Robotic repair control system and method

Abstract

A repaired region on a work surface is presented herein. The repaired region includes a repair boundary. Within the repair boundary, the work surface has a repair texture, and outside the repair boundary, the work surface has a work surface texture. The repaired region also includes a repair depth distribution within the repair boundary and hidden features. The repaired region is a result of performing robotic repair on the work surface to remove defects.

Description

Background Art

[0001] Clearcoat repair is one of the last operations to be automated in the automotive original equipment manufacturing (OEM) sector. Technologies are desired to automate this process as well as other paint applications (e.g., primer sanding, clearcoat defect removal, clearcoat polishing, etc.) suitable for inspection and repair using abrasives and / or robots.

[0002] Early work to automate the detection and repair of paint defects includes a system described in U.S. Patent Publication 2003 / 0139836, which discloses the use of electronic imaging to detect and repair paint defects on vehicle bodies. The system references vehicle imaging data with vehicle CAD data to form three-dimensional paint defect coordinates for each paint defect. The paint defect data and paint defect coordinates are used to develop repair countermeasures for automated repair using multiple automated robots that perform a variety of tasks, including sanding and polishing paint defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views.The drawings are generally shown by way of example, but not limitation, of the various embodiments discussed in this document.

[0004] Figure 1 is a schematic diagram of a robotic paint repair system in which embodiments of the present invention are useful.

[0005] Figure 2 is a schematic diagram of a paint repair robot that may be used with embodiments of the present invention.

[0006] Figure 3 A method of robot defect repair according to an embodiment of the present invention is shown.

[0007] FIG. 4A to FIG. 4B is an image of a defect that may be present on a vehicle.

[0008] Figure 5 Variables of interest in a robotic paint repair system are shown.

[0009] FIG. 6A to FIG. 6D Exemplary pressure responses that may be used in embodiments of the present invention are shown.

[0010] FIG. 7A to FIG. 7C Exemplary orientations are shown that may be useful in embodiments of the invention.

[0011] Figure 8 The pressure profile of an orbital sander is shown.

[0012] FIG. 9A to FIG. 9BVelocity profiles for a rotary sander and an orbital sander are shown.

[0013] FIG. 10A to FIG. 10C Shapes that can be used as the basis for robotic repair trajectories in embodiments of the present invention are shown.

[0014] FIG. 11A to FIG. 11B The orientation and force profiles of the trajectories according to an embodiment of the present invention are shown.

[0015] Fig.12 A diagram showing a repaired working surface according to embodiments described herein is shown.

[0016] Fig.13 A repair strategy generation system according to embodiments described herein is shown.

[0017] Fig.14 A method of generating repair instructions in an embodiment of the present invention is shown.

[0018] Fig.15 It is the repair strategy generation system architecture.

[0019] Figure 16 to Figure 17 An example of a mobile device that may be used in the embodiments shown in the previous figures is shown.

[0020] Fig.18 is a block diagram of a computing environment that may be used in the embodiments shown in the previous figures.

[0021] 19 to 24 show images and analysis of defects as described in further detail in the Examples. DETAILED DESCRIPTION

[0022] Recent advances in imaging technology and computing systems have made the process of clearcoat inspection at production speeds feasible. Specifically, stereo deflectometry has recently been demonstrated to be able to provide images and locations of paint and clearcoat defects as well as spatial information (providing coordinate location information and defect classification) at appropriate resolution to allow subsequent automated spot repair.

[0023] As used herein, the term "vehicle" is intended to encompass a wide range of mobile structures that receive at least one coat of paint or varnish during manufacture. Although many of the examples herein relate to automobiles, it is expressly contemplated that the methods and systems described herein are also applicable to trucks, trains, boats (with or without motors), airplanes, helicopters, and the like.

[0024] The term "paint" is used herein to broadly refer to any of the various layers of a vehicle, such as electrocoat, filler, primer, paint, clearcoat, etc., that have been applied during the refinishing process. Additionally, the term "paint repair" relates to locating and repairing any visual artifacts (defects) on or in any of the paint layers. In some embodiments, the systems and methods described herein use a clearcoat as the target paint repair layer. However, the proposed systems and methods are applicable to any specific paint layer (electrocoat, filler, primer, paint, clearcoat, etc.) with little or no modification.

[0025] As used herein, the term "defect" refers to an area on a working surface that interferes with visual aesthetics. For example, many vehicles appear shiny or metallic after a paint job. "Defects" may include debris trapped within one or more of the various paint layers on a working surface. Defects may also include smudges in the paint, excess paint including streaks or drips, and indentations.

[0026] Paint repair is one of the last remaining steps in the vehicle manufacturing process that is still largely manual. Historically, this has been due to two main factors, the lack of adequate automated inspection and the difficulty of automating the repair process itself. Paint and clear coat repair standards are related to aesthetics as judged by the human eye (the dealer who receives the vehicle and the end customer who inspects the vehicle before purchase). Traditionally, robots have been designed to provide a "perfect" or highly "regular" repair, with crisp, defined edges and uniform cuts (see Figure 4B ). Unfortunately, this results in a repair that is highly visible to the human eye. The systems and methods described herein propose a way to increase the irregularity of the paint repair process so that the repaired defect blends better into the vehicle surface and is less detectable by the customer.

[0027] Figure 1 1 is a schematic diagram of a robotic paint repair system in which embodiments of the present invention are useful. The system 100 generally includes two units, a visual inspection system 110 and a defect repair system 120. The two systems can be controlled by motion controllers 112, 122, respectively, which can receive instructions from one or more application controllers 150. The application controllers can receive input or provide output to a user interface 160. The repair unit 120 includes a force control unit 124 that can be aligned with an end effector 126. As shown in FIG. Figure 1 As shown, the end effector 126 includes two tools 128, as further described in co-pending application Nos. 62 / 940,950 and 62 / 940,960. However, other arrangements are also expressly contemplated.

[0028] The first of the two major challenges, inspection of the vehicle 130 by the inspection unit 110, is interesting due to the nature of the potential problem domain. Generally speaking, the surface of interest is very large compared to the defect itself, where the difference is multiple orders of magnitude. This leads to a compromise between field of view and resolution when it comes to sensor selection. In addition, each paint layer of the finishing process (electrophoretic paint, primer, paint, clear coat, etc.) is different in its visual appearance, with specular reflectivity being particularly noteworthy. Highly specular surfaces (i.e., high gloss) pose unique imaging challenges. Together, these issues make inspection difficult. Recent advances in this field have been made over the past few years using increasing amounts of computing resources, leading to the availability of several commercial solutions. The presence of a sufficiently capable inspection system 110 is important for identifying defects repaired by the repair unit 120.

[0029] The current state of the art in vehicle paint repair is to use fine grinding and / or polishing systems to manually sand / polish defects with or without the aid of power tools while maintaining the desired finish (e.g., matching specular reflectivity in a clear coat). Professionals performing such repairs utilize many hours of training while using their senses to monitor the progress of the repair and make changes accordingly. This complex behavior is difficult to capture in a sensing-limited robotic solution.

[0030] Additionally, abrasive material removal is a pressure driven process, and many industrial manipulators typically operate naturally in an azimuth tracking / control regime and are optimized with regard to azimuth accuracy. The result is an extremely precise system with an extremely rigid error response curve (i.e., small azimuth displacements result in very large correction forces) that is inherently poor under force control (i.e., joint torque and / or Cartesian forces). Closed-loop force control methods have been used (with limited effectiveness) to address the latter along with newer (and more successful) force control flanges that provide soft (i.e., non-rigid) displacement curves that are more suitable for sensitive force / pressure driven processes. However, the issue of robust process strategy / control remains and is the focus of this work.

[0031] Figure 22 is a schematic diagram of a paint repair robot that can be used in embodiments of the present invention. In some embodiments, the robot repair unit 200 has a base 210, which can be fixed. In other embodiments, the base 210 can move in any of six dimensions, translation or rotation around an x-axis 212, a y-axis 214, and / or a z-axis 216. For example, the robot 200 may have a base 210 fixed to a track system that is configured to travel with the vehicle being repaired. Depending on the location of the defect, the robot 200 may need to move closer to or farther away from the vehicle, or may need to move higher or lower relative to the vehicle. The movable base 200 can make it easier to repair defects that are difficult to reach.

[0032] The robotic repair unit 200 has one or more tools 240 that can interact with the work surface. In one embodiment, the tool 240 may include a support pad 250, or another suitable abrasive tool. During the grinding operation, the tool 240 may have an abrasive disc or other suitable abrasive article, which is attached using an adhesive, hook and loop, clamp system, vacuum or other suitable attachment system. However, when the abrasive article moves in conjunction with the support pad 250 to which it is attached, the abrasive article is not necessarily considered to add additional degrees of freedom to the movement of the robotic repair unit 200. When mounted to the robotic repair unit 200, the tool 240 has the ability to be positioned within the degrees of freedom provided by the robotic repair unit 200 (6 degrees of freedom in most cases) and any other degrees of freedom (e.g., compliance force control 230 unit), whose reference system is depicted by axes 252, 254 and 256.

[0033] A support pad 250 is coupled to a tool 240 having tracks that provide some additional degrees of freedom. In most tools, a single degree of freedom is provided by a rotational axis with or without some offset. The support pad 250 reference frame is depicted by axes 252, 254, and 256. The tool 240 axis reference frame is depicted by axes 242, 244, and 246. The tool 240 is coupled to a force control 230 unit output. The force control flange 230 provides a soft (i.e., non-rigid) displacement curve. In most force control units, a single degree of freedom is provided by a sliding (prismatic) joint along an active axis. The force flange output reference frame is depicted by axes 222, 224, and 226. The force control 230 unit is coupled to flange 220. Movement of components 210, 220, 230, 240, and 250 can all be controlled using a robotic controller (e.g., Figure 1 ) and / or some auxiliary controls (e.g., application controller 150).

[0034] The orientation of a particular abrasive particle in the context of an abrasive article coupled to a support pad 250 can be calculated by mathematically transforming the position of the abrasive particle (as a fixed point in the support pad's reference frame) in time to some other desired reference using a series of relative transformations between the above-mentioned component reference frames (shown below in Equation 1 relative to the base 210 reference frame).

[0035]

[0036] The movement (M) of the support pad 250 reference frame relative to the fixed base 210 over time is affected by the movement of the flange 220 over time (e.g., robotic macromotion) as reflected in the first term, the movement of the force control 230 over time (e.g., compliant linear displacement) as reflected by the second term, the movement of the tool 240 over time (e.g., axis rotation) as reflected by the third term, and the rotation of the support pad relative to the tool 240 over time. The first, second, and third terms indicate the repair trajectory, as discussed in more detail below. The fourth term indicates the rotational movement of the support pad 250 (e.g., passive rotation on a random orbital setting). Describing and controlling complex motions is necessary to manage the repair process.

[0037] Figure 3 A method of robotic defect repair according to embodiments of the present invention is shown. Method 300 is an overview of how a robotic repair system repairs a defect according to at least some embodiments described herein.

[0038] For example, in block 310, from a robot controller (such as Figure 1 The application controller 150 in the robot receives the instructions. For example, the instructions include different components for the robotic repair unit (such as Figure 2 movement instructions of components 210, 220, 230, 240 and 250).

