Collision detection system for mobile workstation using machine learning

Abstract

A collision detection system is described that integrates machine learning algorithms to enhance the accuracy and reliability of a detection system. In addition, techniques to identify wheel issues, thereby improving the maintenance and operational efficiency of mobile workstations are described. A state machine monitors vibration patterns from the wheels during movement to detect wheel issues, such as a damaged wheel, by analyzing the motion data. Furthermore, techniques to transmit real-time data to an asset management system that may enable proactive maintenance and timely interventions are described.

Description

Attorney Docket No. 5983.542WO1COLLISION DETECTION SYSTEM FOR MOBILE WORKSTATION USING MACHINE LEARNINGCLAIM OF PRIORITY

[0001] This application claims the benefit of priority to U.S. Provisional Application Serial No. 63 / 737,562, titled “COLLISION DETECTION SYSTEM FOR MOBILE WORKSTATION USING MACHINE LEARNING'’ to Arlow Farrell et al., filed December 20, 2024, which is incorporated by reference herein in its entirety.FIELD OF THE DISCLOSURE

[0002] This document pertains generally, but not by way of limitation, to mobile workstations and, more particularly, to the operational status and maintenance needs of mobile workstations.BACKGROUND

[0003] Mobile workstations are important tools in environments where professionals need to move frequently while maintaining immediate access to equipment and information, such as in hospitals and schools. In hospitals, mobile workstations are commonly used to facilitate bedside care, allowing healthcare professionals to access electronic health records (EHR), monitor patient data, and document treatments in real-time. These workstations may also be equipped with medical devices such as vital signs monitors, barcode scanners for medication administration, and secure storage compartments for supplies and medications. Additional features such as antimicrobial surfaces, adjustable work heights, and integrated batten' systems are often included to meet the unique needs of the healthcare environment.

[0004] In educational settings, mobile workstations play an important role in supporting dynamic and collaborative learning environments. Teachers and administrators frequently use these workstations for managing lesson plans, organizing instructional materials, and delivering multimedia presentations. Workstations in this context often include built-in projectors,Attorney Docket No. 5983.542WO1 document cameras, interactive display screens, and docking stations for laptops or tablets. Some designs incorporate charging ports or hubs to power multiple devices simultaneously, ensuring uninterrupted use throughout the school day. Secure storage compartments and robust mobility mechanisms, such as durable casters, are also critical to ensuring that these workstations may be easily transported and safely used in crowded classrooms or shared spaces.SUMMARY OF THE DISCLOSURE

[0005] This disclosure describes, among other things, a collision detection system that integrates machine learning algorithms to enhance the accuracy and reliability7of these detection systems. By leveraging the capabilities of an inertial measurement unit to monitor motion of a mobile workstation, and by applying a previously trained machine learning model to analyze the motion data, the present inventors have developed a collision detection system that detects and classifies collisions. In addition, this disclosure describes techniques to identify wheel issues, thereby improving the maintenance and operational efficiency of mobile workstations. A state machine monitors vibration patterns from the wheels during movement to detect wheel issues, such as a damaged wheel, by analyzing the motion data. Furthermore, this disclosure describes techniques to transmit real-time data to an asset management system that may enable proactive maintenance and timely interventions, thereby reducing downtime and extending the lifespan of the workstations.

[0006] In some aspects, this disclosure is directed to a mobile workstation including a collision detection system for detecting a collision using a previously trained machine learning model, the mobile workstation comprising: a frame having a front, a back, a right side, and a left side; an inertial measurement unit (IMU) coupled with the frame and configured for generating motion data; and the collision detection system including: a first processor in communication with the IMU, the processor configured for: receiving the motion data from the IMU; applying the previously trained machine learning model to the motion data; using the previously trained machine learning model, identifying and classifying the collision; and inAttorney Docket No. 5983.542WO1 response to the previously trained machine learning model identifying and classifying the collision, generating and transmitting a collision signal; and a second processor configured for: receiving the collision signal, wherein the collision signal includes data representing the classification of the collision; and transmitting, in response to receiving the collision signal, an asset management signal, including the data representing the classification of the collision to an asset management system, wherein the collision detection system provides real-time collision detection and classification for the mobile workstation to the asset management system.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document.

[0008] FIG. 1 depicts an example of a mobile workstation that may implement various techniques of this disclosure.

[0009] FIG. 2 is a simplified block diagram of an example of a collision detection system for detecting a collision using a previously trained machine learning model in accordance with this disclosure.

