combine control error trends, disturbance rate of change, and load estimates to adjust PID parameters in real time, using the following rules:

[0085] Large errors and rates of change: Significant under-adjustment / over-adjustment. Increase, enhance the corresponding Increase, suppress overshoot.

[0086] Small error but oscillation: insufficient damping. Increase.

[0087] Steady-state error exists: insufficient integration. Increase.

[0088] Total disturbance (k) Rapid changes: drastic and temporary disturbances. Increase and enhance resistance to interference.

[0089] Increased load: Increased inertia, , Increase, and vice versa.

[0090] The self-tuned PID parameters act on the system, and the resulting new control effects (error, rate of change of error) are fed back to the DOB module and the self-tuning module for disturbance estimation and parameter optimization in the next cycle.

[0091] This embodiment introduces mechanisms such as multi-level perception fusion, dynamic map reconstruction, adaptive control, and disturbance feedback pathways to form a closed-loop system of "active perception—predictive reconstruction—control coordination," which can significantly improve the AGV's autonomous operation capability, path planning flexibility, and control robustness in unstructured environments. The beneficial effects are as follows:

[0092] 1. Enhanced environmental adaptability, accurate perception of highly dynamic targets, significantly reduced path planning failure probability, proactive avoidance of high-risk areas, and improved path safety and collision avoidance capabilities.

[0093] 2. Enhanced control robustness effectively suppresses disturbances such as gradient changes and load fluctuations, improves trajectory tracking accuracy, adaptively adjusts parameters, and enhances operational stability under conditions such as high-speed emergency stops and sudden load changes.

[0094] 3. Expands applicability to complex scenarios, reduces reliance on manual parameter tuning, increases system response speed, supports unstructured environments (such as temporary warehouses), adapts to dynamic scenarios in multiple industries, and reduces deployment and adaptation costs and time.

[0095] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the present invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure shall fall within the protection scope of the claims.

Claims

1. An AGV intelligent control system for complex dynamic environment, characterized in that, The system comprises: a dynamic map module, configured to process real-time heterogeneous information collected by a plurality of fusion sensors to obtain dynamic levels of various perception factors, thereby constructing a hierarchical dynamic map, and each perception factor in the map having a dynamic attribute; the dynamic attribute comprises: a dynamic level, configured to represent a variation probability of the perception factor; a stable confidence, configured to represent a continuity of the perception factor within a time window; a trigger priority label, configured to represent whether to trigger path reconstruction or speed adjustment; a path planning and reconstruction module, configured to determine whether a current main path needs to be reconstructed according to information provided by the hierarchical dynamic map, and when the path needs to be reconstructed, to call a TEB algorithm, to increase a virtual cost of a region with a high dynamic weight in a path cost map, and to add a path constraint term related to the dynamic attribute in an optimization objective function of the TEB, and after the path is generated, to perform a stability check, and if the check fails, to feed back to the dynamic map module to request to expand a map region and to retry; when the information provided by the hierarchical dynamic map satisfies any one of the following conditions, the path needs to be reconstructed: an obstacle high variation index path point coverage rate is greater than a first threshold value; A perception factor with a high trigger priority is located ahead of the path inwardly; Stable confidence Frequent fluctuations; the virtual cost is: wherein: is a base cost value in the regular cost map; is a dynamic weight amplification coefficient; is a dynamic weight coefficient, representing the probability that the position (x, y) is disturbed by an obstacle; is a dynamic weight coefficient, representing the probability that the position (x, y) is disturbed by an obstacle; The optimized objective function is: wherein, is the traditional TEB cost; is the weight coefficient of the VPI cost term; wherein, is the i-th candidate waypoint on the path; Dj(Xi) represents the distance from the i-th waypoint on the path to the nearest obstacle; is the stable confidence; is the trigger priority; is the dynamic weight index; is the time since last occurrence; is the time decay coefficient.

2. The AGV intelligent control system for complex dynamic environment according to claim 1, wherein, the dynamic level is divided into: a stable factor, a semi-dynamic factor, and a high dynamic factor.

3. The AGV intelligent control system for complex dynamic environment of claim 1, wherein, the stability check includes at least one of the following three items: whether a high dynamic region proportion in a path segment is less than a safety threshold value; whether a safety margin is kept between the path and a known high dynamic factor in the map; whether a start and end point is aligned with a current pose or a target point.

4. The AGV intelligent control system for complex dynamic environment of claim 1, wherein, The system further comprises a DOB module, a self-tuning module, a PID controller, and a control actuator; the DOB module is configured to perceive an external disturbance in real time, to calculate an error between an actual pose and a target trajectory, and to estimate a total disturbance in real time; the DOB module outputs a total disturbance change rate, an error, and an error change rate to the self-tuning module; the self-tuning module adjusts PID parameters in real time according to outputs of the DOB module and a load state; the PID controller acts on the control actuator according to the PID parameters adjusted in real time, and the control actuator forms a final input according to the total disturbance output by the DOB module and the output of the PID controller, and feeds back to the DOB module, so that the DOB module compensates for the external disturbance.

5. The AGV intelligent control system for complex dynamic environment of claim 4, wherein, The total disturbance calculation formula is: is a low-pass filter; is a system nominal transfer function; is an actual pose; is a final input.

6. The AGV intelligent control system for complex dynamic environment of claim 4, wherein, the adjustment of the PID parameters comprises: Small error but oscillating: Increase; There is a steady state error: Increase; Total disturbance changes fast: temporary Increase; Load increase: , increase.

Images