KR-102959840-B1 - Automated Robotic Tire Packing System and Method with Optimization-Based Online Planning Module

KR102959840B1KR 102959840 B1KR102959840 B1KR 102959840B1KR-102959840-B1

Abstract

The present invention relates to an automated robot tire paving system and method equipped with an optimization-based online planning module. In a robot control system for automatic paving of multi-size tires, the system may include a vision module that acquires RGB-D images of tires stacked in a loading area to estimate the pose of individual tires, a geometric planning module that calculates the target pose of the next tire using Mixed Integer Linear Programming (MILP) based on the tire pose acquired from the vision module, and a motion planning module that plans a collision avoidance trajectory using Model Predicted Path Integrating (MPPI) control that randomly samples to load tires to the target pose calculated by the geometric planning module.

Inventors

박준형
박기범
신천호
안상현
이상호
전슬기
한규상
박종열

Assignees

주식회사 라스테크
주식회사 한국네트웍스

Dates

Publication Date: 20260511
Application Date: 20260114

Claims (5)

In an automated robotic tire packaging system for the automatic packaging of multi-standard tires, A vision module (100) that acquires RGB-D images of tires stacked in a loading area and estimates the pose of individual tires; A geometric planning module (200) that calculates the next target pose of the tire by utilizing mixed integer linear programming (MILP) based on the tire pose obtained from the vision module (100); and An automated robot tire paving system equipped with an optimization-based online planning module, comprising: a motion planning module (300) that plans a collision avoidance trajectory by utilizing model predictive path integration (MPPI) control that randomly samples to load the tire to a target pose calculated by the geometric planning module.
In Article 1, The above geometric planning module (200) is, An asymmetric modeling unit (210) that defines different modeling shapes for existing tires and new tires to improve computation speed; A pattern damage detection unit (220) that detects and repairs structural disconnection occurring during loading; and An automated robotic tire paving system equipped with an optimization-based online planning module comprising: a free-form filling control unit (230) that performs filling by relaxing pattern constraints to maximize loading space efficiency.
In Paragraph 2, The above asymmetric modeling section (210) is, Approximation modeling unit (211) that approximates the center hole of the existing tire as two convex polygons with the hole removed and the new tire as a bounding rectangle to prevent overlapping arrangement of the center hole of the existing tire; and An automated robot tire paving system equipped with an optimization-based online planning module, comprising: a validity verification unit (212) that calculates whether there is an overlap between the convex polygon approximated by the approximation modeling unit (211) and the bounding rectangle to verify the validity of the tire placement in real time.
In Paragraph 2, The above pattern damage detection unit (220) is, A monitoring unit (221) that checks in real time the continuity of the outermost contour formed by the last tire row of a previously completed layer using information obtained through the above vision module (100); and A buffer recovery unit (222) that restores the interlocking structure by allocating a new tire as a buffer and placing it in a horizontal position at the location of the empty space when an empty space is detected in the contour confirmed by the monitoring unit (221) above; The above free-form filling control unit (230) is, A loading height detection unit (231) that determines whether the loading height inside the loading frame (50) has reached a set stacking limit; When the limit of the above-mentioned loading height detection unit (231) is reached, an angle expansion unit (232) that generates angle candidates by expanding the angle of a set of direction candidates (Θ) to multiple times for tire placement; and An automated robot tire paving system equipped with an optimization-based online planning module, comprising: an optimal filling control unit (233) that controls by changing the optimization objective function to fill the remaining cavity inside the loading frame (50).
In an automated robot tire packaging method using an industrial robot (40), A recognition step (S1100) in which a vision module (100) analyzes an image of a loading area to recognize a three-dimensional pose including the position and direction of the tire; After the above recognition step (S1100), a placement planning step (S1200) in which the geometric planning module (200) determines a target pose by performing replanning through a three-step loop of 'solve-place-shrink' until the number of target tires of the corresponding layer is exhausted; and An automated robot tire paving method equipped with an optimization-based online planning module, comprising: a driving control step (S1300) in which, after the above-mentioned placement planning step (S1200), the driving of the industrial robot (40) is controlled by performing random sampling-based model prediction path integration (MPPI) control to generate a collision avoidance path to a target pose, wherein the driving of