[0010] FIG. 3 is an example of a decision tree that the previously trained machine learning model may use to implement various techniques of this disclosure.

[0011] FIG. 4 is a flow diagram of an example of a method for detecting a collision with a mobile workstation using a previously trained machine learning model using various techniques of this disclosure.

[0012] FIG. 5 is an example of a state diagram that may determine whether a wheel of a mobile workstation has an issue in accordance with this disclosure.

[0013] FIG. 6 is a flow diagram of an example of a method for detecting a collision of a mobile workstation using a previously trained machine learning model.Attorney Docket No. 5983.542WO1

[0014] FIG. 7 is a flow diagram of an example of a method for detecting a problem with a wheel of a mobile workstation.

[0015] FIG. 8 illustrates a block diagram of an example of a machine upon which any one or more of the techniques (e.g., methodologies) discussed herein may perform.DETAILED DESCRIPTION

[0016] Mobile workstations are widely used in various environments such as hospitals, schools, warehouses, and industrial settings to facilitate the movement of equipment, tools, and supplies. These workstations are often equipped with wheels to enable easy maneuverability and are designed to enhance the efficiency and productivity of the users. However, the frequent movement of these workstations in dynamic and sometimes crowded environments may lead to collisions with obstacles, walls, or other equipment. Such collisions may cause damage to the workstation.Additionally, issues with the wheels, such as becoming stuck or broken, may impede the movement of the workstation and lead to operational inefficiencies.

[0017] To address these challenges, the present inventors have recognized a need for systems configured for detecting collisions in real-time. In some examples, the systems may identify wheel issues in real-time instead of or in addition to detecting collisions. Traditional techniques for collision detection and wheel issue identification often rely on manual inspection or basic sensor systems that may not provide comprehensive and timely information.

[0018] This disclosure describes, among other things, a collision detection system that integrates machine learning algorithms to enhance the accuracy and reliability of these detection systems. By leveraging the capabilities of an inertial measurement unit to monitor motion of a mobile workstation, and by applying a previously trained machine learning model to analyze the motion data, the present inventors have developed a collision detection system that detects and classifies collisions. In addition, this disclosure describes techniques to identify wheel issues, thereby improving the maintenance and operational efficiency of mobile workstations. A state machine monitors vibration patterns from the wheels during movement toAttorney Docket No. 5983.542WO1 detect wheel issues, such as a damaged wheel, by analyzing the motion data. Furthermore, this disclosure describes techniques to transmit real-time data to an asset management system that may enable proactive maintenance and timely interventions, thereby reducing downtime and extending the lifespan of the workstations.

[0019] FIG. 1 depicts an example of a mobile workstation that may implement various techniques of this disclosure. The mobile workstation 100 is an example of a powered workstation, e.g., mobile cart, having a permanent / resident battery providing power to one or more electronic devices coupled to the workstation. The mobile workstation 100 includes a permanently installed rimary battery 102, e.g., a resident battery, to supply power to the electronic equipment and / or components of the cart. The mobile workstation 100 further includes a backup battery 104 to supply power when the charge in the primary battery 102 has been sufficiently depleted, such as below a threshold. The mobile workstation 100 includes a removable battery 106 that may supply power when the charge in both the primary battery' 102 and the backup battery' 104 has been sufficiently depleted.

[0020] A removable battery refers to a battery that is designed to be easily detached and reattached to the mobile workstation, e.g., mobile cart. This type of battery is intended for quick and convenient removal for recharging purposes, allowing users to swap out depleted batteries with fully charged ones without significant downtime. The removable battery typically features user-friendly mechanisms such as latches or connectors that facilitate its easy removal and replacement, ensuring minimal disruption to the operation of the mobile workstation.

[0021] The mobile workstation 100 includes an electrical sy stem 110. The electrical system 110 is configured for supplying power to various user peripherals, including computers, monitors, locking mechanisms, and the like. The mobile workstation 1 0 may be used in a hospital environment, for example. Other examples of mobile workstations may be used in educational or industrial environments.Attorney Docket No. 5983.542WO1

[0022] The electrical system 110 is in electrical communication with an inertial measurement unit 112 (IMU). The inertial measurement unit 112 is coupled with a frame 114 of the mobile workstation 100. The frame 114 includes a front 116, a back 118, a right side 120, and a left side 122. The inertial measurement unit 112 is configured for generating motion data of the mobile workstation 100. The inertial measurement unit 112 includes a multi-axis accelerometer to measure linear acceleration. In some examples, the inertial measurement unit 112 includes a multi-axis gyroscope to detect angular velocity or rotational rates, such as to detect an orientation and generate orientation data. As described in more detail below, a processor may receive the motion data from the IMU, apply a previously trained machine learning model to the motion data, and using the previously trained machine learning model, identify and classify a collision with the mobile workstation 100, such as a collision to the front 116, back 118, right side 120, or left side 122.