[0039] In block 320, the robotic motion controller moves the abrasive article mounted to the tool to a suitable position in preparation for engaging the defect. The defect location on the vehicle is known from the inspection system. Moving the abrasive article to a suitable position includes moving the article to the top of or near the defect. This orientation may be referred to as the nominal pose of the support pad.

[0040] In block 330, the abrasive article engages the defect. The engagement defect may include a sanding defect area, as indicated in block 332, or a polishing defect area, as indicated in block 334. The engagement defect also includes different repair parameters that change the support pad relative to the nominal pose, such as the speed of the support pad 332, the force applied to the support pad 334, the orientation shift of the support pad 336, and the final repair shape 338 resulting from the sanding and polishing operations.

[0041] In block 340, the defect area is cleaned. Cleaning may include wiping off any fluid used in sanding or polishing, as well as wiping off debris. After the cleaning step, the tool may reengage the defect, as indicated in block 342. For example, a dual-mount tool system may have both a sanding unit and a polishing unit available, so that after cleaning is achieved, the next repair step may be achieved.

[0042] In block 350, the defect area is inspected to determine if the repair is adequate. If additional repairs are required, the method 300 may receive new instructions, as indicated by arrow 360, and the method may repeat. Inspecting the defect repair may include capturing a post-repair image 352, which may be presented to a repair operator or saved as desired. The inspection may also include verifying the repair, as indicated in block 354, which may include comparing pre-repair and post-repair images, detecting whether the defect would be visible / perceptible to the human eye, or another suitable verification technique.

[0043] FIG. 4A to FIG. 4B is an image of a defect that may be present on a vehicle. Figure 4A A raised defect 410 on a working surface 400 is shown. The raised defect 410 may be caused by debris trapped beneath one or more paint layers on the working surface 400. Also noteworthy is the texture 420 on the working surface 400. When paint is applied to a working surface in a manufacturing environment, environmental disturbances (such as the movement or vibration of the vehicle, the movement of the circulating air, and the nature of the applied paint) result in a textured surface 420, which is often referred to as "orange peel" due to its appearance. Orange peel can also be intentionally added to the clearcoat surface so that different levels of orange peel texture and increase the aesthetics of different surfaces of the vehicle.

[0044] Unfortunately, repairs performed on a work surface having orange peel will destroy the texture and may produce highly visible repair areas, as shown in image 450 . Figure 4B The repair in 454 clearly shows a circular profile 458 where the abrasive article contacts the surface. In addition, the inner circle 454 is an artifact of the repair strategy. Between the center 452 of the repair area, a wave effect is shown due to the force profile, where the surface height decreases from the center 452 to the circle 454, rises again to a high point 456, and then decreases again to the edge 458. The force profile can be understood as being similar in shape to a "donut cake" where higher pressure is applied in the annular area within the perimeter of the disk. The desired repair blends the polished surface smoothly with orange peel wrinkles around the edge of the repair to produce a feathered result.

[0045] Generally speaking, it is desirable to repair any defects present in the paint "perfectly", however, the concept of a perfect repair is largely subjective and therefore cannot be given a formal definition. Informally, a "perfect" repair is one in which the end result is visually indistinguishable to the human eye from an otherwise defect-free area of ​​the work surface, while the concept of an optimal repair is considered to refer to the best repair possible given some starting conditions. For example, not all defects can be repaired to a perfect state. In addition, time is a key parameter for defect repair, as vehicle manufacturing is typically an assembly line process. An effective repair can then be characterized as a repair that renders the defective area indistinguishable in the shortest possible time.

[0046] The human eye is very good at noticing items that are "perfect" or "regular" in nature, as well as abrupt transitions in boundaries or textures. This sensitivity to abrupt visual boundary transitions requires control over the transitions between the repaired and unrepaired areas. For many reasons, including the nearly perfectly circular nature of the repair perimeter 458 and the annular central depression 452, such as Figure 4B The repair shown is highly visible. In the former case, such a transition is caused by a change in surface texture (i.e., from the original paint texture (commonly referred to as orange peel due to its appearance) to a generally smoother polished repaired area), while in the latter case, such a transition is caused by a change in the height of the surface caused by the distribution of material removal during the repair process. Generally speaking, it is impossible to remove defects without some local changes in surface texture and / or height. That is, there is practicality in methods that fully repair defects while leaving as few changes as possible, and the changes left make it difficult for the human eye to notice them. In this regard, we aim to maximize the hiding of defect repairs on finished articles. As described herein, hidden features are those features that reduce the visual conspicuity of the repair and are therefore less likely to be noticed by the human eye. Hidden features may include, for example, feathering around boundary edges, uneven repair areas, repair depth profiles, uneven cutting rates, etc.

[0047] A cutting modeling driven approach is proposed to derive a repair strategy that aims to reduce the resulting visual appearance of defect repairs while managing boundary transitions. It is important to note that during the repair of the original defect, care needs to be taken not to increase the perceived defects. In some embodiments, the repair strategy begins with identifying the desired characteristics of the cutting distribution (i.e., properties that adequately remove defects while also exhibiting other desired hidden characteristics (such as blending / feathering)) and finding the robot motion that leads to the distribution. Such an approach is possible by utilizing a predictive cutting model of abrasive / substrate interaction based on first principles and supplemented with measurement results. Further discussion is provided below with reference to Figure 5 .

[0048] The methods and systems herein operate under the assumption that the substrate is locally planar. This assumption does not result in a loss of generality, because a more complex model taking into account the geometry of the substrate enables the same method to be applied to local non-planar surfaces. Such models are possible and are contemplated in some embodiments herein. Generally speaking, defects may be present at any depth in any one of the paint layers, and may take various forms, including: pits, hairs, scratches, dust bumps, drips, fish eyes.

[0049] One basis for understanding material removal (and a good first approximation) is the well-known Preston equation for material removal (Equation 2 below), which expresses the instantaneous rate of material removal (cutting) as the product of pressure, relative velocity, and a constant (Preston's constant) that is defined in part by the complex interaction between the abrasive, substrate, and any cutting fluid.

[0050]

[0051] Here k p is a constant that depends on the abrasive / surface interaction, p is the pressure at any given point on the surface, and v rel is the relative velocity between the abrasive and the surface at that point. is the rate at which material is removed. According to Equation 2, and the abrasive and any cutting fluid are predetermined and remain constant for the duration of the defect repair (i.e., k p The domain-specific inputs to the instantaneous cut are the applied force (and resulting pressure) and the tool velocity (rotational, orbital, etc.), assuming that the robot is fixed. The total cut is determined via the integration of the instantaneous cut over time, which is distributed accordingly as a function of any macroscopic motion of the robot end effector.

[0052] In this regard, the removed material on the surface can be expressed as the integral of the pressure distribution on the abrasive media (resulting from the interaction with the substrate), scaled by the relative velocity between the abrasive and the substrate and Preston's constant. Here, we note that the pressure distribution depends strongly on the applied force, but also on the relative attitude of the abrasive / backup pad and the substrate (i.e., it is geometric in nature). Let

[0053] X(t): = [X p (t),X o (t)] Equation 3a

[0054] For a p ) and orientation (X o ) components of the robot repair path. Then the cut (x) at a point on the substrate can be expressed as:

[0055]

[0056] where x is the point of interest on the basis in some fixed reference frame, and is the distance from the tool center point to the point of interest, as expressed in a reference frame centered at the tool center point (from which the pressure and velocity profiles are defined). Equation 3b provides the material removed at a point on substrate x after executing a repair strategy involving the robot motion path (X(t)).

[0057] The pressure and relative velocity distribution terms are both the orientation of the tool (X o(t) ), and also a function of time (force can be controlled in time, which changes the pressure distribution, and velocity can also change in time with track and / or rotary tool speed). The output of these distributions is the pressure and velocity at the point of interest (x) at time t. The constant term k p Adjust between repairs as the disc life decreases. In our modeling below, we assume this is constant over the life of a single repair. Integrating these terms over time yields the total cut at that point. Therefore, the remaining steps are to find and generate the appropriate pressure distribution p(x,t) and macroscopic motion x(t) of the end effector tool, depending on the desired outcome. For the purpose of generating the repairs described above, both fully remove the defect while leaving as little visual impact as possible. Creating an irregular boundary between the repaired and unrepaired surfaces makes the repair less visible to human inspection.

[0058] Figure 5 Variables of interest in a robotic paint repair system are shown. The variables in the system 500 can be manipulated to account for irregularities in the robotic repair. The variables can generally be broken down into controllable variables 550 and dynamic constraints 560. The controllable variables 550 include variables that can be set by the robot controller. Dynamic constraints are caused by the controllable variables or are limits set on the robot itself, such as maximum acceleration, velocity, or applied force. Dynamic constraints are either generated by the controllable variables,

[0059] The trajectory variables 510 include controllable values ​​of position 502 and orientation 504. The position 502 of the support pad can be defined in coordinate space (x, y, z). The orientation 504 of the support pad can be defined by roll, pitch, and yaw (r, p, y). For example, the support pad can be positioned flush with the work surface, or can be tilted at a certain angle relative to the workpiece. The trajectory variables can be programmed to adjust during repair. For example, the support pad can move from a first position (x1, y1, z1) at a first time to a second position (x2, y2, z2) at a second time. Similarly, the orientation (r, p, y) can change from a first point in time to a second point in time. This results in a dynamic pose U(t) that changes over time. The pose is defined as the relative position and relative orientation of the support pad relative to the team surface of the work being done by the abrasive. The pose can position the support pad to be perfectly aligned with the work surface, or the pose can be offset to allow different types of contact with the part of the abrasive.

[0060] The tool variables 530 may also be changed during the repair. For example, the effective force 506 applied to the support pad may be changed over time. In addition, the rotational speed 508 of the support pad may also be changed. For example, in the case of a random orbital tool setting performing a circular repair, it may have a first rotational speed and / or force when moving between 0° and 90° of the circular repair motion, and a second speed and / or force within the range of 90° to 360° of the circular repair motion. In another example, it may have a first speed within the first two seconds of the motion, and a second speed within the last six seconds of the motion.

[0061] The robot motion combined with the rotational / orbital motion of the tool produces a relative velocity 566 between the abrasive medium and the substrate over time. However, we note that in practice, the robot's velocity (the macroscopic motion of the tool) is on a scale that is typically at least an order of magnitude slower than the rotational velocity 508, and is therefore typically negligible when calculating instantaneous cutting in the presence of a power tool. However, the dynamic pose U(t) can be considered if necessary. The combined controlled force 506 and trajectory variable 510 also produces a dynamic pressure 564 over time due to the abrasive / backup pad interaction.

[0062] In practice, tool variables cannot be changed instantly and are bounded by dynamic constraints. Therefore, any trajectory variables 510 and tool variables 530 must take into account the dynamic constraints of the tool and robot.

[0063] While trajectory variables 510 and tool variables 530 can be adjusted during a repair, geometric variables 520 are typically only exchanged between repairs. For example, support pads 522 have a given diameter that remains constant during a repair. Similarly, tracks 524 of the tool connected to support pads 522 are also set prior to a repair and are typically only changed between repairs. Base surface 526 is also limited because it is a function of the location of the defect on the vehicle body. Geometric variables 520 also contribute to experienced pressure 564 over time.