Description

Automated Robotic Tire Packing System and Method with Optimization-Based Online Planning Module The present invention relates to an automated robotic tire paving system and method equipped with an optimization-based online planning module, and is an invention regarding an automated robotic tire paving system and method equipped with an optimization-based online planning module capable of high-density inclined loading of tires by integrating vision recognition information, optimization-based geometric planning, and real-time feedback motion planning, while considering the characteristics of tires having an annular geometric structure and elasticity. Although the demand for automation in the logistics and packaging sectors has recently surged, the final loading stage of the tire industry still relies heavily on human labor. This is because it is difficult to maintain a robust stacking structure using the conventional sequence-based open-loop method due to the tire's annular structure, deformation caused by elasticity, and the accumulation of placement errors. Existing systems enforce predefined patterns tailored to a single tire type, making them unable to flexibly respond to variability in real-world environments or mixed tire types; consequently, there is a high risk of the load losing lateral support and collapsing. Therefore, there is an urgent need for an online tire pavement loading framework capable of real-time replanning based on recognition information. FIGS. 1 and 2 are exemplary diagrams of an automated robotic tire paving system equipped with an optimization-based online planning module according to an embodiment of the present invention. FIGS. 3 and 4 are block diagrams of an automated robotic tire paving system equipped with an optimization-based online planning module according to an embodiment of the present invention. FIG. 5 is an exemplary diagram of a vision module according to one embodiment of the present invention. FIG. 6 is an exemplary diagram of an asymmetric modeling section according to an embodiment of the present invention. FIG. 7 is an exemplary diagram of a pattern breakage detection unit according to one embodiment of the present invention. Specifically, the case with a buffer in the blue box and the case without a buffer in the red box are compared, where (a) to (d) illustrate the formation of a lag, detection of damage (pattern collapse), recovery through buffer placement, and the dense final stacking state after free-form filling, and (e) to (g) illustrate the initial pattern collapse due to unsafe rotation and the point contact state vulnerable to rolling, through which it can be seen that buffer correction and perception feedback are required. FIG. 8 is a flowchart illustrating an automated robot tire paving method equipped with an optimization-based online planning module according to an embodiment of the present invention. Embodiments of the present invention will be described in detail below with reference to the attached drawings. However, the present invention is not limited to these embodiments and can be modified in various forms. In the drawings, parts unrelated to the description have been omitted to clearly and concisely explain the present invention, and the same reference numerals are used for identical or extremely similar parts throughout the specification. Additionally, in the drawings, thicknesses, widths, etc., are depicted enlarged or reduced to make the description clearer; however, the thicknesses, widths, etc., of the present invention are not limited to those depicted in the drawings. And when any part of the specification is described as "including" another part, unless specifically stated otherwise, it does not exclude other parts and may include additional parts. Hereinafter, an automated robotic tire paving system and method equipped with an optimization-based online planning module will be described in detail with reference to the attached drawings. FIGS. 1 and 2 are exemplary diagrams of an automated robot tire paving system equipped with an optimization-based online planning module according to an embodiment of the present invention, and FIGS. 3 and 4 are block diagrams of an automated robot tire paving system equipped with an optimization-based online planning module according to an embodiment of the present invention. As illustrated in FIGS. 1 to 4, an automated robot tire paving system equipped with an optimization-based online planning module according to one embodiment of the present invention can load tires at a high density by considering the annular geometric structure and elasticity of the tires through RGB-D vision sensing, Model Predictive Path Integral (MPPI) control, and optimization-based Rick-Rack rules. In general, the task of loading tires into containers or trailers in tire logistics still relies heavily on manual labor. Furthermore, due to the inherent annular structure and elasticity of tires, there is a problem where the s