[0023] The mobile workstation 100 further includes a plurality of wheels 124, such as a part of a caster or other wheel assembly, coupled with the frame 114. As described in more detail below, this disclosure describes techniques to identify wheel issues, thereby improving the maintenance and operational efficiency of mobile workstations.

[0024] FIG. 2 is a simplified block diagram of an example of a collision detection system 200 for detecting a collision using a previously trained machine learning model in accordance with this disclosure. The collision detection system 200 includes the inertial measurement unit 112 of FIG. 1. The inertial measurement unit 112 includes one or both of an accelerometer 202 for generating motion data and a gyroscope 204 for generating orientation data, where the motion data and the orientation data is respect to the frame of the mobile workstation 100 of FIG. 1 to which the inertial measurement unit 112 is coupled. For example, a collision with the mobile workstation 100 of FIG. 1 may result in the accelerometer 202 generating motion data. In some examples, a collision with the mobile workstation 100 may additionally result in the gyroscope 204 generating motion data.Attorney Docket No. 5983.542WO1

[0025] The inertial measurement unit 112 includes or is in communication with a processor 206. The processor 206 is configured for executing a first set of instructions that implement a previously trained machine learning model (ML model), e.g., the ML model 208, and / or a second set of instructions that define a finite state machine (FSM), e.g., the FSM 210. The processor 206 is configured for receiving the motion and / or orientation data from the IMU, such as the motion data from the accelerometer 202 and the orientation data from the gyroscope 204.

[0026] The processor 206 is configured for applying the previously trained ML model 208 to the motion and / or orientation data. Using the previously trained ML model 208, the processor 206 is configured for identifying and classifying the collision.

[0027] For example, the previously trained ML model 208 identifies collisions, such as by continuously sampling motion data from the IMU, e.g., every 38 milliseconds. The collision detection system 200 and, in particular, the ML model 208 may be trained through deliberate impacts of the mobile workstation 100 against walls, doors, workstations, and other objects to establish characteristic patterns for different types of collisions with the mobile workstation. In some examples, the collision detection system 200 includes a communications interface 214 that may receive training data that the processor 206 may use to update the ML model 208.

[0028] During operation when the inertial measurement unit 112 captures motion data that matches the trained collision patterns, the ML model 208 may identify and distinguish a collision that could result in damage from a minor bump where damage is unlikely. The previously trained ML model 208 may also recognize distinct signature patterns for collisions at different locations of the mobile workstation, e.g., front, back, left, and right sides of the mobile workstation. That is, in addition to determining that the mobile workstation 100 had a collision, the previously trained ML model 208 is able to determine the impact location on the mobile workstation 100.

[0029] When the ML model 208 determines that the motion data and / or orientation data substantially match a collision pattern, the ML model 208 classifies the specific type of collision and the processor 206 stores thisAttorney Docket No. 5983.542WO1 classification in a location of the registers 212. For example, the processor 206 may store values from 0 to 4 to indicate no collision, back collision, right side collision, front collision, or left side collision, respectively.

[0030] In response to the previously trained ML model 208 identifying and classifying the collision, the processor 206 generates and transmits a collision signal 230, such as an interrupt signal, that is sent to the interrupt manager 216, which routes the collision signal 230 to the processor 218. The processor 206 triggers the collision signal 230 when the detected pattern from the data of the accelerometer 202 and / or the gyroscope 204 matches the patterns used to train the ML model 208. In some examples, the ML model 208 may filter out certain types of impacts. For example, impacts to the base of the mobile workstation 100 that do not match the trained collision patterns may be ignored.

[0031] The processor 218 is configured for receiving the collision signal 230, such as via the interrupt manager 216. The collision signal includes data representing the classification of the collision, such as a code representing a collision to the front, back, left side, or right side. The interrupt manager 216 retrieves the code from one or more of the registers 212 and transmits the collision signal 230 to the processor 218 via a communication link 236.

