Systems and methods for semi-automatic cleaning devices with adjustable cleaning parameters

By integrating sensing modules and machine learning algorithms in semi-automatic cleaning equipment and adjusting cleaning parameters, the problem that existing equipment cannot adapt to different floor types is solved, and efficient cleaning and polishing of VCT floors is achieved, reducing costs and labor demands.

CN119055150APending Publication Date: 2024-12-03AVIDBOTS CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410692243.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-30
Filing Date
2024-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing automatic and semi-automatic cleaning equipment cannot fully adapt to changing environments and optimize and maximize cleaning performance, especially when maintaining vinyl composite floor tile (VCT) floors, traditional polishing methods are time-consuming and costly.

Method used

An adjustable semi-automatic cleaning device is designed to detect floor type and gloss through the front and rear sensing modules, and to adjust cleaning parameters using machine learning algorithms, combining interchangeable cleaning pads and camera sensors to achieve different floors. Types of optimized cleaning and polishing.

Benefits of technology

Efficient cleaning and polishing under different floor types and gloss conditions are achieved, reducing labor costs and extending polishing operation intervals, providing cost-effective cleaning solutions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119055150A_ABST
    Figure CN119055150A_ABST
Patent Text Reader

Abstract

A system and method for a semi-automatic cleaning apparatus with adjustable cleaning parameters. A floor cleaning system of a semi-automatic cleaning apparatus adjusts cleaning parameters through one or more control systems to optimize cleaning performance in specific operating environments and applications. Using a sensor, either a front sensing module or a rear sensing module of a semi-automatic cleaning apparatus may detect different floor types and adjust parameters accordingly prior to initiating a cleaning or polishing plan for conventional floors and VCT floor veneers. The glossiness of the floor can also be detected by measuring the reflection of the light source (i.e., the LED strip) with a camera sensor. Machine learning algorithms may be used for floor cleaning or floor polishing.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and benefits of U.S. Provisional Patent Application No. 63 / 505,042, filed on May 30, 2023, entitled “SYSTEM AND METHOD OF A SEMI-AUTONOMOUS CLEANING APPARATUS WITH ADJUSTABLE CLEANING PARAMETERS,” the disclosure of which is incorporated herein by reference in its entirety. Background Art

[0003] Embodiments described herein relate to automated and semi-automated cleaning equipment and, more particularly, to systems and methods for improving the cleaning of indoor surfaces.

[0004] It is well known to use automatic and semi-automatic cleaning equipment that is configured to perform a range of tasks. For example, semi-automatic equipment or robots can be used to clean indoor surfaces such as department stores, shopping malls, airports and office buildings.

[0005] Most automated scrubbing cleaning systems or semi-automated cleaning equipment are considered silent or lack intelligence. While they can work in a variety of environments and situations, they are unable to fully adapt to changing circumstances to optimize and maximize cleaning performance.

[0006] Vinyl composite tile (VCT) flooring is a versatile and durable flooring used extensively in commercial retail spaces. The most common specification for VCT flooring is 0.125-inch thick, 12-inch square tiles that are glued to a concrete subfloor. After installation, a finish is applied to the VCT to improve the floor's appearance and protect the tiles. This floor finish can be sanded or "buffed" to a high-gloss finish.

[0007] Different businesses have different expectations and standards for the maintenance and appearance of VCT floor finishes. A business that wishes to convey a sense of cleanliness and order may choose to polish its floors multiple times a week to maintain a shiny, glossy appearance. However, polishing floors is time-consuming and expensive, and in some cases requires the use of large propane burners, the use of which requires special safety precautions, meaning that businesses must carefully weigh the costs and benefits of any floor polishing program.

[0008] Small automated polishing platforms can provide value to customers by simultaneously reducing their labor costs and improving the appearance of floors through more frequent polishing. While it is not yet certain that such platforms will replace large, dedicated propane or battery-powered polishers, such equipment could significantly extend the time between intensive polishing operations through frequent, light polishing maintenance.

