DETECTING DEGRADATION OF BACK SQUEEGEE WATER PICK-UP PERFORMANCE FOR AUTONOMOUS FLOOR SCRUBBERS

Abstract

A system and/or method can be provided for detecting the status of one or more components and/or systems of, for example, a manual, semi-autonomous, or fully autonomous cleaning device or the like. For example, systems and methods can be used for detecting degradation of back squeegee performance. In some embodiments, a system and/or method for detecting the status of one or more components is provided for detecting vacuum performance degradation by monitoring the current (amperage) being drawn by a vacuum motor. In addition, one or more other components can be monitored by inspecting images captured by a camera mounted on a back door of the cleaning device to determine, for example, one or more other problems associated with a squeegee mount, water pick up, and/or the like.

Description

CROSS REFERENCE TO RELATED APPLICATIONS

The application claims priority to and the benefit of U.S. Provisional Patent Application Ser. No. 62/617,716, entitled “DETECTING DEGRADATION OF BACK SQUEEGEE WATER PICK-UP PERFORMANCE FOR AUTONOMOUS FLOOR SCRUBBERS”, filed on Jan. 16, 2018, the disclosure of which is incorporated herein by reference in its entirety.

BACKGROUND

The embodiments described herein relate to semi-autonomous cleaning devices and more particularly, to a system and method for detecting the status of one or more components and/or systems in a semi-autonomous cleaning device to determine the operating condition of one or more components.

The use of semi-autonomous devices configured to perform a set of tasks is known. For example, robots can be used to clean a surface, mow a lawn, collect items from a stocked inventory, etc. In some instances, however, some known robots fail to provide a user with an indication of the robot's position, progress, and/or status of one or more components of the system. For example, the problem of debris accumulation in back squeegee of a cleaning robot or floor scrubber is a common problem. In manual floor scrubbers, the operator can prevent the problem from happening by observing debris in the floor and avoiding driving the floor scrubber over the debris. The operator can also detect if the squeegee has blocking debris by visually inspecting the operation of one or more functions of the floor scrubber such as, for example, the quality of water pick-up provided by the back squeegee. In self-driving or semi-automatic floor scrubbers, the prevention and detection of debris in the back squeegee currently presents challenges that can reduce the efficacy and/or efficiency of these devices.

SUMMARY

Systems and methods for detecting the status of one or more components and/or systems in a semi-automatic cleaning device are described herein. For example, systems and methods described herein can be used for detecting degradation of back squeegee performance which can obviate or mitigate at least one disadvantage of some known cleaning devices.

In some embodiments, a method for detecting the status of one or more components and/or systems in a semi-automatic cleaning device can include detecting vacuum performance degradation by monitoring the current (amperage) being drawn by the vacuum motor, or the voltage at the terminals of the vacuum motor. In addition, one or more components can be monitored by inspecting images captured by a camera mounted on a back door of the cleaning device to determine, for example, one or more other problems associated with a squeegee mount, water pick up, and/or the like.

Thus, the systems and/or methods described herein can detect any problems associated with, for example, a back squeegee (or other suitable component) and can warn and/or can provide an indication to the operator about the problem. In some instances, such systems and/or methods can limit and/or substantially prevent water drop by the cleaning device due to any problem that may occur. Other features and advantages of the systems and/or methods are described more fully below.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a rear perspective view of a cleaning device according to an embodiment.

FIG. 2 is a detailed rear view of a rear-mounted camera on a cleaning device such as, for example, the cleaning device of FIG. 1.

FIG. 3 is a rear perspective view illustrating the rear camera scanning a portion of a floor behind the cleaning device to detect the presence of excess water.

FIG. 4 is a top view of the cleaning device that shows a camera field of vision with respect to the general orientation of the cleaning device.

FIG. 5 is a flow chart illustrating a method for detecting the status of one or more components and/or systems of a cleaning device according to an embodiment.

FIG. 6 is a block diagram showing the interconnection of the functional modules used for visual streak detection by the floor scrubber.