[0064] The trajectory variables 510, geometry variables 520, and instrumental variables 530 all together produce a set of repair characteristics 570 for a given repair. In some embodiments, it is expected that at least one repair characteristic 570 contributes in some form to the concealment of the repair. In some embodiments, multiple characteristics 570 contribute in some form to the concealment of the repair.

[0065] The repair boundary 572 generally refers to the perimeter of the repair. Many current robotic repairs are circular, such as Figure 4B . In other words, they have a constant radius extending from the repair center. In contrast, a non-circular boundary 572 refers to a boundary with a certain non-constant radius. Non-circular boundaries are a form of hiding because they are generally not very noticeable in many scenes. Some examples include rotationally symmetric (periodic) shapes, such as ellipsoids, stars, etc.; non-periodic and / or random shapes, without symmetry (rotational, radial, bilateral or in other forms); and general arbitrary (open) curves.

[0066] Specifically, we exploit rotational symmetry. An n-fold rotational symmetry (i.e., n-fold rotational symmetry about an origin or axis means that a rotation of 360° / n (30°, 60°, 90°, 120°, 180°, etc.) angles does not change the repair pattern. "1-fold" symmetry is not considered symmetric by this definition, since a rotation of 360° does not actually rotate the shape. Some examples include ellipses and lemniscates (2-fold), squares (4-fold), some petal-shaped curves, etc. A circle is actually infinitely fold (i.e., any rotation results in the same shape).

[0067] The restoration volume 574 refers to the volume of the working surface (i.e., substrate material) removed. In general, this can be specified as the total volume or more usefully as the volume distribution of the removed material (i.e., the cutting depth as a function of the substrate orientation). The above examples of hidden features naturally extend from the above restoration boundary cases to the restoration distribution, such as symmetry, etc. In addition, we consider the contour of the cut over some area of ​​interest. For example, the cutting depth as a function of the distance from the center of the restoration or the defect location. Here, the hidden form can be expressed as mathematical function properties, such as monotonicity, convexity, etc.

[0068] One example of a volumetric hiding strategy is feathering 576, which involves gradually reducing the depth of cut with distance from the defect. Feathering 576 or blending refers to a technique that makes the outer edge or border of the repair less visible and "blends" into the orange peel. Some examples of feathering are shown in Figures 19-23.

[0069] Other (hidden) characteristics 578 of the repair may also be introduced by varying the different controllable variables 550 .

[0070] With respect to pressure distribution, closed cell foam can be approximated as a spring damper for a single support pad. For example, if we assume that the support pads are made of foam and that compression (displacement) remains relatively low, we can assume a fixed pressure profile for each pad configuration and model the pressure distribution as described in Figure 6 below.

[0071] Fig. 6A 6F through 6F illustrate exemplary pressure responses that may be used in embodiments of the present invention. FIG. 6A to FIG. 6D All show how a tool 610 (such as a support pad) may interact with a work surface 600, and the resulting experienced pressure 620 along a cross section of the support pad. Schematic pressure distributions showing various support pad and substrate interface configurations are shown for a rigid support (6A) and a deformable support (6C). In the top image, when Figure 6B and Fig.6D When tilted to a certain non-zero offset, the support pad is aligned with the substrate plane. For all cases, the force is applied perpendicular to the support pad support. Figure 6B An example of can be modeled using equations 4 and 5 below.

[0072]

[0073] where u and v represent coordinate positions as expressed in a reference frame positioned at the center point of the abrasive, and are oriented with u pointing along the surface in an oblique direction.

[0074] conform to:

[0075] ∫∫p(u,v)dudv=f 工具 Equation 5

[0076] FIG. 7A to FIG. 7C Exemplary orientations that may be useful in embodiments of the present invention are shown. Fig. 6A As shown in FIG. 6E , the support pad may be angled relative to the work surface. FIG. 7A to FIG. 7C Shown are the different inclinations that a support pad may have relative to a surface. Fig. 7A A normal tilt 700 is shown, where the support pad is flush with the work surface. Figure 7B An outward tilt 720 is shown, and Figure 7CAn inward tilt 730 is shown. However, while each of the tilts 700, 720, and 730 are shown as being constant for an entire rotation of a circle, it is expressly contemplated that the orientation of the support pad may vary within a given rotation, thereby introducing desired irregularities into the repair.

[0077] Figure 8 The pressure profile of an orbital sander is shown. Several different tools can be used for grinding operations, including vibratory, rotary, orbital, and random orbital sanders. An orbital sander moves in a circular motion, such as Figure 8 As shown. Random orbital sanders also include passive rotation of the support pad. Due to the additional random rotation, random orbital sanders can leave fewer swirl patterns on the surface. For ease of understanding, Figure 8 The motion of an orbital sander is shown, however, a random orbital sander is expressly contemplated herein to provide an additional variable of passive rotational speed of the back-up pad.

[0078] Figure 8 Also shown is how the effective tool pressure distribution can be modeled for use in equations 3a and 3b above. The effective pressure resulting from the tool motion is considered to be the time average of the support pad pressure distribution over the tool motion range. For this example, the support plate pressure distribution is shown at the top right and the effective tool pressure distribution is shown at the bottom right for a (random) track tool with a track radius of one third the support plate radius.

[0079] Figure 8 The motion of an orbital sander 800 is shown, with a given disc pressure 840 and a resulting disc pressure 850. The orbital sander 800 has a known orbit radius 810, a support pad radius 820, and a resulting effective radius 830 of the affected workspace area. This results in a higher effective disc pressure at the center of the larger affected area, and a lower effective disc pressure near the edge. The effective disc pressure can be manipulated across the repair area to introduce hidden features into the repair properties. Higher pressures are associated with higher removed material. Moving the orbital sander over the repair surface can introduce hidden volume features and hidden boundary features into the repair.

[0080] FIG. 9A to FIG. 9B Velocity profiles for a rotary sander and an orbital sander are shown. Fig. 9A and Fig. 9B Schematic diagrams of characteristic abrasive velocities for rotary and orbital settings are shown in FIG. 9 , respectively. The velocity vectors are depicted by arrows 920 and 960, respectively. The rotary sanding unit has a radius 910 and is configured to rotate in a direction 940, thereby generating a velocity profile as shown by arrow 920. The outer edge of the rotary sander 900 has a higher velocity than the interior of the rotary sander.

[0081] Orbital sander 950 has a tool area 952 that is smaller than an effective tool area 972. Orbital sander 950 has an orbit radius 962 and rotates in direction 964 resulting in speed 960. Orbital sander 950 rotates in direction 974.

[0082] The robotic repair unit can know what abrasive tool and what grade of abrasive material is present on the tool for a given repair. Additionally, in some embodiments, the robotic repair unit also has an indication of the remaining life of the abrasive disc or the effectiveness of the abrasive. Knowing the details about the abrasive material and what kind of tool is attached to the robotic arm allows for even more control over the final repair. While Fig. 9A and Fig. 9B Two types of abrasive tools are shown in , but other abrasive tools are known and are contemplated for use in at least some embodiments.

[0083] FIG. 10A to FIG. 10C 1 shows a shape that can be used as the basis for a robotic repair trajectory in an embodiment of the present invention. Many current robotic repair units rely on circles for generating repairs, typically rotating an abrasive disk around a single point to remove a defect. As described above, and as Figure 4B As shown, this results in a repair that is "too regular" and noticeable to the human eye. Other shapes and designs have been explored to determine what other designs may be affected by the robotic repair unit without resulting in a circular repair area.

[0084] For example, the following curves can be used to produce sufficiently irregular and therefore hidden repair features: bean curves, butterfly curves, eight-leaf curves, ellipses, leaf-shaped lines (bifoliate, trifoliate, quadrifoliate, etc.), cardioid curves, oval curves, lemniscates, radial spirals, spirals (Archimedean spiral, Cotes spiral, Fermat spiral, hyperbola, etc.), super ellipses, trochoids (epitrochoid, hypotrochoid, epicycloid, hypocycloid, etc.), logarithmic and rose curves, etc.

[0085] A family of shapes of particular interest are the hypotrochoids and epitrochoids, which can be repaired by the robotic unit according to equations 7 and 8 below, using Fig. 10A Some exemplary shapes obtained in this manner are shown in FIG. Fig. 10B is shown in Table 1010.

[0086]

[0087]

[0088] Fig. 10C Another set of shapes is shown, referred to herein as "rose line" shapes 1020. Rose line shapes 1020 may be obtained using the following Equation 9:

[0089] r=a sin(nθ)+b Equation 9

[0090] The general rosette shapes 1020 are each shown with an associated n value. The coefficients (a, b) may be used to stretch or expand the shape, respectively.

[0091] Note that the rosette, along with the circle, ciliary curve, and epicycloid / hypocycloid, are special cases of epitrochoids and / or hypotrochoids (ie, can be represented by careful choice of a, b, and h).

[0092] FIG. 11A to FIG. 11B The repair trajectory and resulting material removal (cut) distribution according to an embodiment of the present invention are shown. As shown in the comparison between Table 1100 and Table 1150, combining the shape and tilt of the support pad can result in very different material removal profiles. Each shape in Table 1100 corresponds to a rosette with an n value of 2, 3, 4, or 5, and a tilt of -5°, 0°, or 5°. The resulting material removal profile is Fig. 11B As shown in Fig. 11B As shown, a Rosette (and therefore Epitrochoid / Hypotrochoid) based trajectory can focus abrasive removal on defect areas while also varying the removal volume on repair areas. This results in a better blending of the repair into the surrounding orange peel on the working surface via irregularities.

[0093] Such tracks offer significant hiding flexibility. As an example, Fig. 11B The cutting distribution 1152 shows defect modification (in areas smaller than the support pad diameter) and a smooth transition between the defect modification and the surrounding area. Fig. 11B The cut distribution 1154 shows a "donut cake" shaped restoration that exhibits smooth feathering and non-circular rotational symmetry (in this case 8-fold rotational symmetry) as hidden features.

[0094] Fig.12 A diagram of a repaired work surface according to embodiments described herein is shown. Work surface 1200 has an orange peel texture that is attempted to be blended with sanded areas 1250. An abrasive disc attached to a back-up pad has a center 120 and is movable along work surface 1200 as indicated by directions 1212 and 1214. Fig.12 In the embodiment shown, the back-up pad is attached to a random orbital sander that is also movable in the directions indicated by arrows 1222 and 1224 .

[0095] The repair track 1230 is shown as having an irregular shape that does not correspond to a regular polygon. The repair track 1230 has a plurality of curves and convex indentations, which results in the repair area 1250 having an irregular perimeter. Fig.12A support pad is shown with an inclined orientation, resulting in a pressure gradient applied over the area of ​​the working surface 1200 contacting the support pad at a given time. This also results in irregularities in the volume removed within the repair area.

[0096] Fig.13 A repair strategy generation system according to embodiments described herein is shown. The repair strategy generator 1300 receives information from one or more data sources and, based on the received information about defects present on a vehicle, generates a repair strategy for the defect. The goal of the repair strategy is to sufficiently remove the defect and sufficiently blend the repair surface with the orange peel texture of the vehicle so that visibility and detectability to the human eye are reduced.