[0009] It is desirable to provide a semi-automatic cleaning device with an adjustable configuration to fully adapt to changing cleaning scenarios. It is also desirable to use the improved semi-automatic cleaning device as a floor polisher for VCT floor finishes. Summary of the invention

[0010] A system and method for a semi-automatic cleaning device with adjustable cleaning parameters. The floor cleaning system of the semi-automatic cleaning device adjusts the cleaning parameters through one or more control systems to optimize cleaning performance in specific operating environments and applications. Using sensors, the front sensing module or the rear sensing module of the semi-automatic cleaning device can detect different floor types and adjust the parameters accordingly before initiating a cleaning or polishing plan for conventional floors and VCT floor finishes. The glossiness of the floor can also be detected by measuring the reflection of a light source (i.e., LED light strip) using a camera sensor. Machine learning algorithms can be used for floor cleaning or floor polishing. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A perspective view of a semi-automatic cleaning device.

[0012] Figure 2 It is a front view of the semi-automatic cleaning equipment.

[0013] Figure 3 This is the rear view of the semi-automatic cleaning equipment.

[0014] Figure 4 This is the left view of the semi-automatic cleaning equipment.

[0015] Figure 5 This is the right side view of the semi-automatic cleaning equipment.

[0016] Figure 6 This is an exploded view of a semi-automatic device.

[0017] Figure 7 A diagram illustrating an exemplary workflow.

[0018] Figure 8 A diagram illustrating the detection of floor glossiness.

[0019] Fig. 9 A graph of the cropped image.

[0020] Fig.10 A plot comparing the gloss values ​​predicted by the random forest classification method with the gloss values ​​measured with Rhopoint. DETAILED DESCRIPTION

[0021] Figures 1 to 5 Exemplary embodiments of automated or semi-automated cleaning equipment are shown. Figure 1A perspective view of a semi-automatic cleaning device. Figure 2 It is a front view of the semi-automatic cleaning equipment. Figure 3 This is the rear view of the semi-automatic cleaning equipment. Figure 4 This is the left view of the semi-automatic cleaning equipment. Figure 5 This is the right side view of the semi-automatic cleaning equipment.

[0022] Figures 1 to 5 A semi-automatic cleaning device 100 is shown. The device 100 (also referred to herein as a "cleaning robot" or "robot") includes at least a frame 102, a drive system 104, an electronic system 106, and a cleaning assembly 108. The cleaning robot 100 can be used to clean (e.g., vacuum, scrub, disinfect, etc.) any suitable surface area, such as floors in homes, commercial buildings, warehouses, etc. The robot 100 can be of any suitable shape, size, or configuration, and can include one or more systems, mechanisms, components, or sub-assemblies that can perform any suitable functions related to, for example, traveling along a surface, mapping a surface, cleaning a surface, and / or the like.

[0023] The framework 102 of cleaning equipment 100 can be any suitable shape, size and / or configuration. For example, in some embodiments, framework 102 can include a series of assemblies or similar assemblies, which are coupled to form a supporting structure, configured to support drive system 104, cleaning assembly 108 and electronic system 106. Cleaning assembly 108 can be directly connected to framework 102 or other suitable supporting structures or subframes (not shown). The framework 102 of cleaning equipment 100 also includes strobe lights 110, headlights 112, front sensor modules 114 and rear sensor modules 128, rear wheels 116, rear skirts or scrapers 118, optional handles 120 and cleaning hoses 122. Framework 102 also includes one or more internal water storage tanks or water storage volumes for storing water, disinfectant (i.e. bleach, soap, cleaning fluid, etc.), debris (dirt) and dirty water. More information about the cleaning device 100 is further disclosed in U.S. utility patent application 17 / 650,678, filed on February 11, 2022, entitled “APPARATUS AND METHODS FOR SEMI-AUTONOMOUS CLEANING OF SURFACES,” the entire contents of which are incorporated herein by reference.

[0024] More specifically, in this embodiment, the front sensing module 114 also includes a structured light sensor located in a vertical and horizontal mounting position, one or more sensors (such as an active stereo sensor), and an RGB camera. Figure 3As shown, the rear sensing module 128 includes a rear optical camera. In other embodiments, the front sensing module 114 and the rear sensing module 128 may also include other sensors, including one or more optical cameras, thermal imagers, LiDAR (light detection and ranging), structured light sensors, active stereo sensors (for 3D) and RGB cameras or optical cameras.

[0025] like Figure 3 As shown, the rear view of the semi-automatic cleaning device 100 further shows the frame 102, the cleaning hose 122, the cleaning water tank 130, the cleaning water filling port 132, the rear skirt 118, the "strobe light" 110 and the electronic system 106. The electronic system 106 also includes a display screen 134, which can be a static display screen or a touch display screen. The rear skirt 118 includes a scraper head or a rubber blade, which engages with the floor surface as the cleaning device 100 moves.