FIG. 7 shows a system block diagram for a squeegee detection algorithm.

DETAILED DESCRIPTION

In some embodiments, a system and/or method can be provided for detecting the status of one or more components and/or systems of, for example, a semi-automatic cleaning device or the like. For example, systems and methods can be used for detecting degradation of back squeegee performance. In some embodiments, a system and/or method for detecting the status of one or more components is provided for detecting vacuum performance degradation by monitoring the current (amperage) being drawn by a vacuum motor, the voltage at the terminals of the vacuum motor, or the operating power consumed by the vacuum motor. In some embodiments, the vacuum motor is an electric motor. In addition, one or more other components can be monitored by inspecting images captured by a camera mounted on a back door of the cleaning device to determine, for example, one or more other problems associated with a squeegee mount, water pick up, and/or the like.

The systems and/or methods described herein can be used on any suitable device, machine, system, robot, etc. For example, in some embodiments, the systems and methods described herein can be used with and/or on a semi-autonomous cleaning robot or the like. In some embodiments, such a semi-autonomous cleaning robot can be similar to or substantially the same as any of those described in U.S. Patent Publication No. 2016/0309973 entitled, “Apparatus and Methods for Semi-Autonomous Cleaning of Surfaces,” filed Apr. 25, 2016, the disclosure of which is incorporated herein by reference in its entirety.

In some embodiments, any of the systems and/or methods described herein can be used to measure an electric current of a vacuum motor connected to a main control board of a cleaning device. The cleaning device can be any semi-autonomous (or manual or fully autonomous) cleaning device or robot. The control board can be, for example, an electronic control board or printed circuit board (PCB) that includes at least a processor and a memory. The electric current of the vacuum motor can provide information about the quality of the vacuum being created. For example, in some instances, the current can be relatively high when the vacuum operates correctly and relatively low when there is/are one or more problems (or vice versa).

Cleaning systems, and in particular, vacuum cleaning systems are dependent on the consistent application of cleaning fluid, mechanical agitation, for example with a moving brush system, and the consistent removal of the cleaning fluid from the surface through a vacuum. Many cleaning systems rely on a flexible rubber squeegee in pressure contact with the floor to contain the cleaning fluid and debris from the surface for removal by a vacuum system.

One of the significant problems with vacuum cleaning systems is the potential for larger objects, such as plastic bags, balls, packaging, or other objects to become lodged in the pathway between the surface being cleaned and a return/dirty water tank, creating a compromised vacuum function. A lodged object will block the proper flow of cleaning fluid and debris from the surface to the return/dirty water tank, and compromise the cleaning effectiveness of the system, caused by a compromised cleaning operation of some component or components of the floor scrubber. This problem is exacerbated when the cleaning system is autonomous, as much time may pass before the blockage situation is detected and resolved through a corrective action, resulting in improperly cleaned surfaces and requiring expensive and time-consuming re-cleaning.

When cleaning a surface, many different types of debris can be present. In an ideal situation, the surfaces to be cleaned by the vacuum cleaning system have been pre-cleaned of all large debris. Typically, this pre-cleaning is done manually by human workers who operate brooms and other tools to pick up the larger debris and remove it manually in bins. While this pre-cleaning process is time consuming and expensive, it is even less desirable to have the vacuum cleaning system routinely compromised by clogging debris.

Detecting a clogged vacuum pathway is a difficult problem for either a human operator or for an autonomous vacuum cleaning system. In some cases, the failure is evident by the failure of the vacuum system to adequately remove the cleaning fluid and debris from the surface to the return/dirty water tank. This failure may be observable by noting excess cleaning fluid deposited on the cleaning surface, particularly at the edges of the squeegee. Complicating this situation is the fact that the blockage may be either a partial or a full blockage. This means that the failure symptoms such as excess cleaning fluid deposited on the cleaning surface may appear to various degrees, and in many cases of lighter or partial clogging, be difficult to detect.