[0032] In response to receiving the collision signal, the processor 218 transmits an asset management signal 232, including the data representing the classification of the collision to a remote computing device 226 of an asset management system 234 via a communication link 228. For example, the processor 218 transmits the asset management signal 232 to a system-on- module 220 on the mobile workstation 100. The system-on-module 220 includes a processor 222 and one or more transceivers 224. The processor 222 embeds or encapsulates the data into a packet and transmits the packet via the transceivers 224 to the remote computing device 226.

[0033] In some examples, the transceivers 224 include a wireless communication device configured to receive the asset management signal 232 via a wireless communication link 228. As an example, the transceivers 224 include a Bluetooth low energy (BLE) device for wireless transmissionAttorney Docket No. 5983.542WO1 of data. In some examples, the wireless communication device, e.g.. a BLE device, forms part of a mesh network. Additionally or alternatively, the transceivers 224 include a WiFi device for wireless transmission of data. For example, the system-on-module 220 transmits the packet via WiFi over the communication link 228 to the remote computing device 226. In this manner the collision detection system 200 provides real-time collision detection and classification for the mobile workstation 100 to the asset management system 234.

[0034] In some examples, a register of the registers 212 stores data that identifies the mobile workstation 100, e.g., a unique identifier. The interrupt manager 216 may transmit the data that identifies the mobile workstation 100 over the communication link 236 to the processor 218 and processor 218 may include the data that identifies the mobile workstation in the asset management signal 232. In addition, one or more registers of the registers 212 may store data representing one or both of a time and date of the collision and a floor location of the mobile workstation 100.

[0035] The asset management system 234 and. in particular, the remote computing device 226 receives the asset management signal 232 via the communication link 228. The remote computing device 226 may include one or more computing devices that, in some examples, may be co-located. The asset management system 234 extracts the collision data in the asset management signal 232 and processes the collision data to support fleet management and maintenance of the mobile workstations. When a collision occurs, the asset management system 234 receives detailed information, such as the time of collision, floor location, cart identification, and specific impact location (left, right, front, or back of cart).

[0036] The asset management system 234 helps identify potential maintenance needs by detecting collisions that could lead to mechanical breakage or wear and tear on the cart. The asset management system 234 provides visibility into these collisions so that reliance on workers reporting these incidents is unnecessary'. The asset management system 234 processes the collision information to support fleet management decisions, allowing maintenance teams to proactively address potential equipment issues beforeAttorney Docket No. 5983.542WO1 they result in failures that could impact the workplace, e.g.. clinical operations.

[0037] In some examples, the remote computing device 226 is configured to display the collision data from the asset management signal 232 on a graphical user interface 238 integrated into or coupled to the remote computing device 226. For example, the remote computing device 226 presents a visual representation of the mobile workstation showing the specific impact location on the frame.

[0038] In some examples, the remote computing device 226 is configured to generate and display an alert notification on the user interface 238 when the collision data indicates damage requiring maintenance inspection. The remote computing device 226 may store the collision data in a database and automatically populate maintenance scheduling fields in the user interface 238 based on the classification of the collision and predetermined maintenance protocols.

[0039] In some examples, the remote computing device 226 may process the asset management signal 232 to generate visual reports displayed on the user interface 238, such as showing collision frequency patterns for individual mobile workstations over specified time periods. In some examples, the remote computing device 226 converts the collision data into graphical charts displayed on a dashboard interface showing collision trends by location and time.

[0040] In some examples, the remote computing device 226 automatically generates work orders in a maintenance management system based on the collision classification data received in the asset management signal 232.

[0041] In some examples, the remote computing device 226 displays the floor location data from the asset management signal 232 on an interactive facility map interface, such as displayed on user interface 238, which marks collision locations with visual indicators.

[0042] FIG. 3 is an example of a decision tree 300 that the previously trained machine learning model may use to implement various techniques of this disclosure. In some examples, the ML model 208 of FIG. 2 implementsAttorney Docket No. 5983.542WO1 a decision tree 300 for detecting and classifying collisions involving the mobile workstation 100 of FIG. 1.

[0043] In the non-limiting example shown in FIG. 3, the decision tree 300 first evaluates whether a front collision has occurred at step 302. If yes, it triggers a collision signal, e.g., an interrupt signal, at step 304. If no. it proceeds to check for a right collision at step 306, triggering an interrupt signal if detected at step 308. If no right collision is detected, it checks for a back collision at step 310, again triggering an interrupt if detected at step 312. Finally, if no back collision is detected, it checks for a left collision at step 314 and triggers an interrupt if detected at step 316. If no collisions are detected through this sequence, the outcome is classified as no collision at step 318.