[0026] Figure 3 Further depicted are an emergency stop button 124, a device power on / off button 126, and a rear sensing module 128. The rear sensing module 128 includes an optical camera that is used to view the area behind the device 100. This complements the front sensing module 114 that provides a view forward of the device 100. The two sensing modules work in conjunction to sense obstacles and occlusions.

[0027] In a typical floor maintenance machine, many parameters affect the performance of the machine in a specific application. For example, a typical floor scrubbing machine has the following controls that affect cleaning performance:

[0028] Cleaning head pressure;

[0029] Cleaning solution flow rate;

[0030] Cleaning solution chemistry.

[0031] The following parameters will also change for different models of floor scrubbers:

[0032] Floor pad / brush revolutions per minute (RPM) using brushed or brushless motors (usually 75-300 RPM);

[0033] Vacuum system suction pressure;

[0034] Vacuum system flow rate.

[0035] Different types of floor cleaning or floor care equipment have even greater differences in variables:

[0036] Floor pad RPM (scrubber = 175 RPM, polisher = 1,700 RPM)

[0037] A cleaning system is disclosed that can simultaneously control multiple variables described above to optimize cleaning performance in a particular application. For example, if testing shows that the highest post-scrub gloss performance is achieved for vinyl composite tile (VCT) floors using moderate solution flow, high pad RPM, moderate down force, and low vacuum suction, the proposed system will implement that optimal combination of settings on that particular floor material.

[0038] In addition, such a system can be used as a "two-in-one" machine, replacing both a floor scrubber and a floor polisher by changing the cleaning system parameters when the polishing pad is installed (e.g., no water, very high polishing pad RPM, very light down force, turning off the vacuum system). In a further embodiment, the device can be used as a polisher by increasing the angular velocity of the polishing pad.

[0039] According to this disclosure, the right combination of settings can be chosen in a number of ways:

[0040] 1. Manual selection by the operator;

[0041] 2. Pre-programmed selections.

[0042] Figure 6 This is an exploded view of a semi-automatic device. Figure 6 The semi-automatic device 100 further includes a front sensor module 114 and a cleaning component module 108 with an exchangeable or replaceable cleaning pad.

[0043] Figure 7 300 is an exemplary workflow diagram. The workflow 300 starts with sensor information acquired at step 302. The sensor information may come from the front sensing module 114 or the rear sensing module 128 and may include images or other data streams. The front sensing module 114 may include a gloss detection sensor.

[0044] according to Figure 7 , the floor type is detected in step 302. If the floor type is an incompatible floor type (such as carpet) in step 306, the system does not clean or polish in step 308.

[0045] according to Figure 7 If the floor type is detected as a non-vinyl composite tile (VCT) hard floor at step 310, the system selects the appropriate cleaning setting based on the floor type at step 312 and starts cleaning or polishing at step 324. According to the disclosed information, the non-VCT hard floor at step 310 may include any hard floor type, including hardwood, tile, concrete, marble, and / or other known hard floor materials.

[0046] according to Figure 7If the floor type is vinyl composite tile (VCT) in step 314, the operating mode is selected in step 316. If the mode is cleaning mode in step 318, the appropriate cleaning setting is selected according to the floor type in step 312, and cleaning or polishing is started in step 324, thereby ending the workflow.

[0047] according to Figure 7 If the operation mode in step 316 is polishing in step 320, the workflow selects the appropriate polishing settings. The workflow ends by starting cleaning or polishing in step 324.

[0048] Figure 8 This is a diagram to illustrate the glossiness test of the floor. Figure 8 , showing a camera and a light source (e.g., an LED light) on a cleaning device for detecting the glossiness of a floor. The camera and the LED light shine downward on the floor and are configured to detect the glossiness and / or shininess of the floor in real time. Figure 8 , the camera may be an ESP32 camera module, and the light source may be an LED light strip. The reflection of the LED light strip on the floor surface is configured to be detected by the ESP32 camera module.

[0049] Test Results

[0050] According to the content of the present disclosure, one of the purposes of the present disclosure is to measure the gloss of a floor in an economical and effective manner using a floor cleaning system that can adjust cleaning parameters to optimize cleaning performance under specific operating conditions. Another purpose is to allow the floor cleaning system to polish the floor. Machine learning algorithms can be used to accomplish these tasks.