The techniques described herein use various measurement techniques to establish whether the vacuum system is operating within the desired parameter range. The measured values of these parameters can be compared to a threshold value, be analyzed through a trend analysis, or compared to previous values to generate a signal indicative of a departure from the desired parameter range, i.e. range of normal operation. Of course, depending on the configuration of the system, the measured value may be directly compared to a threshold value instead of computing the difference between the measured value and the threshold value, in for example, a hardware or analog solution.

In one aspect, the motor current is measured to determine changes that would be consistent with the increased load on the vacuum fan due to a blockage in the in the pathway between the surface being cleaned and a return/dirty water tank. Normally, motors draw more current when there is greater shaft resistance, in this case due to increased air turbulence at the vacuum fan blades due to clogging. The additional load or clogging may also be detected by observing changes to the rotational speed of the motor, for example by an optical encoder connected to an electronic measurement device.

In another aspect of the invention, clogging can be measured by detecting the vacuum fan motor noise or microphonics. As the load on the motor increases due to clogging, the motor will change its characteristic vibrations and vibration frequency. The fundamental vibration frequency can be evaluated by connecting a microphone placed on or near to the vacuum fan motor, and sampling the resultant waveform to determine the periodicity.

In another aspect of the invention, the clogging can be detected by measuring the pressure at different points along the vacuum pathway from the squeegee to the return/dirty water tank. Normal, non-clogged operation has a characteristic average pressure profile along the length of the vacuum pathway. Placing pressure sensors along this pathway enables the detection of an abnormal pressure pattern (differential suction) by comparing the relative pressure at points along the vacuum pathway. An extra pressure sensor outside the vacuum system (ambient) can be used to provide a reference pressure, and to confirm that the entire system is operating under adequate vacuum.

The embodiments and/or methods described here also can be used to inspect visually one or more components using the back camera. For example, the control board and/or electronic system of the cleaning device can use and/or analyze the image coming from the back camera to detect the position of the squeegee, for example, using a basic masking. If the squeegee is out of position, the control board and/or electronic system can, for example, use image filtering or the like to detect this problem. In other instances, the control board and/or electronic system can perform any other technique such as, for example, edge detection. For example, if the squeegee has a leaking problem, streaks may be left behind the squeegee. To detect edges, a streak detector can be used and/or implemented at or by the control board or electronic system. To tune one or more parameters to trace the streak, a neural network can be used and/or implemented at or by the control board or electronic system to estimate the most likely parameters associated with the streak detection algorithm. Other visual artifacts, such as detecting irregular ripples or pooled fluid indicating a misplaced or damaged squeegee can be similarly implemented with suitable standard image analysis algorithms.

FIG. 1 is a perspective view illustrating semi-autonomous cleaning device 100 according to an embodiment. The semi-autonomous cleaning device 100 (also referred to herein as “cleaning device,” “device,”, “vacuum cleaning system”, and/or “floor scrubber”) can be any suitable device, machine, system, robot, etc. configured to clean, scrub, or otherwise move along a surface in an at least semi-autonomous manner. For example, in some embodiments, the cleaning device 100 can be similar to or substantially the same as any of the cleaning devices described in the US 2016/0309973 publication. While described as a “semi-autonomous” cleaning device 100, it should be understood that the cleaning device 100 can be fully autonomous or can include one or more systems, subsystems, components, etc. configured to function autonomously. Accordingly, the term “semi-autonomous” is not intended to be limiting to a cleaning device that functions in a partially autonomous manner.

As illustrated in FIG. 1, the floor scrubber 100 includes a set of water tanks and covers 101 (top cover not shown) coupled to a frame 102 with an attached cleaning head 103 and rear squeegee 104. During operation water is dispensed onto the floor through the cleaning head and vacuumed up into a return/dirty water tank 105. Held within the return water tank is a vacuum motor 106 that generates a suction force operable to pull the water off the floor near the rear squeegee and into the return/dirty water tank 105. The floor scrubber 100 includes handlebars 107, which can be used for steering control during manual operation but are not active when the machine is in autonomous run mode.