[0097] The repair strategy generator 1300 has an abrasive product retriever 1302 in communication with an abrasive product database 1340. In one embodiment, the abrasive product database 1340 includes information about the current abrasive product 1342 on the active repair system. The abrasive product 1342 has a grade 1344 and other characteristics 1348, such as size. In some embodiments, the abrasive product database may also have disc life information 1346 about the abrasive product 1342. The abrasive product retriever 1302 can retrieve all of this information about the current abrasive 1342 and potential new abrasive products 1343 that can be replaced with the current abrasive product 1342.

[0098] The repair strategy generator 1300 also includes a defect retriever 1306. The defect retriever 1306 communicates with a defect database 1390. The defect database 1390 includes information about defects on the vehicle, including defects evaluated by the repair strategy generator 1300. A given defect may have one or more feature vectors 1391 that succinctly describe the characteristics of the defect via real numbers and / or classifications, and may have a coordinate location 1392 on the vehicle. For example, the defect database 1390 may also have a pre-repair image 1393 of the defect, such as taken by a vision system. The defect database 1390 may have other information 1394 about the defect of interest and information about other defects, such as similar defects, repair trajectories for repairing similar defects, and evaluations of those repairs.

[0099] The defect selector 1308 selects a defect or a series of defects to be repaired by the repair system. Not all defects need to be repaired. For example, if the defect on the surface of the vehicle is invisible to the potential customer, then repair may not be required. The defect selector 1308 selects each defect that needs to be repaired so that the defect repair strategy generator 1350 generates repair instructions. In one embodiment, repair instructions are generated for multiple defects one at a time, and each repair instruction is sent to the repair robot separately. In another embodiment, the defect repair strategy generator 1350 generates a single trajectory that addresses each of the identified defects for repair.

[0100] The repair strategy generator also communicates with a vehicle database 1395 using a vehicle data retriever 1310. The vehicle data retriever 1310 retrieves information about vehicles that undergo inspection and repair. The vehicle has a surface mesh 1396 that includes a discrete representation of the geometry of the vehicle surface. The vehicle may also include one or more features 1397, including make, model, color, number of paint layers and treatments on the doors, details or other modifications. The vehicle may also have one or more parameters 1398, including the presence of orange peel and texture on the surface. The vehicle database may also store other information 1399.

[0101] The repair strategy database 1320 includes information that can be helpful in evaluating defects and generating strategies for repair. The repair strategy database 1320 includes information about defects, including defect type 1322 and location 1324. The repair strategy database 1320 also includes information about orange peel 1326 that exists near the defect to be repaired. The repair strategy database 1320 may also include other information, including the area of ​​the defect on the working surface of the vehicle.

[0102] The defect repair strategy generator 1350 receives the information retrieved by the abrasive product retriever 1302, the defect retriever 1306, the defect selector 1308, the vehicle data retriever 1310, and the repair strategy database 1320 to generate repair instructions 1364 to be transmitted to the robotic repair cell.

[0103] Repair instructions 1364 include a shape 1376 that the robot end effector will form during repair. Shape 1376 can be a fixed point so that the tool remains fixed during repair. In another embodiment, shape 1376 includes moving the end effector so that the support pad and the abrasive product are dragged across the vehicle work surface in a certain shape. In one embodiment, shape 1376 may include a circle with a radius greater than the radius of the support pad. In another embodiment, shape 1376 may include an ellipse. In other embodiments, shape 1376 may also include a rosette, an epitrochoid, a hypotrochoid, or another polygon, such as a rectangle, a square. In some embodiments, shape 1376 may also include an irregular shape, such as a shape with curved or straight edges, concave or convex portions, or other features.

[0104] The defect repair strategy generator 1350 includes an orientation generator 1352 that generates a starting orientation of the abrasive tool for the repair trajectory. The generated starting orientation may be the same as the ending orientation of the generated trajectory, or it may be different.

[0105] The defect repair strategy generator 1350 also includes a trajectory force profile generator 1354 that generates a force 1374 to be applied to the support pad at each point along the trajectory. In some embodiments, the force 1374 may be applied uniformly at each time point during the repair trajectory. In some embodiments, the force 1374 may be applied uniformly to the support pad during the repair trajectory. In other embodiments, the force 1374 is different at different times 1370 during the repair, for example, in the repair, the force is initially higher at the repair time 1370a than at a later time 1370b. In addition, the end effector may tilt the support pad so that a gradient force 1374 is applied to at least a portion of the repair. The gradient force 1374 may change during the repair so that the tilt is different at time 1370a than at time 1370b.

[0106] The defect repair strategy generator 1350 also includes a trajectory speed profile generator 1358. The trajectory speed profile generator 1358 generates a speed 1378 at which the support pad moves at each point in the repair time 1370a-1370n. For example, in a circular trajectory, the end effector may move the support pad faster during a first portion of the rotation than during a second portion of the rotation.

[0107] In some embodiments, the defect repair strategy generator 1350 also includes an abrasive disc replacement decision device 1360. In some embodiments, the repair instructions 1364 may also include instructions for the repair robot to replace the abrasive disc or backup pad before the next defect repair begins. In one embodiment, the disc replacement decision device 1360 determines whether to replace the disc based on the disc life indication 1346. The disc life indication 1346 can be, for example, a measure of abrasive material remaining on the abrasive disc, or can be based on the number of repair cycles completed with a given abrasive article.

[0108] The repair instructions 1376 are sent to the repair unit 1380 by the repair instruction communicator 1362. The repair instruction communicator 1362 can communicate with the repair unit 1380 using a wired connection or a wireless connection. In some embodiments, the repair strategy generator 1300 is part of the repair unit 1380, so that the repair instruction communicator 1362 directly transmits instructions to the force controller and the end effector, which implements the repair.

[0109] For a series of time points 1370a-1370n, the repair instructions 1364 include the position 1372 of the support pad on the working surface within the shape 1376 of the repair trajectory, the force 1374 to be achieved by the force controller, and the velocity 1378 of the abrasive tool.

[0110] After the repair unit 1380 completes the repair, in some embodiments, the repair characteristics 1381 are collected. Some repair characteristics (such as perimeter 1382 and volume 1384) can be predicted based on the repair strategy generated by the defect repair strategy generator 1350 and verified as part of collecting the repair characteristics 1381. The repair characteristics can also include the degree of feathering 1386. For example, feathering 1386 should exist along the perimeter of the repair area. In some embodiments, feathering 1386 is approximately uniform across the perimeter. In some embodiments, other repair representations 1388 can also be captured, including post-repair imaging.

[0111] Fig.14 The method of generating repair instructions in an embodiment of the present invention is shown. The method 1400 can be implemented in one of the systems described in the embodiments of this document, or in another suitable system.

[0112] In block 1410, vehicle parameters are retrieved. The vehicle parameters relate to the vehicle being prepared for repair. The vehicle may have an associated surface mesh 1412. Retrieving vehicle parameters may also include retrieving properties regarding the paint applied to the vehicle, including layers, amounts, curing conditions, and hardness, as indicated in block 1414. Orange peel properties 1416 may also be retrieved for the entire vehicle or for localized portions surrounding one or more defects on the vehicle.

[0113] In block 1420, the defect is characterized. In some embodiments, a vehicle may have multiple defects, at least some of which are characterized for repair. Characterizing the defect may include defect type 1421, defect severity 1422, or location 1423 on the vehicle. For example, defect type 1421 may include stains or scratches. Defect severity 1422 may refer to the area on the working surface affected by the defect, the length of the defect, the height or depth of the defect, or another characteristic. The defect location may include a coordinate location on the working surface of the vehicle. Characterizing the defect may also include the depth 1424 of the defect relative to the working surface or the depth relative to the paint layer, such as whether the defect is located in the paint layer or in the varnish coating. Characterizing the defect may also include retrieving a pre-repair image 1426 of the working surface. Other features 1428 related to the defect may also be retrieved.

[0114] In block 1430, the defects are mapped to repair strategies. In one embodiment, mapping the defects to repair strategies includes a repair strategy generator, such as Fig.13 A repair strategy generator receives information about the vehicle and the defect and generates a repair trajectory for the defect based on the received information.

[0115] In box 1440, a path is generated for the repair strategy. The path may include one or more orientations 1442. In one embodiment, the orientation 1442 corresponds to a regular shape, including a circle, an ellipse, a rosette, an epitrochoid, or a hypotrochoid. In another embodiment, the orientation 1442 corresponds to an irregular shape. The shape may include a curvature or a straight line, a convex or concave portion, or other features. Generating a path in box 1440 may also include generating one or more orientations 1444. For example, the support pad may contact the working surface evenly so that a uniform pressure is applied to the surface of the support pad and to the working surface. In another embodiment, the support pad is tilted for at least a portion of the generated path. In some embodiments, the tilt may be inward or outward and may change during repair.

[0116] In block 1450, the generated path is time parameterized to generate a repair trajectory. Time parameterizing the path includes assigning velocities and accelerations along the generated path. Generating the time parameterization requires satisfying dynamic constraints, such as the maximum velocity and acceleration achievable by the end effector tool and the robot itself, and the jerk, as indicated in block 1452. Time parameterization may also include validating the constraints after generating the trajectory to ensure that the robot and end effector can achieve the trajectory.

[0117] In block 1460, a repair instruction including the time parameterization is sent to the robot to implement the defect. In one embodiment, the instruction may be automatically sent based on the completion of the time parameterization. In another embodiment, method 1400 repeats, as indicated by arrow 1470, and a repair trajectory is generated for a second defect. Alternatively, as shown in FIG. Fig.14 As indicated, method 1400 may be repeated for a series of defects and a complete trajectory set for vehicle repair before sending instructions.

[0118] Fig.15 15 is a block diagram of a defect detection and sorting system architecture. Remote server architecture 1500 illustrates one embodiment of an implementation of defect detection and sorting system 1510. As an example, remote server architecture 1500 may provide computing, software, data access, and storage services that do not require an end user to be aware of the physical location or configuration of the system delivering the services. In various embodiments, the remote server may deliver the services over a wide area network, such as the Internet, using an appropriate protocol. For example, the remote server may deliver applications over a wide area network, and they may be accessed through a web browser or any other computing component. Figures 1 to 8 The software or components shown or described herein and corresponding data may be stored on a server at a remote location. The computing resources in a remote server environment may be consolidated at a remote data center location, or they may be dispersed. The remote server infrastructure may deliver services through a shared data center, even though they appear to a user as a single access point. Therefore, the components and functions described herein may be provided from a remote server at a remote location using a remote server architecture. Alternatively, they may be provided by a conventional server that is installed directly or otherwise on a client device.

[0119] exist Fig.15 In the example shown, some items are similar to those shown in previous figures. Fig.15 Specifically illustrated is that the remediation strategy generation system may be located at a remote server location 1502. Thus, the computing device 1520 accesses those systems through the remote server location 1502. The operator 1550 may also access the user interface 1522 using the computing device 1520.