[0051] According to the present disclosure, the floor cleaning or polishing method is to run a machine learning algorithm on a semi-automatic cleaning device 100 (i.e., ESP32Cam). A low-cost gloss meter can be used and placed at the chassis level below the cleaning device. In order to implement the machine learning algorithm, the first step is to train the algorithm offline using a more powerful machine (i.e., a computer or cloud computer).

[0052] Data collection and data processing

[0053] According to the present disclosure, four floor images under different lighting conditions are obtained, as well as Rhopoint gloss meter measurement data for each data point. According to the present disclosure, the data collection device collects multiple data points. In order to train the algorithm, the data is divided into 90% for training and 10% for validation.

[0054] According to the present disclosure, testing was performed using a 20x20 image containing reflections of a single RGB LED. Fig. 9This is a picture of the image being cropped to reduce processing time. No post-processing is done as the RAW image sensor data is not used.

[0055] Training Algorithms

[0056] According to the present disclosure, random forest is an exemplary machine learning algorithm for this application, and of course K nearest neighbors, linear regression and neural networks can also be used. In other embodiments, these and other machine learning algorithms can be considered.

[0057] Image Processing

[0058] According to the information disclosed, once the machine learning algorithm is trained, the goal is to transfer the algorithm to the ESP32Cam and perform all processing and predictions on the board. The ESP32Cam acquires images and stores them in compressed jpg format. However, in order to train and predict with machine learning algorithms, uncompressed images are required. This can be easily achieved in Python using CV2. On the ESP32, there is a function to convert a compressed image into an RGB array. Then, the image is cropped.

[0059] return

[0060] According to the present disclosure, the MicroMLGen library was chosen because it can port decision trees and random forests into C++ header files that can run on the ESP32Cam. In other implementations, other libraries and models can also be used.

[0061] It takes about 700 milliseconds (ms) for the ESP32Cam to turn on the LED, capture an image, process the image, and make a prediction. This is over 5 times faster than the measurements collected by the Rhopoint gloss meter.

[0062] Classification and results

[0063] In one embodiment, a random forest classification model is trained. To generate labels, the measured gloss of the training data set is rounded to the nearest 2.5 GU and converted to a string. Therefore, the trained algorithm can predict the nearest 2.5 GU and make estimates within the range of gloss values ​​in the training set (20-82.5 GU).

[0064] In this embodiment, the final result is a classification algorithm trained using 35 estimators. Fig.10 Schematic diagram comparing the gloss values ​​predicted by the random forest classification method with the gloss values ​​measured by the Rhopoint gloss meter.

[0065] According to the disclosure, the proposed solution is not to differentiate between broad categories of floor materials (e.g., carpet vs. hard floor) and employ completely different cleaning methods, but rather to differentiate between floor types that are traditionally cleaned using the same method (e.g., ceramic tile and vinyl composite tile (VCT)) and fine-tune the cleaning system parameters to optimize performance.

[0066] In a further embodiment, automatic optimization can be accomplished by floor type detection machine learning (ML) algorithms. In a further embodiment, these ML algorithms can also be extended to perform floor cleanliness and floor gloss detection.

[0067] In a further embodiment, the glossiness of the floor may be detected and a glossiness map constructed in real time.

[0068] In a further embodiment, the customer can set a cleaning plan, the cleaning device automatically detects the plan, and a person (or an operator of the cleaning device) selects the plan from a graphical user interface (GUI) of the device. In a further embodiment, the plan can be selected remotely.

[0069] In further embodiments, the cleaning device can measure the cleanliness and / or glossiness of the floor behind it, and then it can decide to go back and clean an area again with optimized or more aggressive cleaning settings based on the best plan it determines. In more embodiments, the cleaning device can also create a glossiness / cleanliness map and recommend cleaning routes to customers (i.e., decide how to clean the facility by itself or execute an automated cleaning plan).

[0070] According to the present disclosure, a computer-implemented method for floor cleaning operation with adjustable cleaning parameters of a semi-autonomous cleaning device is disclosed. The method includes the following steps: receiving data from one or more sensors of the cleaning device, detecting a floor type. If the floor type is an incompatible floor type, stopping the operation of the cleaning device. If the floor type is a non-vinyl composite tile (VCT) floor type, selecting appropriate cleaning settings based on the floor type.