[0044] The inertial measurement unit 112 of FIG. 2 continuously samples data from the accelerometer 202 and / or gyroscope 204 of FIG. 2, such as every 38 milliseconds. The ML model 208 analyzes the data against collision patterns established during its training, where the ML model 208 learned to recognize characteristic signatures for impacts from different directions, such as by deliberately impacting a mobile workstation against walls, doors, and other objects. The ML model 208 distinguishes between significant collisions and minor impacts by comparing the detected motion patterns against these trained parameters.

[0045] FIG. 4 is a flow diagram of an example of a method 400 for detecting a collision with a mobile workstation using a previously trained machine learning model using various techniques of this disclosure. The method 400 begins with IMU power-up at block 402, followed by a check for additional training data at block 404. If there is new training data ("YES" branch of block 404), the training data is added to the registers 212 of FIG. 2, such as over I2C communication via the communications interface 214. If there is no additional training data ("NO" branch of block 404), then the inertial measurement unit 112 of FIG. 2 begins sampling at block 406, such as every 38 milliseconds.

[0046] When sampling occurs, the collision detection system 200 of FIG. 2 and, in particular, the ML model 208 evaluates for possible collisions atAttorney Docket No. 5983.542WO1 block 408. If no collision is detected ("NO" branch of block 408), the process returns to sampling at block 406. If a possible collision is detected ("YES" branch of block 408), the ML model 208 of the collision detection system 200 further evaluates the data at block 410, such as using the decision tree 300 of FIG. 3, which for brevity7will not be described again.

[0047] If the ML model 208 determines that there was no collision ("NO" branch of block 412), then the process returns to sampling at block 406. If the ML model 208 determines that there was a collision ("YES" branch of block 412), then the collision detection system 200 generates a collision signal at block 414, e.g., triggers an interrupt. This triggers a sequence in which, at block 416, the processor 218 of FIG. 2 requests the collision data stored in the registers 212 of the inertial measurement unit 112 and the IMU sends the collision data. Then, at block 418, the processor 218 transmits the data to the system-on-module 220, which then transmits the data to the asset management system 234 including the remote computing device 226 of FIG. 2.

[0048] As mentioned above, in addition to the collision detection techniques described above, this disclosure describes techniques to identify wheel issues, such as with one or more wheels 124 of the mobile workstation 100 of FIG. 1, thereby improving the maintenance and operational efficiency of mobile workstations. As described in more detail below, the mobile workstation, such as the mobile workstation 100 of FIG. 1, includes a system for detecting wheel malfunctions by monitoring characteristic vibration patterns during movement of the mobile workstation.

[0049] FIG. 5 is an example of a state diagram 500 that may determine whether a wheel of a mobile workstation has an issue in accordance with this disclosure. A finite state machine transitions between the states shown in the state diagram 500, where the states monitor acceleration values against predetermined thresholds to detect wheel malfunctions. A processor is configured for executing instructions that implement the FSM. For example, the processor 206 of FIG. 2 is configured for executing the instructions that implement the FSM 210. Using the FSM, the collision detection system 200 of FIG. 2 analyzes motion data, such as acceleration data from theAttorney Docket No. 5983.542WO1 accelerometer 202 of FIG. 2, across multiple axes, e.g., X, Y, and Z axes, to identify patterns, e.g., characteristic vibration signatures, that indicate potential wheel issues such as a damaged wheel.

[0050] Referring to the state diagram 500, at state 502, the FSM sets a counter to 0. To go from the state 502 to the next state 504, the FSM checks to see if the acceleration on the X, Y, and / or Z axes is above an upper threshold value, such as after approximately 15 samples at 26 Hertz (Hz). If the acceleration is not above the threshold ("NO" branch of state 504), then the FSM resets to the state 502. If it is above the threshold ("YES" branch of state 504), then the FSM goes to the next state 506, where the FSM checks to see if the acceleration values go below a lower threshold value, such as after 15 samples at 26 Hertz (Hz).

[0051] If the acceleration is not below the threshold ("NO" branch of state 506), then the FSM resets to the state 502. If the acceleration is below the threshold ("YES" branch of the state 506), then the FSM goes to the state 508, where the counter is increased, and then back to the state 504. This process of checking whether the acceleration is above a threshold and then below a threshold is repeated a number of times until a counter limit is reached, such as ten times, and is used to detect a pattern of vibration.