Although not shown in FIG. 1, the floor scrubber 100 includes an electronic system having one or more computing devices configured to control one or more components of the floor scrubber 100. For example, in some embodiments, the electronic system can be similar to or substantially the same as those included in the cleaning devices described in the US 2016/0309973 publication. As such, the electronic system can include a control board, a printed circuit board (PCB), and or any suitable computing device, each of which can include at least a memory and a processor. Controls, instructions, and/or information is displayed to an operator through a touch screen 108 that is included in and/or electrically or electronically connected to the electronic system.

FIG. 2 illustrates a detailed view of a portion of a floor scrubber 200. The floor scrubber 200 can be similar to or the same as the floor scrubber 100 described above with reference to FIG. 1. The rear of the floor scrubber 200 has an electrical access panel 201 which has a camera 202 mounted to the access panel 201 that is pointed behind the floor scrubber 200 to monitor water pick up off the floor. As described above, the floor scrubber 200 can be similar to any of the cleaning devices described in detail in the US 2016/0309973 publication. The camera 202 can be any suitable imaging device configured to capture a still image or record a video. More particularly, with the camera 202 pointed behind the floor scrubber 200 (e.g., toward the floor), the camera 202 can be configured to capture a still image or a video of a portion of the floor from which information can be analyzed and/or extracted to determine, for example, an amount of water left on the floor.

FIG. 3 illustrates a detailed view of the overall operation of capturing an image or recording a video using the camera 202. The camera 202 is configured to scan the path behind the floor scrubber 200. The camera field of vision depicted by 301 is to provide a visual aide, but the actual field of vision is related to the ability of the camera 200. That is to say, in some embodiments, the camera's 202 field of vision can be larger than the field of vision 301 shown in FIG. 3, can be smaller than the field of vision 301, and/or can be a different shape that the shape of the field of vision 301. Moreover, in some embodiments, one or more settings of the camera 202 can be modified such that the camera 202 has any desired field of vision. In some instances, the target area to be monitored is located behind a rear squeegee 303 (e.g., similar to or the same as the rear squeegee 104 shown in FIG. 1), which is inspecting the floor where the floor scrubber has just cleaned. In other words, the target area to be monitored is within the field of vision 301 and includes an area of the floor behind the rear squeegee 303. FIG. 4 illustrates a position along a surface associated with a field of vision 402 of the camera 202 as a cleaning device 400 (e.g., similar to or the same as the cleaning devices 100 and/or 200) moves along the surface.

FIG. 4 illustrates a top view of the cleaning device that shows a camera field of vision with respect to the general orientation of the cleaning device. In some embodiments, the field of vision monitored by the rear camera is extended towards the floor scrubber to include rear components of the floor scrubber, including the rear squeegee. This allows the camera image to be analyzed for the presence and correct positioning of the features of the floor scrubber including the rear squeegee.

FIG. 5 is a flow chart illustrating an overview of a process flow 500 or logic executed by the electronic system within the floor scrubber (e.g., the floor scrubber 100, 200, and/or 400). Once the floor scrubber is started in autonomous cleaning mode, at step 502, the floor scrubber begins, cleaning, at step 503, at a designated, desired, and/or predetermined area. During the cleaning process, at step 503, the one or more cameras on the floor scrubber captures one or more images or records one or more videos of the recently cleaned surface, at step 506. These images or videos are then monitored and analyzed by the on-board computing device (e.g., included in the electronic system), at step 506. Further, a streak detection algorithm can be used to detect excess water at step 508. One example of a streak detection algorithm is the canny edge detection algorithm or variations thereof. The streak detection algorithm is an image processing technique that takes the image gathered (e.g., from step 506), removes any excess noise, and evaluates intensity gradients of the image (or image data). If the gradient value of the edges in the image is calculated to be below a predetermined threshold and no potential edges are detected, the floor cleaner continues to operate where the process reverts back to normal cleaning (e.g., at step 503). If the streak detection algorithm detects excess water, indicated by visual artifacts (at step 508), it moves on to the next step of the flow chart (at step 514). Excess water detection, indicating improper or compromised cleaning operation (at step 508) may be accomplished by measuring the intensity gradient within an image or image data, determining whether there is a potential edge of water in the path cleaned by the floor scrubber. In further embodiment, the computing device of the floor scrubber flags and/or otherwise defines an indication of a potential issue with the rear squeegee (e.g., the rear squeegee 303).