[0120] Fig.15 Another example of a remote server architecture is also depicted. Fig.15It is also contemplated that some elements of the systems described herein are disposed at a remote server location 1502, while other elements are not. By way of example, storage devices 1530, 1540, or 1560 or repair systems 1570 may be disposed at a location separate from location 1502 and accessed by a remote server at location 1502. Regardless of where they are located, they may be directly accessed by computing device 1520 over a network (wide area network or local area network), hosted at a remote site by a service, provided as a service, or accessed by a connection service residing at a remote location. Moreover, data may be stored in substantially any location and intermittently accessed by or forwarded to interested parties. For example, a physical carrier may be used instead of or in addition to an electromagnetic wave carrier.

[0121] It should also be noted that the elements of the system described herein or their portions can be disposed on a variety of different devices. Some of these devices include servers, desktop computers, laptop computers, embedded computers, industrial controllers, tablet computers or other mobile devices, such as handheld computers, cellular phones, smart phones, multimedia players, personal digital assistants, etc.

[0122] Figure 16 to Figure 17 An example of a mobile device that may be used in the embodiments shown in the previous figures is shown.

[0123] Fig.16 is a handheld device 16 that can be used as a user or client (e.g., as Fig.15 1520) in which the system (or portion thereof) of the present invention may be deployed. For example, the mobile device may be deployed in an operator compartment of the computing device 1520 for generating, processing, or displaying data. Fig.17 is another example of a handheld or mobile device.

[0124] Fig.16 A general block diagram of the components of a client device 1616 that can run some of the components shown and described herein is provided. The client device 1616 interacts with these components, or runs some components and interacts with some components. In the device 1616, a communication link 1613 is provided, which allows the handheld device to communicate with other computing devices, and in some embodiments provides a channel for automatically receiving information such as by scanning. Examples of communication links 1613 include allowing communication through one or more communication protocols (such as wireless services for providing cellular access to the network), and protocols that provide local wireless connections to the network.

[0125] In other examples, the application may be received on a removable secure digital (SD) card connected to the interface 1615. The interface 1615 and the communication link 1613 communicate with the processor 1617 (which may also be embodied as a processor) along a bus 1619, which is also connected to the memory 1621 and the input / output (I / O) components 1623, as well as the clock 1625 and the position system 1627.

[0126] In one embodiment, I / O components 1623 are provided to facilitate input and output operations, and the device 1616 may include input components (such as buttons, touch sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometers, orientation sensors) and output components (such as display devices, speakers, and / or printer ports). Other I / O components 1623 may also be used.

[0127] Clock 1625 illustratively includes a real-time clock component that outputs time and date. It can also provide timing functions for processor 1617.

[0128] Illustratively, location system 1627 includes components for outputting the current geographic location of device 1616. This may include, for example, a global positioning system (GPS) receiver, a LORAN system, a dead reckoning system, a cellular triangulation system, or other positioning system. It may also include, for example, mapping software or navigation software that generates desired maps, navigation routes, and other geographic functions.

[0129] Memory 1621 stores operating system 1629, network settings 1631, applications 1633, application configuration settings 1635, data repository 1637, communication driver 1639, and communication configuration settings 1641. Memory 1621 may include all types of tangible volatile and non-volatile computer-readable memory devices. It may also include computer storage media (described below). Memory 1621 stores computer-readable instructions that, when executed by processor 1617, cause the processor to perform computer-implemented steps or functions according to the instructions. Processor 1617 may also be activated by other components to facilitate its functions.

[0130] Fig.17 The device is shown to be a smartphone 1671. The smartphone 1671 has a touch-sensitive display 1673 that displays icons or tiles or other user input mechanisms 1675. The mechanisms 1675 can be used by a user to run applications, make calls, perform data transfer operations, etc. In general, smartphones 1671 are built on mobile operating systems and provide more advanced computing capabilities and connectivity than feature phones.

[0131] Note that other forms of device 1616 are possible.

[0132] Fig.18 is a block diagram of a computing environment that may be used in the embodiments shown in the previous figures.

[0133] Fig.18 is an example of a computing environment in which elements or (for example) portions of the systems and methods described herein may be deployed. Fig.18 , an exemplary system for implementing some embodiments includes a general purpose computing device in the form of a computer 1810. Components of the computer 1810 may include, but are not limited to, a processing unit 1820 (which may include a processor), a system memory 1830, and a system bus 1821 that couples various system components including the system memory to the processing unit 1820. The system bus 1821 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The memories and programs described with respect to the systems and methods described herein may be deployed in Fig.18 in the corresponding part of .

[0134] Computer 1810 generally includes various computer-readable media. Computer-readable media can be any available media that can be accessed by computer 1810, and includes both volatile / non-volatile media and removable / non-removable media. By way of example and not limitation, computer-readable media may include computer storage media and communication media. Computer storage media is different from and does not include modulated data signals or carrier waves. It includes hardware storage media, which includes both volatile / non-volatile and removable / non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical disk storage devices, cassettes, tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be used to store desired information and can be accessed by computer 1810. Communication media can be embodied as computer-readable instructions, data structures, program modules or other data in a transmission mechanism, and include any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

[0135] The system memory 1830 includes computer storage media in the form of volatile and / or nonvolatile memory, such as read-only memory (ROM) 1831 and random access memory (RAM) 1832. A basic input / output system 1833 (BIOS), containing the basic routines that help transfer information between elements within the computer 1810, such as during startup, is typically stored in ROM 1831. RAM 1832 typically contains data and / or program modules that are immediately accessible to and / or currently being operated on by the processing unit 1820. By way of example and not limitation, Fig.18 Operating system 1834 , application programs 1835 , other program modules 1836 , and program data 1837 are shown.

[0136] The computer 1810 may also include other removable / non-removable and volatile / non-volatile computer storage media. By way of example only, Fig.12 Shown are hard disk drive 1841 that reads and writes to non-removable, non-volatile magnetic media, non-volatile magnetic disk 1852, optical disk drive 1855, and non-volatile optical disk 1856. Hard disk drive 1841 is typically connected to system bus 1821 through a non-removable memory interface, such as interface 1840, while optical disk drive 1855 is typically connected to system bus 1821 by a removable memory interface, such as interface 1850.

[0137] Alternatively or in addition, the functions described herein may be performed at least in part by one or more hardware logic components. For example, but not limited to, exemplary types of hardware logic components that may be used include field programmable gate arrays (FPGAs), application specific integrated circuits (e.g., ASICs), application specific standard products (e.g., ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), etc.

[0138] Discussed above and in Fig.18 The drives and their associated computer storage media shown in the figure provide storage of computer readable instructions, data structures, program modules and other data for the computer 1810. Fig.18 , for example, hard disk drive 1841 is shown as storing operating system 1844, application programs 1845, other program modules 1846, and program data 1847. Note that these components may be the same as or different from operating system 1834, application programs 1835, other program modules 1836, and program data 1837.

[0139] A user may enter commands and information into the computer 1810 through input devices such as a keyboard 1862, a microphone 1863, and a pointing device 1861 such as a mouse, trackball, or touch pad. Other input devices (not shown) may include a joystick, a game controller, a satellite dish, a scanner, or the like. These and other input devices are typically connected to the processing unit 1820 through a user input interface 1860 coupled to the system bus, but may also be connected through other interface and bus structures. A visual display 1891 or other type of display device is also connected to the system bus 1821 via an interface such as a video interface 1890. In addition to a monitor, the computer may also include other peripheral output devices such as speakers 1897 and a printer 1896, which may be connected through an output peripheral interface 1895.

[0140] The computer 1810 operates in a networking environment using logical connections, such as a local area network (LAN) or a wide area network (WAN) to one or more remote computers, such as the remote computer 1880 .

[0141] When used in a LAN networking environment, the computer 1810 is connected to the LAN 1871 through a network interface or adapter 1870. When used in a WAN networking environment, the computer 1810 typically includes a modem 1872 or other means for establishing communications over the WAN 1873, such as the Internet. In a networking environment, program modules may be stored in the remote memory storage device. Fig.18 It is shown that, for example, remote application programs 1885 can reside on remote computer 1880.

[0142] A repaired region on a work surface is presented. The repaired region includes a repair boundary. Within the repair boundary, the work surface has a repair texture, and outside the repair boundary, the work surface has a work surface texture. The repaired region also includes a repair depth distribution within the repair boundary and hidden features. The repaired region is the result of performing robotic repair on the work surface to remove defects.

[0143] The repaired area may be the result of a grinding operation on the working surface. The grinding operation may have removed the working surface texture from a portion of the repaired area.

[0144] The repair boundary may be rotationally symmetric. The repair boundary may have an n-fold rotational symmetry, where n is finite and greater than or equal to 2. The repair boundary may have an n-fold rotational symmetry, where n is greater than or equal to 2 and less than or equal to 25. The repair boundary may have an n-fold rotational symmetry, where n is greater than or equal to 3 and less than or equal to 25. The repair boundary may have an n-fold rotational symmetry of the repair boundary, where n is greater than or equal to 3 and less than or equal to 8.

[0145] The repair boundary may be an epitrochoid or a hypotrochoid.The repair boundary may be defined as having an a parameter and an h parameter, and both the a parameter and the h parameter are non-zero.

[0146] The repair region may be implemented such that the path of the performed robotic repair is an epitrochoid or a hypotrochoid. A path is defined as having an a parameter and an h parameter, and both the a parameter and the h parameter are non-zero.

[0147] Repair boundaries can be asymmetric.

[0148] The repair boundary can be one sixth of the effective tool radius.

[0149] The repair boundary can be one quarter of the effective tool radius.

[0150] The repair boundary can be one third of the effective tool radius.

[0151] The repair boundary can be one-half of the effective tool radius.

[0152] The repaired area may be implemented such that the depth of cut decreases monotonically radially outward from the center of the repaired area.

[0153] The repaired area may be implemented such that defect remnants remain within the repaired area.

[0154] Repair areas may include feathering.

[0155] The repair area can be blended into the working surface.

[0156] The repair area may not be obvious to the person.

[0157] The repair boundary can have either a convex portion or a convex portion.

[0158] The repair boundary may include straight lines.

[0159] The repair region may be implemented such that the repair depth profile includes a first depth at a first point and a second depth at a second point relative to the working surface. The first point and the second point may be within the repair boundary.

[0160] The repair region may be implemented such that the repair depth profile includes a first depth at a first point and a second depth at a second point relative to the working surface. The first point and the second point may be within the repair boundary.

[0161] The repair boundary may include a first cutting contour at a first point and a second cutting contour at a second point. The first cutting contour may be different from the second cutting contour.

[0162] The repair region may be implemented such that the first point is closer to the repair boundary than the second point. The first depth may be greater than the second depth.

[0163] A method for robotically repairing a defect on a work surface is proposed. The method includes receiving a surface mesh of the work surface. The method also includes receiving a location of the defect. The location is a coordinate location corresponding to a point on the surface mesh. The method also includes generating a repair map for repairing the defect. The repair map includes a repair orientation and a repair force at the repair orientation. The method also includes generating a time parameterization of the repair map. The method also includes sending a repair instruction to a repair robot. The repair instruction includes the repair map and the time parameterization. The repair robot includes a tool configured to contact the defect and grind the work surface at the defect location. The repair orientation includes the orientation of the tool, and the force includes the force applied by the tool on the work surface.