[0052] If the acceleration is below the threshold and the counter limit has been reached, then the upper and lower threshold conditions have been met and the FSM goes to the state 510. At the state 510, the FSM causes the processor 206 to write to an FSM output register of the registers 212 and, at state 512. generates a wheel issue signal such as the collision signal 230, e.g., an interrupt signal, to indicate a wheel problem has been detected, and send the wheel issue signal to the processor 218 via the communication link 236. Such an instance of the collision signal 230 represents an indication of a possible problem with at least one of the wheels, such as a damaged wheel. The FSM then returns to the first state 502.

[0053] The processor 218 receives the wheel issue signal, namely the collision signal 230, where the wheel issue signal includes data representing the identified wheel problem. In response to receiving the wheel issue signal, the processor 218 increases an internal counter. In order to minimizeAttorney Docket No. 5983.542WO1 false positives for the FSM, such as when the mobile workstation merely rolls over a patch of rough floor, the processor 218 records how many times the FSM reports a possible problem with a wheel.

[0054] In response to receiving the wheel issue signal, such as if this occurs ten times, then the processor 218 transmits a maintenance alert signal, such as the asset management signal 232, to the system-on-module 220, which is an indication that something might be wrong with one of the wheels 124. The maintenance alert signal may include data representing the identified wheel problem. The system-on-module 220 then relays the asset management signal 232 to the remote computing device 226. However, if the mobile workstation begins to move normally again, e.g., with no abnormal vibrating patterns, the processor 218 resets the internal counter. In some examples, the counter in the state diagram 500 is separate from the internal counter in the processor 218.

[0055] FIG. 6 is a flow diagram of an example of a method 600 for detecting a collision of a mobile workstation using a previously trained machine learning model. At block 602, the method 600 includes receiving the motion and / or orientation data from the IMU. For example, the processor 206 receives acceleration data from the accelerometer 202 and / or orientation data from the gyroscope 204 of the inertial measurement unit 112.

[0056] At block 604, the method 600 includes applying a previously trained machine learning model to the motion and / or orientation data. For example, the processor 206 applies the previously trained ML model 208 to the motion and / or orientation data.

[0057] At block 606, the method 600 includes using the previously trained machine learning model to identify and classify the collision. For example, the ML model 208 identifies that a collision with the mobile workstation has occurred, such as the mobile workstation 100 of FIG. 1, and then classifies the collision as a front, back, left side, or right side collision.

[0058] At block 608, in response to the previously trained machine learning model identifying and classifying the collision, the method 600 generates and transmits a collision signal. For example, in response to the ML modelAttorney Docket No. 5983.542WO1208 identifying and classifying a collision, the processor 206 generates an and transmits the collision signal 230.

[0059] At block 610, the method 600 includes receiving the collision signal, where the collision signal includes data representing the classification of the collision. For example, the processor 218 receives the collision signal 230, which includes data indicating whether the collision was a front, back, left side, or right side collision.

[0060] At block 612, the method 600 includes transmitting, in response to receiving the collision signal, an asset management signal, including the data representing the classification of the collision to a computing device of an asset management system. For example, in response to receiving the collision signal 230, the processor 218 transmits an asset management signal 232 to the remote computing device 226 of the asset management system 234. The method 600 provides real-time collision detection and classification for the mobile workstation to the asset management system.

[0061] FIG. 7 is a flow diagram of an example of a method 700 for detecting a problem with a wheel of a mobile workstation. At block 702, the method 700 includes analyzing the acceleration data, such as over a specified distance, e g., 9 feet, to identify patterns indicative of a problem with at least one of the wheels, such as a damaged wheel. For example, the FSM 210 of FIG. 2 analyzes the acceleration data from the accelerometer 202, such as using the state 502 of FIG. 5.

[0062] At block 704. the method 700 includes generating and transmitting a wheel issue signal when a wheel problem is detected. For example, the processor 206 generates and transmits the collision signal 230 in FIG. 2 when the FSM 210 detects or determines that there is a wheel problem, e.g., a damaged wheel.

[0063] At block 706, the method 700 includes receiving the wheel issue signal. For example, the processor 218 receives the collision signal 230 of FIG. 2, which indicates possible damage to one or more of the wheels 124 of the mobile workstation 100.

[0064] At block 708, the method 700 includes transmitting, in response to receiving the wheel issue signal, a maintenance alert signal to the computingAttorney Docket No. 5983.542WO1 device of the asset management system. For example, in response to receiving the collision signal 230, the processor 218 transmits the asset management signal 232, to the remote computing device 226 of the asset management system 234, which includes data indicating that there is problem with one of the wheels 124 of the mobile workstation 100.