In further embodiments, the computing device on-board the floor scrubber monitors a voltage and amperage associated with and/or otherwise drawn by a vacuum motor at step 514. In some instances, a drop or spike in the voltage and/or amperage of the vacuum motor, at step 514, may indicate an issue with the rear squeegee such as a blockage or any other cause of suction loss, such as a clogged vacuum pathway. If the drop or spike in the voltage and/or amperage occurs in conjunction with the streak detection algorithm (visual scanning) indicating potential water detected, at step 514, the floor scrubber will move to the next step 518 to halt operation and alert the operator in order to prevent potential damage to the device or to prevent leaving excess water on the floor. A poorly functioning vacuum motor can also be detected by detecting electrical parameters of the motor, for example applied voltage with not current drawn.

In further embodiments, the rear squeegee can be a consumable item that can be serviced, removed, and/or replaced. Thus, if excess water is detected, at step 508, and there is no change in the voltage and/or amperage (e.g., no drop or spike) to the vacuum motor, at step 514, then the electronic system and/or the compute device included therein, can initiate a corrective action such as sending an alert or notification to the operator indicative of in instruction to motor and/or maintenance the rear squeegee, at step 522. The alert and/or notification can be any suitable alert and/or notification. For example, the alert and/or notification can be a visual indication (e.g., a flashing light, visual light, etc.) and/or an audible indication (e.g., an alarm, an audio sound or any suitable audible output). In other embodiments, the corrective action can include sending or wirelessly transmitting an alert or notification such as an electronic signal sent to a remote electronic device such as, for example, a controller, a remote, a smart phone, a desktop, a laptop, a control server and/or any other suitable device. The signal may also be directed to a remote autonomous floor scrubber management system, wherein repair and maintenance functions can be coordinated for one or more floor scrubbers or other machines. The signal can be indicative of an instruction for the remote device to provide an alert or notification to be observed by the operator. The electronic signal can be an electronic message (e-mail, an instant message (IM), a text notification or short message service (SMS) or a facsimile (e.g., fax), In further embodiments, the alert and/or notification may include tactile vibrations such as buzzing of a mobile phone or pager on the operator and rumbling of the steering wheel or seat of the floor scrubber. Corrective actions can include directing an operator or maintenance personnel to inspect various subsystems of the floor scrubber, stopping the floor scrubber, stopping the vacuum motor, logging the time, status and/or position of the floor scrubber, ordering replacement parts, or indicating additional repair, correction, or maintenance activities.

FIG. 6 is a block diagram showing the interconnection of the functional modules used for visual streak detection by the floor scrubber (e.g., the floor scrubber 100, 200, and/or 400). The block diagram 600 of FIG. 6 includes a Front Camera 608 that is mounted on the front of the floor scrubber, generally pointing in the direction of travel for the floor scrubber. The Front Camera 608 feeds the continuous image to the Preprocessing unit 607, which filters and transforms the image to a reference image. The Preprocessing Unit 607 applies image processing filters on the input image to remove noise, reduce size or transform to another space. These operations can be done with OpenCV or with other similar software libraries. The preprocessor outputs video data to the Features Estimation unit 606. The Features Estimation Unit 606 extracts edge, color and texture features from the preprocessed image. These operations could be done with OpenCV libraries or coded using algorithms found in well-known image processing literature.