[0164] The method can be implemented so that the tool is coupled to a support pad, which is coupled to the abrasive article. The tool can have a repair orientation in the repair position. The repair orientation can include the orientation of the tool relative to the working surface. The orientation can be tilted outward and tilted inward or flush with the working surface.

[0165] The method may be implemented such that the repair position is a first repair position and the repair orientation is a first repair orientation. The repair instructions may also include the tool being in the first repair position, having a first applied repair force, and being in the first repair orientation at a first time, and the tool being in the second repair position, having a second applied repair force, and being in the second repair orientation at a second time.

[0166] The method may be implemented such that the first repair orientation is different from the second repair orientation.

[0167] The method may be implemented such that the first repair orientation is the same as the second repair orientation.

[0168] The method may be implemented such that the first repair orientation is the same as the second repair orientation.

[0169] The method may be implemented such that the first repair orientation is different from the second repair orientation.

[0170] The method may be implemented such that the first applied repair force is the same as the second applied repair force.

[0171] The method may be implemented such that the first applied repair force is different from the second applied repair force.

[0172] The method may be implemented such that the tool has a moving part, and wherein the repair instructions include a tool speed of the moving part.

[0173] The method may be implemented such that the repair instructions further include a first tool speed at a first time and a second tool speed at a second time. The first tool speed and the second tool speed may be the same.

[0174] The method may be implemented such that the repair instructions further include a first tool speed at a first time and a second tool speed at a second time. The first tool speed and the second tool speed may be different.

[0175] The method may be implemented such that the tool is a rotary sander and the tool speed is the rotational speed.

[0176] The method may be implemented such that the tool is a vibrating sander and the tool speed is the vibration rate.

[0177] The method may be implemented such that the tool is an orbital sander having orbits and the tool speed is the rotational orbit speed.

[0178] The method may be implemented such that the tool is a random orbital sander having an orbit and the tool speed is the rotational orbital speed.

[0179] The method may be implemented such that the tool is a random orbital sander having an axis of motion and the tool speed is an axial speed.

[0180] The method may be implemented such that the repair map comprises an ordered plurality of locations, and wherein the temporal parameterization comprises the tool passing through the ordered plurality of locations in sequence.

[0181] The method may be implemented such that the ordered plurality of orientations forms an open path such that the starting orientation is different from the ending orientation.

[0182] The method may be implemented such that the ordered plurality of orientations forms a closed path such that the starting orientation is the same as the ending orientation.

[0183] The method may be implemented such that a plurality of orientations causes the tool to trace out a shape.

[0184] The method may be implemented such that the shape is a regular shape selected from the group consisting of a circle, an ellipse, a polygon, a rosette, an epitrochoid, or a hypotrochoid.

[0185] The method may be implemented such that the shape is an irregular shape having convex portions, concave portions, straight portions, or curved portions.

[0186] The method may be implemented such that the repair instructions include commands for the repair robot to execute the repair instructions.

[0187] The method may be implemented such that the repair instructions also include a command to exchange the abrasive article for a new abrasive article.

[0188] The method may be implemented such that the command is based on a received abrasive article parameter.The abrasive article parameter may be an abrasive grade or a remaining life of the abrasive article.

[0189] The method may be implemented such that a repair area including an area on the working surface abraded by the tool is larger than an area of ​​a support pad coupled to the tool.

[0190] The method may be implemented such that the repair region has a grinding depth profile across the repair region, and wherein the grinding depth profile is non-uniform across the repair surface.

[0191] The method may be implemented such that a first grinding depth at a first point relative to the working surface is shallower than a second grinding depth at a second point.

[0192] A repair robot for repairing defects on a work surface is proposed. The repair robot has a robot arm having a base at a first edge and a flange at a second end. The repair robot also has a force control coupled to the flange. The repair robot also has an end effector coupled to the force control. The repair robot also has a tool coupled to the end effector. The repair robot also has a support pad coupled to the tool. The support pad is also coupled to an abrasive disc. The repair robot also has a robot controller configured to cause the power arm to move the tool to an orientation above the defect and to execute a repair trajectory in response to a received repair instruction. The repair trajectory includes a repair path that the tool follows on the work surface. The repair path includes a plurality of orientations, and at each of the plurality of orientations includes a tool orientation, a tool force, and a tool speed. The repair robot also has computer-implemented instructions that, when executed, cause the repair robot to execute the received repair instruction.

[0193] The repair robot may also be implemented such that a first tool orientation at a first tool position is different from a second tool orientation at a second tool position.

[0194] The repair robot may also be implemented such that a first tool force at a first tool orientation is different from a second tool force at a second tool orientation.

[0195] The repair robot may also be implemented such that a first tool speed at a first tool orientation is different from a second tool speed at a second tool orientation.

[0196] The repair robot may also be implemented such that the repair path comprises a regular shape.

[0197] The repair robot can also be implemented so that the regular shape is a circle, an ellipse, a polygon, a rosette, an epitrochoid or a hypotrochoid.

[0198] It is also possible to implement the repair robot such that the repair path comprises an irregular shape having convex or concave portions.

[0199] It is also possible to implement the repair robot such that the repair path has rotational symmetry.

[0200] It is also possible to implement the repair robot such that the repair path has no rotational symmetry.

[0201] The repair robot can also be implemented so that the repair path is asymmetric.

[0202] The repair robot may also be implemented such that the abrasive disc is removable and the repair instructions include instructions to remove the current abrasive disc and place a new abrasive disc on the back-up pad.

[0203] The repair robot may also be implemented such that the robot controller generates repair instructions based on defect characteristics. The defect characteristics are defect type, defect size, or defect location on the work surface.

[0204] It is also possible to implement a repair robot such that the robot controller generates repair instructions based on abrasive disc parameters. The abrasive disc parameters are grind grade or remaining disc life.

[0205] The repair robot can also be implemented such that the robot controller generates repair instructions based on a working surface parameter. The working surface parameter is a paint parameter or a defect depth.

[0206] The repair robot may also be implemented such that the working surface is a vehicle and wherein the paint parameter is the number of paint coats, the type of paint coats or the paint hardness.

[0207] It is also possible to implement a repair robot so that the vehicle is a car.

[0208] The repair robot can also be implemented so that the base is fixed relative to the vehicle during the repair process.

[0209] The repair robot may also be implemented such that the base is moved relative to the vehicle during the repair process.

[0210] A repair robot may also be implemented so that both the base and the car are moved during the repair process.

[0211] It is also possible to implement the repair robot such that the tool is a vibrating sander and the tool speed is the vibration rate of the vibrating sander.

[0212] The repair robot may also be implemented such that the tool is a rotary sander and the tool speed is the rotation speed.

[0213] The repair robot may also be implemented such that the tool is an orbital sander having orbits, and the tool speed is the orbital rotation speed.

[0214] The repair robot may also be implemented such that the tool is a random orbital sander having an orbit and the tool speed is the orbital rotation speed.

[0215] The repair robot may also be implemented such that the tool is a random orbital sander having an axis and the tool speed is the axial speed.

[0216] A repair instruction for a robotic repair unit is presented. The repair instruction includes a starting orientation of a tool coupled to the robotic repair unit. The tool includes an abrasive article configured to contact and abrade a work surface. The repair instruction also includes a repair path, the repair path including a first orientation of the tool at a first time and a second orientation of the tool at a second time. The repair instruction also includes a force profile, the force profile including a first applied force by the robotic repair unit on the abrasive article at a first time, and a second applied force by the robotic repair unit on the abrasive article at a second time. The repair instruction may also have a tool speed profile, the tool speed profile including a first tool speed at a first time and a second tool speed at a second time. The repair instruction may also have a computer-readable instruction, which, when executed, causes the repair robot to execute the received repair instruction.

[0217] The repair instructions may also have an ending orientation of the tool, where the ending orientation is different than the starting orientation.

[0218] The repair instructions may be implemented such that the working surface includes a defect, and the repair instructions are configured to reduce a visual appearance of the defect on the working surface.

[0219] The repair instructions may be implemented such that the perimeter of the repair area is blended into the working surface. The blending may include feathering along the edge of the repair area. The blending may include grinding the repair depth profile within the repair area of ​​the working surface.

[0220] The repair instructions may be implemented such that a first repair depth at a first location is less than a second repair depth at a second location. The first location may be closer to the repair perimeter than the second location.

[0221] The repair instructions may be implemented such that the abrasive article has an abrasive article region, and wherein the repair region is larger than the abrasive article region.

[0222] The repair instructions may be implemented such that the repair area is twice the area of ​​the abrasive article.

[0223] The repair instructions may be implemented such that the size of the repair area is twice the diameter of the abrasive article.

[0224] The repair instruction may be implemented such that the second orientation is the same as the first orientation.

[0225] The repair instructions may be implemented such that the second orientation is different from the first orientation.

[0226] The repair instructions may be implemented such that the first force is different from the second force.

[0227] The repair instructions may be implemented such that the first tool speed is different from the second tool speed.

[0228] The repair instructions may also include a first tool orientation at a first time and a second tool orientation at a second time. The first tool orientation and the second tool orientation may be selected from the group consisting of: flush with the work surface, tilted outwardly relative to the work surface, and tilted inwardly relative to the work surface.

[0229] The repair instructions may be implemented such that the first tool orientation is different than the second tool orientation.

[0230] The repair instructions may be implemented such that the repair path includes an open path such that the starting orientation is different from the ending orientation.

[0231] The repair instructions may be implemented such that the repair path comprises a closed path such that the starting orientation is the same as the ending orientation.

[0232] The repair instructions may be implemented such that the repair path comprises a regular shape, and wherein the regular shape comprises a circle, an ellipse, a polygon, an epitrochoid, a hypotrochoid, or a rosette.

[0233] The repair instructions can be implemented so that the repair path has rotational symmetry.

[0234] The repair instructions may be implemented such that the repair path is asymmetric.

[0235] The repair instruction may be implemented such that the repair path is an irregular path. The irregular path has a concave portion or a convex portion.

[0236] The repair instructions may be implemented such that the starting orientation includes the tool substantially in contact with the defect.

[0237] The repair instructions may be implemented such that the work surface is a vehicle.

[0238] The repair instructions may be implemented so that the repair instructions are for a repair robot that remains stationary during repair. The work surface may be stationary during repair. The work surface may be movable during repair.

[0239] The repair instructions may be used for a repair robot that moves during repair. The work surface may be stationary during repair. The work surface may move during repair.

[0240] The repair instructions may be implemented such that the tool is a vibrating sander, and the first speed is a first vibration rate, and the second speed is a second vibration rate.

[0241] The repair instructions may be implemented such that the tool is a rotary sander, the first speed is a first rotational speed, and the second speed is a second rotational speed.

[0242] The repair instructions may be implemented such that the tool is an orbital sander having an orbit, and wherein the first speed is a first orbital rotational speed, and wherein the second speed is a second orbital rotational speed.

[0243] The repair instructions may be implemented such that the tool is a random orbital sander having an orbit, and wherein the first speed is a first orbital rotational speed, and wherein the second speed is a second orbital rotational speed.

[0244] The repair instructions may be implemented such that the tool is a random orbital sander having an axis of motion, and wherein the first speed is a first axial speed and the second speed is a second axial speed.