[0065] FIG. 8 illustrates a block diagram of an example of a machine upon which any one or more of the techniques (e.g., methodologies) discussed herein may perform. In alternative embodiments, the machine 800 may operate as a standalone device or are connected (e.g., networked) to other machines. In a networked deployment, the machine 800 may operate in the capacity of a server machine, a client machine, or both in server-client network environments. In an example, the machine 800 may act as a peer machine in peer-to-peer (P2P) (or other distributed) network environment. The machine 800 is a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile telephone, a smart phone, a web appliance, a network router, switch or bridge, a server computer, a database, conference room equipment, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by that machine. In various embodiments, machine 800 may perform one or more of the processes described above. Further, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations.

[0066] Examples, as described herein, may include, or may operate on. logic or a number of components, modules, or mechanisms (all referred to hereinafter as “modules”). Modules are tangible entities (e.g., hardware) capable of performing specified operations and is configured or arranged in a certain manner. In an example, circuits are arranged (e.g., internally or with respect to external entities such as other circuits) in a specified manner as a module. In an example, the whole or part of one or more computer systems (e g., a standalone, client or server computer system) or one or more hardware processors are configured by firmware or software (e.g.,Attorney Docket No. 5983.542WO1 instructions, an application portion, or an application) as a module that operates to perform specified operations. In an example, the software may reside on a non-transitory computer readable storage medium or other machine readable medium. In an example, the software, when executed by the underlying hardware of the module, causes the hardware to perform the specified operations.

[0067] Accordingly, the term “module” is understood to encompass a tangible entity7, be that an entity that is physically constructed, specifically configured (e.g., hardwired), or temporarily (e.g., transitorily) configured (e.g., programmed) to operate in a specified manner or to perform part or all of any operation described herein. Considering examples in which modules are temporarily configured, each of the modules need not be instantiated at any one moment in time. For example, where the modules comprise a general-purpose hardware processor configured using software, the general- purpose hardware processor is configured as respective different modules at different times. Software may accordingly configure a hardware processor, for example, to constitute a particular module at one instance of time and to constitute a different module at a different instance of time.

[0068] Machine (e.g., computer system) 800 may include a hardware processor 802 (e g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 804, and a static memory 806, some or all of which may communicate with each other via an interlink 808 (e.g., bus). The machine 800 may further include a display unit 810, an alphanumeric input device 812 (e.g., a keyboard), and a user interface (UI) navigation device 814 (e.g., a mouse). In an example, the display unit 810, input device 812 and UI navigation device 814 are a touch screen display. The machine 800 may additionally include a storage device (e.g., drive unit) 816, a signal generation device 818 (e.g., a speaker), a network interface device 820, and one or more sensors 821, such as a global positioning system (GPS) sensor, compass, accelerometer, or other sensor. The machine 800 may include an output controller 828, such as a serial (e.g., universal serial bus (USB), parallel, or other wired or wireless (e.g., infrared (IR), near fieldAttorney Docket No. 5983.542WO1 communication (NFC), etc.) connection to communicate or control one or more peripheral devices (e.g.. a printer, card reader, etc.).

[0069] The storage device 816 may include a machine readable medium 822 on which is stored one or more sets of data structures or instructions 824 (e g., software) embodying or utilized by any one or more of the techniques or functions described herein. The instructions 824 may also reside, completely or at least partially, within the main memory 804, within static memory 806, or within the hardware processor 802 during execution thereof by the machine 800. In an example, one or any combination of the hardware processor 802, the main memory 804, the static memory 806, or the storage device 816 may constitute machine readable media.

[0070] While the machine readable medium 822 is illustrated as a single medium, the term "machine readable medium" may include a single medium or multiple media (e g., a centralized or distributed database, and / or associated caches and servers) configured to store the one or more instructions 824.