[0071] According to the method of the present disclosure, if the floor type is a vinyl composite tile (VCT) floor type, an operation mode is selected. If the selected operation mode is cleaning, a cleaning operation mode is selected and appropriate cleaning settings are selected. If the selected operation mode is polishing, appropriate polishing settings are selected, instructions are provided to the cleaning device to start cleaning or polishing, and instructions are sent to the cleaning component module of the cleaning device to execute the instructions.

[0072] According to the present disclosure, the sensor of the method is a front sensing module or a rear sensing module. The front sensing module or the rear sensing module of the method further includes one or more cameras. The front sensing module of the method is installed at the front of the device at an angle suitable for capturing floor sensing data, and is directed to capture floor images.

[0073] According to the present disclosure, the incompatible floor types of the method include carpet, artificial turf or grass. The stopping operation of the method further includes stopping the movement of the cleaning device and not executing the cleaning or polishing plan. The cleaning component module of the method further includes an exchangeable or replaceable cleaning pad.

[0074] According to the present disclosure, a semi-autonomous cleaning device configured for adjustable floor cleaning operation includes a frame, a processor, one or more sensing modules having at least one sensor, and a cleaning component configured for floor cleaning operation. The device is configured to select adjustable cleaning parameters for the floor cleaning operation by receiving data from one or more sensors of the cleaning device and detecting the floor type.

[0075] According to the present disclosure, if the floor type is a non-vinyl composite tile (VCT) floor type, the device selects the appropriate cleaning settings based on the floor type. If the floor type is a vinyl composite tile (VCT) floor type, the device selects an operating mode. If the selected operating mode is cleaning, the device selects the cleaning operating mode and selects the appropriate cleaning settings.

[0076] According to the present disclosure, if the selected operation mode is polishing, the device selects appropriate polishing settings. The device also provides instructions to the cleaning device to start cleaning or polishing, and sends instructions to the cleaning component modules of the cleaning device to execute the instructions.

[0077] According to the present disclosure, if the floor type of the device is an incompatible floor type, the device is further configured to stop the operation of the cleaning device. The one or more sensing modules of the device are front sensing modules or rear sensing modules. The front sensing module or rear sensing module of the device further includes one or more cameras.

[0078] According to the present disclosure, the front sensing module is mounted on the front of the device at an angle suitable for capturing floor sensing data and directed to capture floor images. Incompatible floor types of the device include carpet, artificial turf or grass.

[0079] According to the present disclosure, the stopping operation of the device further includes stopping the movement of the cleaning device and not executing the cleaning or polishing plan. The cleaning component module of the device further includes an exchangeable or replaceable cleaning pad.

[0080] The functions described herein may be stored as one or more instructions on a processor-readable medium or a computer-readable medium. The term "computer-readable medium" refers to any medium that can be accessed by a computer or a processor. For example, such a medium may include RAM, ROM, EEPROM, flash memory, CD-ROM or other optical disk storage devices, disk storage devices or other magnetic storage devices, or any other medium that can store program code in the form of instructions or data structures and can be accessed by a computer. It should be noted that computer-readable media can be tangible and non-temporary. The term "code" used herein may refer to software, instructions, code or data that can be executed by a computing device or a processor. A "module" can be considered as a processor that executes computer-readable code.

[0081] The processor described herein may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate circuit or transistor logic, a discrete hardware element, or any combination thereof, intended to perform the functions described herein. A general-purpose processor may be a microprocessor, but may also be a controller or a microcontroller, a combination thereof, or a similar device. The processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, a combination of one or more microprocessors and a DSP core, or any other such configuration. Although this article is primarily described with respect to digital technology, the processor may also primarily include analog components. For example, any signal processing algorithm described herein may be implemented in an analog circuit. In certain embodiments, the processor may be a graphics processing unit (GPU). Compared to a central processing unit (CPU), the parallel processing capabilities of a GPU may reduce the time to train and use neural networks (and other machine learning models). In some embodiments, the processor may be an ASIC, including a dedicated machine learning circuit customized for model training and / or model reasoning.

[0082] The disclosed or illustrated tasks may be distributed across multiple processors or computing devices of a computer system, including geographically distributed computing devices.

[0083] The method disclosed herein includes one or more steps or operations for implementing the method. These method steps and / or operations can be interchangeable without departing from the scope of the claims. In other words, unless the correct operation of the described method requires a specific order of steps or operations, the order and / or use of specific steps and / or operations can be modified without exceeding the scope of the claims.