[0245] A repair strategy generation system for grinding defects on a work surface is presented. The repair strategy generation system includes a work surface retriever configured to retrieve a surface mesh associated with the work surface. The system also includes a defect retriever configured to retrieve defect characteristics of the defect. The system also includes a repair trajectory generator configured to generate a repair trajectory for grinding the defect based on the defect characteristics. The repair trajectory generator includes a path generator configured to generate a path for execution by a tool on a robotic repair unit; a force profile generator configured to generate a force profile for the tool to apply on an abrasive article coupled to the tool; and a time parameterizer configured to associate a velocity with the generated path so that at a first time, the tool is in a first orientation and applies a first force, and at a second time, the tool is in a second orientation and applies a second force. The system also includes an instruction communicator configured to transmit the generated repair trajectory to the robotic repair unit for execution. The system also includes a controller having a processor and computer implemented instructions that, when executed, cause the working surface retriever to retrieve a surface mesh, the defect retriever to retrieve defect characteristics, the repair trajectory generator to generate a repair trajectory, and the instructing the communicator to transmit the generated repair trajectory.

[0246] The repair strategy generation system may further include an abrasive product retriever configured to retrieve abrasive article properties regarding the abrasive article.

[0247] The repair strategy generation system may be implemented such that the abrasive article characteristic is the grinding grade or the remaining abrasive disc life.

[0248] The repair strategy generation system may further include an abrasive disc replacement decision generator configured to generate an abrasive article replacement command based on the abrasive article characteristic. The command communicator transmits the abrasive article replacement command using the generated repair trajectory.

[0249] The repair strategy generation system may be implemented such that the instruction communicator also transmits a repair initiation command for the robotic repair unit to execute the repair trajectory upon receipt.

[0250] The repair strategy generation system may be implemented such that the instruction communicator also transmits a repair initiation command for the robotic repair unit to execute an abrasive article replacement command prior to executing the repair trajectory.

[0251] The repair strategy generation system may be implemented such that the defect characteristic is a pre-repair image of the defect.

[0252] The repair strategy generation system may be implemented such that the defect characteristic is a defect type, a defect location on the working surface, a defect depth relative to a surface of the working surface, or a defect size parameter.

[0253] The repair strategy generation system may be implemented such that a repair trajectory is generated based at least in part on past defect repairs.

[0254] The repair strategy generation system may be implemented such that the working surface retriever also retrieves working surface characteristics.

[0255] The repair strategy generation system may be implemented such that the working surface is a vehicle, and wherein the working surface characteristic is an orange peel characteristic.

[0256] The repair strategy generation system may be implemented such that the working surface properties are paint properties.

[0257] The repair strategy generating system may be implemented such that the paint characteristic is paint hardness, paint color, paint layer thickness, number of paint layers, or paint type.

[0258] The repair strategy generation system may be implemented such that the defect characteristic is the depth of the defect within the paint.

[0259] The repair strategy generation system may be implemented such that the first orientation and the second orientation are the same.

[0260] The repair strategy generation system may be implemented such that the first orientation and the second orientation are different.

[0261] The repair strategy generating system can be implemented so that a first area of ​​the abrasive article contacting the working surface does not overlap with a second area of ​​the abrasive article contacting the working surface. The first area can correspond to the abrasive article in a first orientation, and the second area can correspond to the abrasive article in a second orientation.

[0262] The repair strategy generating system may be implemented such that the first applied force is different from the second applied force.

[0263] The repair strategy generating system may be implemented such that the first applied force is the same as the second applied force.

[0264] The repair strategy generation system can be implemented such that the tool has an orientation relative to the working surface such that a force profile is applied along an area of ​​the abrasive article that contacts the working surface.

[0265] The repair strategy generation system can be implemented so that the orientation is tilted outward, tilted inward, or flush with the work surface.

[0266] The repair strategy generation system may be implemented such that the repair path is an open path such that the starting and ending orientations of the tool are different.

[0267] The repair strategy generation system may be implemented such that the repair path is a closed path such that the starting position and the ending position are the same.

[0268] The repair strategy generation system may be implemented such that the repair path is circular, elliptical, polygonal, rosette-shaped, epitrochoid-shaped, or hypotrochoid-shaped.

[0269] The repair strategy generation system can be implemented so that the repair path is an irregular shape.

[0270] The repair strategy generation system may be implemented such that the repair path includes a convex portion.

[0271] The repair strategy generation system may be implemented such that the repair path includes a concave portion.

[0272] The repair strategy generation system may be implemented such that the repair path includes straight portions.

[0273] A repair strategy generation system can be implemented such that the repair path has rotational symmetry.

[0274] The repair strategy generation system can be implemented such that the repair path is asymmetric.

[0275] The repair strategy generation system may be implemented such that the tool is a vibrating sander and the tool speed is the vibration rate.

[0276] The repair strategy generation system may be implemented such that the tool is a rotary sander and the tool speed is the rotational speed.

[0277] The repair strategy generation system may be implemented such that the tool is an orbital sander having orbits, and the tool speed is the orbital rotation speed.

[0278] The repair strategy generation system may be implemented such that the tool is a random orbital sander having an orbit and the tool speed is the orbital rotation speed.

[0279] The repair strategy generation system may be implemented such that the tool is a random orbital sander having an axis of motion and the tool speed is an axial speed.

[0280] The repair strategy generation system may be implemented such that the tool is coupled to a back-up pad that is coupled to the adhesive article.

[0281] A method for generating a repair trajectory of a work surface is proposed. The method includes retrieving work surface parameters using a work surface parameter retriever. The method also includes retrieving defect parameters of a defect on the work surface using a defect parameter retriever. The defect parameters include the location of the defect on the work surface. The method also includes generating a repair path for the defect using a repair path generator. The repair path includes a repair position, a repair force, and a repair orientation of a tool for contacting the work surface. The method also includes using a time parameterizer to time parameterize the repair path to generate a repair trajectory. The method is implemented by a repair robot controller having a processor and stored computer-implemented instructions, which, when executed, causes the controller to complete the steps of retrieving work surface parameters, retrieving defect parameters, generating a repair path, and time parameterizing the repair path.

[0282] The method may further include transmitting the repair trajectory to the repair robot using the command communicator.

[0283] The method may also include checking the trajectory for compliance with dynamic constraints of the repair robot. The dynamic constraints include maximum acceleration, maximum velocity, or jerk.

[0284] The method may be implemented such that the trajectory includes a first time and a second time. The repair orientation may be a first repair orientation, the repair force is a first repair force, and the repair orientation is a first repair orientation. At the first time, the tool is in the first repair orientation, in the first orientation, with the first repair force. At the second time, the tool is in the second repair orientation, in the second repair orientation, with the second repair force.

[0285] The method may be implemented such that the first repair orientation is the same as the second repair orientation.

[0286] The method may be implemented such that the first repair orientation is different from the second repair orientation.

[0287] The method may be implemented such that the first repair force is the same as the second repair force.

[0288] The method may be implemented such that the first repair force is different from the second repair force.

[0289] The method may be implemented such that the first repair orientation is the same as the second repair orientation.

[0290] The method may be implemented such that the first repair orientation is different from the second repair orientation.

[0291] The method may be implemented such that the tool has a moving part. The moving part has a first speed at a first time and a second speed at a second time.

[0292] The method may be implemented such that the first speed is different from the second speed.

[0293] The method may be implemented such that the first speed is the same as the second speed.

[0294] The method may be implemented such that the repair tool is a vibrating sander and the first tool speed and the second tool speed are a first vibration rate and a second vibration rate.

[0295] The method may be implemented such that the repair tool is a rotary sander and the first tool speed and the second tool speed are a first rotation rate and a second rotation rate.

[0296] The method may be implemented such that the repair tool is an orbital sander having orbits, and the first tool speed and the second tool speed are a first rotational rate and a second rotational rate.

[0297] The method may be implemented such that the repair tool is a random orbital sander having an axis of motion, and the first tool speed and the second tool speed are a first axial rate of motion and a second axial rate of motion.

[0298] The method may be implemented such that the repair orientation is flush with respect to the working surface, angled outwardly with respect to the working surface, or angled inwardly with respect to the working surface.

[0299] The method may be implemented such that the tool is coupled to a back-up pad, and wherein the back-up pad is removably coupled to the abrasive article, and the abrasive article directly contacts the working surface.

[0300] The method may be implemented such that the method further comprises retrieving abrasive article characteristics and generating a replace abrasive article command based on the abrasive article characteristics.

[0301] The method may be implemented such that the abrasive article characteristic is an abrasive grade or an indicator of the abrasive article's remaining life.

[0302] The method may be implemented such that the repair path includes a plurality of positions through which the tool will pass when executing the repair path.

[0303] The method may be implemented such that the repair path is an open path such that the starting orientation is different from the ending orientation.

[0304] The method may be implemented such that the repair path is a closed path such that the starting orientation is the same as the ending orientation.

[0305] The method may be implemented such that the repair path comprises a regular shape selected from the group consisting of: a circle, an ellipse, a rosette, an epitrochoid, a hypotrochoid, or a polygon.

[0306] The method may be implemented such that the repair path comprises an irregular shape having features selected from the group consisting of: a convex portion, a concave portion, a straight line, and a curved line.

[0307] The method can be implemented such that the repair path has rotational symmetry.

[0308] The method can be implemented so that the repair path is asymmetric.

[0309] The method may be implemented such that the working surface is a vehicle.

[0310] The method may be implemented such that the working surface parameter is a paint property of a paint layer on the vehicle.

[0311] The method may be implemented such that the working surface parameter is the orange peel texture of the vehicle.

[0312] The method may be implemented such that the defect parameter is the defect type.

[0313] The method may be implemented such that the defect parameter is the defect depth relative to the working surface.

[0314] The method may be implemented such that the defect parameter is a pre-repair image of the defect.

[0315] The method may be implemented such that the repair force is selected to cause feathering along the repair area.

[0316] A defect repair trajectory for a repair robot is proposed. The trajectory includes a starting orientation of a tool of the repair robot and an ending orientation of the tool on a work surface. The tool contacts and grinds the work surface. The trajectory also includes a trajectory shape, which includes a first orientation of the tool at a first time and a second orientation of the tool at a second time. The trajectory also includes a force profile, which includes a first force applied at a first time and a second force applied at a second time. The trajectory also includes a velocity profile, which includes a first tool velocity at a first time and a second tool velocity at a second time. The trajectory also includes an orientation profile, which includes a first orientation of the tool at a first time and a second orientation of the tool at a second time.

[0317] The defect repair trajectory can be implemented such that the first force applied is the same as the second force applied.

[0318] The defect repair trajectory can be implemented such that the first force applied is different from the second force applied.

[0319] The defect repair trajectory may be implemented such that the first orientation is the same as the second orientation.

[0320] The defect repair trajectory may be implemented such that the first orientation is different from the second orientation.

[0321] The defect repair trajectory can be implemented such that the first tool speed is the same as the second tool speed.

[0322] A defect repair trajectory can be implemented such that a first tool speed is different from a second tool speed.

[0323] The defect repair trajectory can be implemented such that the first orientation is different from the second orientation.

[0324] The defect repair trajectory can be implemented so that the first orientation is the same as the second orientation.

[0325] The defect repair trajectory can be implemented so that the ending orientation is different from the starting orientation.