Furthermore, system 600 also has a Rear Camera 601, that is mounted on the rear of the floor scrubber, generally pointing opposite the direction of travel for the floor scrubber. The Rear Camera 601 feeds the continuous image to the Preprocessing unit 602, which filters and transforms the image to an image of interest. As is known in image processing technology, the continuous image stream may be sampled periodically to provide a series of static images for use in further image processing. The Preprocessing Unit 602 applies image processing filters on the input image to remove noise, reduce size or transform to another space. The two image streams coming from Features Estimation unit 606 and Features Estimation unit 603 are compared in Water Areas Segmentation unit 604. The Water Areas Segmentation Unit 604 examines the generated edge, color and texture features from both rear and front cameras and provides a likelihood for different image areas to be covered with water. A learning-based mechanism such as Support Vector Machine (SVM) can be used. In addition, and not shown, would be a comparison delay equivalent to the transit time for floor scrubber between the two cameras, so that the comparison is on the same area of the floor, pre and post cleaning. The Decision Rendering unit 605, takes the output of the Water Areas Segmentation unit 604 and decides on the presence of water patches and generate appropriate notifications.

FIG. 7 shows a system block diagram for the squeegee detection algorithm. The block diagram 700 of FIG. 7 includes a Rear Camera 701 that sends continuous video output to Preprocessing unit 702. Preprocessing unit 702 provides discrete features extraction and/or applies image processing filters on the input image to remove noise, reduce size or transform to another space. These operations could be done with OpenCV or with similar software libraries. The output of the Preprocessing unit 702 is fed into the Matching unit 703. The Memory 704 contains reference features encoded to facilitate easy comparison the features identified by the Rear Camera 701. The Memory 704 also contains information on where in the visual field the identified objects should be placed. The Memory 704 feeds into the Model Generation unit 705, that creates a model for comparison to the actual features and position observed by the Rear Camera 701. Model generation could be as simple as retrieving a template or a set of features from memory, or it could involve rotating, resizing or subdividing the template or model to match against different possible location and orientations of the squeegee in the image. These operations could be done with the help of standard computer vision or computer graphics libraries such as OpenCV and or OpenGL. The Matching module 703, compares discrete features by comparing their descriptors which could be done using an algorithm like RANSAC for example which is also available in OpenCV, or by performing patch matching. This can be done with standard techniques available in opensource libraries or coded following well known image processing algorithms. The output of the Matching unit 703 feeds into the Pose Extraction unit 706. Pose estimation uses the results of matching to generate a hypothesis (or hypotheses) about the pose of the squeegee in the image, including a confidence estimation. The Decision Rendering unit 707, utilizes the results of pose estimation to determine whether the squeegee or any of its visually identifiable (visually monitored) mechanical components such as squeegee, squeegee assembly, bolts, carrier, or idler wheels are in the correct position, misaligned, trailing behind the robot or totally absent and generate appropriate notifications and corrective actions. Identifying misplaced or misaligned components is particularly crucial for removeable, replaceable, or disposable parts such as rear squeegee rubbers and idler wheels. While in this implementation, the camera position is advantageously directed to the rear of the device and towards the rear squeegee assembly, other implementations may benefit from cameras other positions, including at the underside, rear, front or side of the floor scrubber.

In another embodiment, the system compares the intensity gradients of a front facing camera with the gradient of a rear facing camera to account for baseline intensity gradients of the surface being cleaned. Some delay or hysteresis is added to the signaling algorithm, for situations where the intensity gradient of the surface being cleaned is changing due to different patterns in the surface.