[0084] As used herein, the term "plurality" refers to two or more than two. For example, a plurality of components refers to two or more than two components. The term "determining" includes a variety of operations and may include calculating, computing, processing, deriving, investigating, searching (e.g., searching in a table, database, or other data structure), determining, etc. In addition, "determining" also includes receiving (e.g., receiving information), accessing (e.g., accessing data in a memory), etc. In addition, "determining" also includes parsing, selecting, choosing, establishing, etc.

[0085] The phrase "based on" does not mean "only based on" unless expressly specified otherwise. In other words, the phrase "based on" means both "only based on" and "at least based on."

[0086] Although the above written description of the system enables a person of ordinary skill to make and use what is currently believed to be the best mode thereof, a person of ordinary skill will understand and appreciate that variations, combinations, and equivalents of the specific embodiments, methods, and examples herein exist. Therefore, the present system should not be limited to the above embodiments, methods, and examples, but should be limited to all embodiments and methods within the scope and concept of the present system. Therefore, the present disclosure is not intended to be limited to the embodiments shown herein, but should be given the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A computer-implemented method for performing a floor cleaning operation using adjustable cleaning parameters of a semi-automatic cleaning device, the method comprising the following steps: receiving data from one or more sensors of the cleaning device; Detect floor type; If the floor type is an incompatible floor type, stopping the operation of the cleaning device; If the floor type is a non-Vinyl Composite Tile (VCT) floor type: Choose the appropriate cleaning setting based on the floor type; If the floor type is Vinyl Composite Tile (VCT) floor type: Select the operating mode: If the selected operation mode is Cleaning: Select the cleaning operation mode Choose the appropriate cleaning setting; If the selected operation mode is Polishing: Choose the appropriate polishing setting; Provides instructions to cleaning equipment to initiate cleaning or polishing; and The instructions are sent to the cleaning component module of the cleaning device to execute the instructions. 2 . The method according to claim 1 , wherein the sensor is a front sensing module or a rear sensing module. 3 . The method of claim 2 , wherein the front sensing module or the rear sensing module further comprises one or more cameras.

4. The method of claim 2, wherein the front sensing module is mounted on the front of the device at an angle suitable for capturing floor sensing data and is oriented to capture floor images.

5. The method of claim 1, wherein the incompatible floor types include carpet, artificial turf, or grass.

6. The method of claim 1, wherein stopping operation further comprises stopping movement of the cleaning device and not executing a cleaning or polishing schedule.

7. The method of claim 1, wherein the cleaning assembly module further comprises an exchangeable or replaceable cleaning pad.

8. A semi-automatic cleaning device configured for adjustable floor cleaning operation, comprising: frame; processor; one or more sensing modules having at least one sensor; constructing a cleaning assembly for a floor cleaning operation; The device is configured to select adjustable cleaning parameters for a floor cleaning operation in the following manner: receiving data from one or more sensors of the cleaning device; Detect floor type; If the floor type is a non-Vinyl Composite Tile (VCT) floor type: Choose the appropriate cleaning setting based on the floor type; If the floor type is Vinyl Composite Tile (VCT) floor type: Select the operating mode: If the selected operation mode is Cleaning: Select the cleaning operation mode Choose the appropriate cleaning setting; If the selected operation mode is Polishing: Choose the appropriate polishing setting; Providing instructions to the cleaning equipment to initiate cleaning or polishing; and The instructions are sent to the cleaning component module of the cleaning device to execute the instructions.

9. The apparatus of claim 8, wherein if the floor type is an incompatible floor type, the apparatus is further configured to stop operation of the cleaning apparatus. 10 . The device of claim 8 , wherein the one or more sensing modules are front sensing modules or rear sensing modules.

11. The device of claim 8, wherein the front sensing module or the rear sensing module further comprises one or more cameras.

12. The device of claim 11, wherein the front sensing module is mounted on the front of the device at an angle suitable for capturing floor sensing data and is oriented to capture floor images.

13. The apparatus of claim 8, wherein the incompatible floor types include carpet, artificial turf, or grass.

14. The apparatus of claim 8, wherein stopping operation further comprises stopping movement of the cleaning apparatus and not executing a cleaning or polishing schedule.

15. The apparatus of claim 8, wherein the cleaning assembly module further comprises an exchangeable or replaceable cleaning pad.