[0326] The defect repair trajectory can be implemented so that the ending orientation is the same as the starting orientation.

[0327] The defect repair trajectory can be implemented so that the trajectory shape is circular, elliptical, rosette, epitrochoid, hypotrochoid or polygonal.

[0328] The defect repair trajectory can be realized so that the trajectory shape has rotational symmetry.

[0329] The defect repair trajectory can be implemented such that the trajectory shape is asymmetric.

[0330] The defect repair track can be implemented so that the track shape has a convex or concave portion and a perimeter with a curved portion or a straight portion.

[0331] The defect repair trajectory may be implemented such that the tool is a rotary sander and the first tool speed and the second tool speed are rotational speeds.

[0332] The defect repair trajectory may be implemented such that the tool is a vibrating sander and the first tool speed and the second tool speed are vibration rates.

[0333] The defect repair trajectory may be implemented such that the tool is an orbital sander having an orbit, and the first tool speed and the second tool speed are orbital rotational speeds.

[0334] The defect repair trajectory can be implemented such that the tool is a random orbital sander having an orbit, and the first tool speed and the second tool speed are orbital rotational speeds.

[0335] The defect repair trajectory may be implemented such that the tool is a random orbital sander having an axis of motion, and the first tool speed and the second tool speed are axial speeds.

[0336] A defect repair trajectory may be implemented such that the repair path includes the tool traveling over the defect.

[0337] The defect repair trajectory may be implemented such that defect remnants are preserved after executing the repair path.

[0338] The defect repair trajectory may be implemented such that the working surface is a vehicle, and abrading the working surface includes changing a texture of the working surface within the repair area.

[0339] The defect repair trajectory can be implemented so that the texture of the working surface within the repair area is different from the texture of the working surface outside the repair area.

[0340] The defect repair trajectory can be implemented such that the repair area includes a boundary area where the repair area texture is blended into the working surface texture.

[0341] The defect repair trajectory can be implemented so that the boundary area includes feathering.

[0342] The above description and accompanying drawings are given by way of example only and are not intended to limit the exemplary embodiments in any way, except as shown in the appended claims. It should be noted that the various technical aspects of the various elements of the various exemplary embodiments described above can be combined in many other ways, all of which are considered to be within the scope of the present disclosure.

[0343] Therefore, although exemplary embodiments are disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible. Therefore, the present disclosure is not limited to the above embodiments, but may be modified within the scope of the attached claims and the full scope of their equivalents.

[0344] Example

[0345] 19 to 23 show some examples of feathering and surface roughness. FIG. 19A to FIG. 19E An example of feathering is shown. Fig.19A A grayscale image of a repaired area on a reflective surface is shown. The polished area 1902 is located on the reflective surface 1904. Fig.19A The repair in FIG. 1 shows a feathering transition 1910. The width of the exemplary abraded area 1902 is approximately 40 mm. The surface 1904 is varnish coated on top of the painted surface. The darkening of the abraded area 1902 represents damage to the reflective surface 1904. This damage is caused by cutting or smearing of the surface by the abrasive used to remove or reduce the defect. The abraded area 1902 is significantly larger than the defect being repaired.

[0346] Feathering is important to prevent visible valleys from being apparent to individuals viewing the reflective surface once the abraded area 1902 is polished.As discussed above, the reflective surface 1904 may have a wavy surface feature known as "orange peel."

[0347] FIG. 19B to FIG. 19E Four examples of treated surfaces are shown. Fig.19B An unevenly feathered abrasive surface is shown with gradual feathering 1920 on one side and almost no feathering 1930 on the other side. Fig.19C An example 1940 is shown having irregular feathering around the edges. Fig.19E An undercut with no feathering 1960 and unbalanced feathering 1970 are shown. Fig.19D A preferred feathering 1950 is shown which is uniformly present around the perimeter.

[0348] The amount of feathering present can be measured by quantifying the damage to the reflecting surface over a particular path or area. Fig. 20A and Fig. 20B Examples of feathering measurement techniques 2000, 2050 are shown. Fig. 20A A line 2002 is shown drawn from the center of the repair area across the feathering transition at the edge. Fig. 20B Shows the Fig. 20A2002, which extends along axis 2052, which represents the number of pixels from the center of the image. Pixel value 2054 represents the brightness value of the pixel. As shown, there is a brighter center 2060, which transitions to a darker pixel in a more severely polished center ring 2065 of the polished area before transitioning to a fully reflective surface 2070.

[0349] like FIG. 21A to FIG. 21B As shown, feathering techniques can be used to introduce irregularities or non-uniformities in the polished area. Five lines 2202, 2204, 2206, 2208, and 2210 are drawn from the center of the treated area to the outer untreated area. The pixel measurements along the path are Fig. 22B The unevenness 2220 seen in the values ​​for the five samples shows the effect of feathering.

[0350] 22 and 23 illustrate mathematically how feathering may be measured using surface texture, waviness, and / or roughness, for example, in a region across a path.

[0351] Fig.22A A repaired area 2300 is shown with a line 2302 drawn from the center to the un-abraded portion. The area is measured over a path 10 pixels wide.

[0352]

[0353] Where S r is the light reflected in the direction of the mirror, T r is the total reflected flux, R q is the RMS surface area roughness, θ is the specular direction, and λ is the wavelength of light. Fig.22A Graphs of surface texture 2310, surface waviness 2320, and surface roughness 2330 are shown.

[0354] Applying Equation 10 to Fig.23A , it can be seen that the transition region has less feathering than desired, with an RMS roughness of 81.43. Fig. 23B A higher variability in the area where feathering is present is shown, where the RMS Roughness is 206.8. The specified roughness range for orange peel depends on the desired aesthetic of the manufacturer, and also on the orientation of the vehicle. For example, a lower panel on a utility vehicle may have orange peel where the variability of the orange peel shows a very tight transition that looks almost like a rough powder coat, which would be represented as a high roughness number. In another application on a vehicle hood surface, the orange peel may have a smoother wavy quality, which would be represented by a lower roughness number.

[0355] Fig.24A and Fig. 24B It shows that before polishing ( Fig.24A ) and after polishing ( Fig. 24B ) is an image of the repaired area taken by the user.

Claims

1. A repaired area on a working surface, the repaired defective area comprising: a repair boundary, wherein within the repair boundary, the working surface has a repair texture, and outside the repair boundary, the working surface has a working surface texture; a distribution of repair depths within the repair boundary; Hiding features, including uneven repair areas in non-circular repair boundaries; and Wherein the repaired area is a result of performing robotic repair on the work surface to remove defects.

2. The repaired area of ​​claim 1, wherein the repaired area is the result of a grinding operation on the working surface.

3. The repaired area of ​​claim 2, wherein the grinding operation removes the working surface texture from a portion of the repaired area. The repaired region of claim 1 , wherein the repair boundary is rotationally symmetric. 5 . The repaired region of claim 4 , wherein the repair boundary can have an n-fold rotational symmetry, where n is finite and greater than or equal to 2. 6 . 6 . The repaired region of claim 4 , wherein the repair boundary can have an n-fold rotational symmetry, wherein n is greater than or equal to 2 and less than or equal to 25. 7 . The repaired region of claim 4 , wherein the repair boundary can have an n-fold rotational symmetry, wherein n is greater than or equal to 3 and less than or equal to 25. 8 . The repaired region of claim 4 , wherein the repair boundary can have an n-fold rotational symmetry, wherein n is greater than or equal to 3 and less than or equal to 8.

9. The repaired region of claim 1, wherein the repair boundary is an epitrochoid or a hypotrochoid.

10. The repaired region of claim 9, wherein the repair boundary is defined to have an a parameter and an h parameter, and both the a parameter and the h parameter are non-zero.

11. The repaired region of claim 1 , wherein the path of the robotic repair performed is an epitrochoid or a hypotrochoid.

12. The repaired region of claim 11, wherein the path is defined as having an a parameter and an h parameter, and both the a parameter and the h parameter are non-zero.

13. The repaired area of ​​any one of claims 1 to 12, wherein the repair boundary is asymmetric.

14. The repaired area according to any one of claims 1 to 12, wherein the repair boundary is one sixth of the effective tool radius.

15. The repaired area of ​​any one of claims 1 to 12, wherein the repair boundary is one quarter of the effective tool radius.

16. The repaired area of ​​any one of claims 1 to 12, wherein the repair boundary is one third of the effective tool radius.

17. The repaired area of ​​any one of claims 1 to 12, wherein the repair boundary is one-half of the effective tool radius.

18. The repaired region of any one of claims 1 to 12, wherein the depth of cut decreases monotonically radially outward from the center of the repaired region.

19. The repaired region according to any one of claims 1 to 12, wherein defect residues remain in the repaired region.

20. The repaired area of ​​any one of claims 1 to 12, wherein the repaired area comprises feathering.

21. The repaired region of any one of claims 1 to 12, wherein the repair region is blended into the working surface.

22. The repaired area of ​​any one of claims 1 to 12, wherein the repaired area is not obvious to a person.

23. The repaired area according to any one of claims 1 to 12, wherein the repair boundary has a convex portion or a convex portion.

24. The repaired area of ​​any one of claims 1 to 12, wherein the repair boundary comprises a straight line.

25. The repaired area of ​​any one of claims 1 to 12, wherein a repair depth profile comprises a first depth at a first point and a second depth at a second point relative to the working surface, wherein the first point and the second point are within the repair boundary.

26. The repaired region of any one of claims 1 to 12, wherein the repair boundary comprises a first cutting profile at a first point and a second cutting profile at a second point, and wherein the first cutting profile is different from the second cutting profile.

27. The repaired area of ​​claim 25, wherein the first point is closer to the repair boundary than the second point, and wherein the first depth is greater than the second depth.

28. A method for repairing a defect on a work surface using a robot, the method comprising: receiving a surface mesh of the working surface; receiving a location of the defect, wherein the location is a coordinate location corresponding to a point on the surface mesh; generating a repair map for repairing the defect, wherein the repair map includes a repair position and a repair force at the repair position; generating a temporal parameterization of the repair map; sending a repair instruction to a repair robot, wherein the repair instruction includes the repair map and the time parameterization; and The repair robot includes a tool configured to contact the defect and grind the working surface at the defect location to form a repaired area including a hidden feature, wherein the hidden feature includes an uneven repair area in a non-circular repair boundary, wherein the repair orientation includes an orientation of the tool, and the force includes a force applied by the tool on the working surface.

29. A method for generating a repair trajectory of a work surface, the method comprising: Retrieve work surface parameters using a work surface parameter retriever; retrieving defect parameters of a defect on the working surface using a defect parameter retriever, wherein the defect parameters include a location of the defect on the working surface; generating a repair path for the defect using a repair path generator, wherein the repair path includes a repair position, a repair force, and a repair orientation of a tool for contacting the working surface; temporally parameterizing the repair path using a temporal parameterizer to generate a repair trajectory to form a repaired region including hidden features, wherein the hidden features include a non-uniform repair region in a non-circular repair boundary; and The method is implemented by a repair robot controller having a processor and stored computer-implemented instructions, which when executed cause the controller to complete the steps of retrieving work surface parameters, retrieving defect parameters, generating a repair path, and parameterizing the repair path time.

Images