In situations where the edge detection algorithm detects streaking at the edges of the squeegee during sharper turns in the cleaning path, such areas that have not been cleaned properly can be logged into a database to note for further cleaning. From this database, the areas where some such streaking occurs can be marked for a second pass and re-cleaned. The monitoring systems described herein can be used to detect the presence of multiple failures, either individually, or preferably in concert to improve the quality and specificity of alerts and corrective actions. Corrective actions can include directing an operator or maintenance personnel to inspect various subsystems of the floor scrubber, stopping the floor scrubber, logging the time, status and/or position of the floor scrubber, ordering replacement parts, or indicating additional repair, correction, or maintenance activities. These activities can be prioritized in the order they are presented to an operator or to maintenance personnel by some combination of ease of execution of the corrective action, cost of the corrective action, or likelihood of a specific cause of the fault.

In further embodiments, the computing device on-board the floor scrubber monitors a voltage and amperage associated with and/or otherwise drawn by a vacuum motor 514. In some instances, a drop or spike in the voltage and/or amperage of the vacuum motor 516 can indicate an issue with the rear squeegee such as a blockage or any other cause of suction loss. If the drop or spike in the voltage and/or amperage occurs in conjunction with the canny or streak detection algorithm (visual scanning) indicating potential water detected (e.g., at step 512), the floor scrubber will halt operation 518 to prevent potential damage or to prevent leaving excess water on the floor. In some embodiments, the rear squeegee can be a consumable item that can be serviced, removed, and/or replaced. Thus, if excess water is detected (e.g., at step 512) and there is no change in the voltage and/or amperage (e.g., no drop or spike) to the vacuum motor (e.g., at step 520), then the electronic system and/or the compute device included therein can send an alert or notification to the operator (i.e., alerting the operator) indicative of in instruction to motor and/or maintenance the rear squeegee 522. The alert and/or notification can be any suitable alert and/or notification. For example, the alert and/or notification can be a visual indication (e.g., a flashing light, etc.) and/or an audible indication (e.g., an alarm, or any suitable audible output). In other embodiments, the alert or notification can be a signal sent to a remote electronic device such as, for example, a controller, a remote, a smart phone, a desktop, a laptop, a control server and/or any other suitable device. The signal can be indicative of an instruction for the remote device to provide an alert or notification to be observed by the operator.

The monitoring systems described herein can be used to detect different types of failures, either individually, or preferably in concert for more precise diagnostic capabilities. For example, a compromised vacuum function can be created if a squeegee develops a hole, tear or aperture, is misplaced, is an incorrect part, is installed with excessive skew or otherwise misaligned, is dragging debris, falls off entirely, or is worn to the extent that it does not make a good seal with the cleaning surface. The clog detection system would measure out of range pressure along the vacuum pathway relative to ambient pressure. The operating electrical or mechanical parameters such as speed of the vacuum motor or current draw may also depart from normal operating parameters under the above conditions, due to decreased air turbulence at the vacuum fan blades due to additional air flow.

While various embodiments have been described above, it should be understood that they have been presented by way of example only, and not limitation. Where schematics and/or embodiments described above indicate certain components arranged in certain orientations or positions, the arrangement of components may be modified. While the embodiments have been particularly shown and described, it will be understood that various changes in form and details may be made.

Although various embodiments have been described as having particular features, concepts, and/or combinations of components, other embodiments are possible having any combination or sub-combination of any features, concepts, and/or components from any of the embodiments described herein. The specific configurations of the various components can also be varied. For example, the specific size, specific shape, and/or specific configuration of the various components and/or various inputs or outputs can be different from the embodiments shown, while still providing the functions as described herein. The size, shape, and/or configuration of the various components can be specifically selected for a desired or intended usage.

Where methods and/or events described above indicate certain events and/or procedures occurring in certain order, the ordering of certain events and/or procedures may be modified and that such modifications are in accordance with accepted and/or desired variations of the specific embodiments. Additionally, certain events and/or procedures may be performed concurrently in a parallel process when possible, as well as performed sequentially as described above. Certain steps may be partially completed or may be omitted before proceeding to subsequent steps.

Claims

1. A method of implementing a corrective action on a floor scrubber, the floor scrubber having a compromised vacuum function, the floor scrubber having at least one vacuum motor, the method comprising:

determine normal operating parameters for at least one vacuum motor of the floor scrubber;

determine a range of normal operation of the at least one vacuum motor;

monitoring the operating parameters of the vacuum motor;

comparing at least one current operating parameter to the normal operating range;

if the comparison is outside the normal operating range: determine that a compromised vacuum function has occurred; generating at least one alert on the floor scrubber indicating a compromised vacuum function has occurred; and

implementing at least one corrective action on the floor scrubber based on the alert.

2. The method of claim 1 wherein the operating parameter is selected from a list consisting of current draw, operating voltage, operating power, rotational speed, noise and differential suction.

3. The method of claim 1 wherein the alert is selected from a list consisting of a visual light, an audio sound, electronic message, an instant message, a text notification, and a tactile vibration.

4. The method of claim 1 wherein the compromised vacuum function is selected from a list consisting of a compromised squeegee, a missing squeegee, a poorly functioning vacuum motor, and a clogged vacuum pathway.

5. The method of claim 1 wherein the corrective action is selected from a list consisting of stopping the floor scrubber, stopping the vacuum motor, alerting the operator, and wirelessly transmitting the alert to a remote autonomous floor scrubber management system.

6. A method of detecting a compromised cleaning operation in a floor scrubber, the method comprising:

capturing an image of a recently cleaned surface, using at least one camera of the floor scrubber;

analyzing the image for evidence of improper cleaning operation;

detecting a compromised cleaning operation by detecting visual artifacts;

generating an alert; and

implementing at least one corrective action on the floor scrubber based on the cause of the alert.

7. The method of claim 6 wherein the step of detecting a compromised cleaning operation further comprises detecting water streaks using an edge detection algorithm.

8. The method of claim 6 wherein the step of analyzing the image further comprises of the step of processing the image to enhance edges and remove artifacts.

9. The method of claim 8 wherein the edge detection algorithm is a canny algorithm or a variation thereof.

10. The method of claim 6 wherein the step of detecting a compromised cleaning operation further comprises of detecting a scratch generated by a hard object stuck under the vacuum cleaning system of the floor scrubber.

11. The method of claim 6 wherein the step of detecting a compromised cleaning operation further comprises of detecting irregular ripples or pooling of fluid indicating a misplaced or damaged squeegee.

12. The method of claim 6 wherein the step of analyzing the image for evidence of improper cleaning operation further comprises comparing the images of the front and rear cameras on the floor scrubber to detect differences in the images.

13. The method of claim 6 wherein the corrective action is to recognize that areas of the cleaned surface have not been cleaned properly and to note the locations of those areas for further cleaning.

14. The method of claim 6 where instructions are generated to re-clean areas that have not been cleaned properly.

15. A method of detecting missing or misaligned mechanical components on a floor scrubber, using a computer processor on the floor scrubber, the method comprising:

storing a list of mechanical components in memory of the floor scrubber;

storing a list of expected locations of the mechanical components in memory of the floor scrubber;

capturing an image of the mechanical component using at least one camera of the floor scrubber;

analyzing the camera image to identify the mechanical components;

analyzing the position of the identified mechanical components relative to the expected locations of the mechanical components in memory;

generating an alert if the identified mechanical components are misaligned or missing; and

implementing at least one corrective action on the floor scrubber based on the alert.

16. The method of claim 15 wherein the mechanical component is selected from a list consisting of a squeegee, a squeegee assembly, bolts, carrier, or idler wheels.

17. The method of claim 15 wherein the mechanical component is removable, replaceable or disposable.

18. The method of claim 15 wherein the corrective action is selected from a list consisting of stopping the floor scrubber, alerting the operator, wirelessly transmitting the alert to a remote autonomous floor scrubber management system, and requesting service maintenance of the floor scrubber.

19. The method of claim 15 wherein the camera is located at the underside, rear, front or side of the floor scrubber.

20. The method of claim 19 wherein the camera is located above and in view of the visually monitored mechanical components.