[0071] The term “machine readable medium” may include any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 800 and that cause the machine 800 to perform any one or more of the techniques of the present disclosure, or that is capable of storing, encoding or carrying data structures used by or associated with such instructions. Non-limiting machine readable medium examples may include solid-state memories, and optical and magnetic media. Specific examples of machine readable media may include: non-volatile memory, such as semiconductor memory devices (e.g., Electrically Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM)) and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; Random Access Memory (RAM): Solid State Drives (SSD); and CD-ROM and DVD-ROM disks. In some examples, machine readable media may include non- transitory machine readable media. In some examples, machine readable media may include machine readable media that is not a transitory propagating signal.Attorney Docket No. 5983.542WO1

[0072] The instructions 824 may further be transmitted or received over a communications network 826 using a transmission medium via the network interface device 820. The machine 800 may communicate with one or more other machines utilizing any one of a number of transfer protocols (e.g., frame relay, internet protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks may include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), mobile telephone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks (e.g., Institute of Electrical and Electronics Engineers (IEEE) 802. 11 family of standards known as Wi-Fi®, IEEE 802.16 family of standards known as WiMax®), IEEE 802.15.4 family of standards, a Long Term Evolution (LTE) family of standards, a Universal Mobile Telecommunications System (UMTS) family of standards, peer-to-peer (P2P) networks, among others. In an example, the network interface device 820 may include one or more physical jacks (e.g., Ethernet, coaxial, or phonejacks) or one or more antennas to connect to the communications network 826. In an example, the network interface device 820 may include a plurality of antennas to wirelessly communicate using at least one of single-input multiple-output (SIMO), multiple-input multipleoutput (MIMO), or multiple-input single-output (MISO) techniques. In some examples, the network interface device 820 may wirelessly communicate using Multiple User MIMO techniques.

[0073] Examples, as described herein, may include, or may operate on, logic or a number of components, modules, or mechanisms. Modules are tangible entities (e.g., hardware) capable of performing specified operations and are configured or arranged in a certain manner. In an example, circuits are arranged (e.g., internally or with respect to external entities such as other circuits) in a specified manner as a module. In an example, the whole or part of one or more computer systems (e.g., a standalone, client, or server computer system) or one or more hardware processors are configured by firmware or software (e.g., instructions, an application portion, or an application) as a module that operates to perform specified operations. In an example, the software may reside on a machine-readable medium. In anAttorney Docket No. 5983.542WO1 example, the software, when executed by the underlying hardware of the module, causes the hardware to perform the specified operations.

[0074] Accordingly, the term “module” is understood to encompass a tangible entity, be that an entity that is physically constructed, specifically configured (e.g., hardwired), or temporarily (e.g., transitorily) configured (e.g., programmed) to operate in a specified manner or to perform part or all of any operation described herein. Considering examples in which modules are temporarily configured, each of the modules need not be instantiated at any one moment in time. For example, where the modules comprise a general-purpose hardware processor configured using software, the general- purpose hardware processor is configured as respective different modules at different times. Software may accordingly configure a hardware processor, for example, to constitute a particular module at one instance of time and to constitute a different module at a different instance of time.

[0075] Various embodiments are implemented fully or partially in software and / or firmware. This software and / or firmware may take the form of instructions contained in or on a non-transitory computer-readable storage medium. Those instructions may then be read and executed by one or more processors to enable performance of the operations described herein. The instructions are in any suitable form, such as but not limited to source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. Such a computer- readable medium may include any tangible non-transitory medium for storing information in a form readable by one or more computers, such as but not limited to read only memory' (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory; etc.Various Notes

[0076] Each of the non-limiting claims or examples described herein may stand on its own, or may be combined in various permutations or combinations with one or more of the other examples.

[0077] The above detailed description includes references to the accompanying drawings, which form a part of the detailed description. The drawings show, by way of illustration, specific embodiments in which theAttorney Docket No. 5983.542WO1 invention may be practiced. These embodiments are also referred to herein as 'examples." Such examples may include elements in addition to those shown or described. However, the present inventors also contemplate examples in which only those elements shown or described are provided. Moreover, the present inventors also contemplate examples using any combination or permutation of those elements shown or described (or one or more claims thereof), either with respect to a particular example (or one or more claims thereof), or with respect to other examples (or one or more claims thereof) shown or described herein.

[0078] In the event of inconsistent usages between this document and any documents so incorporated by reference, the usage in this document controls.

[0079] In this document, the terms “a” or “an” are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of “at least one” or “one or more.” In this document, the term “or” is used to refer to a nonexclusive or, such that “A or B” includes “A but not B,” “B but not A,” and “A and B,” unless otherwise indicated. In this document, the terms "including” and "in which” are used as the plain- English equivalents of the respective terms “comprising” and “wherein.” Also, in the following claims, the terms “including” and “comprising” are open-ended, that is, a system, device, article, composition, formulation, or process that includes elements in addition to those listed after such a term in a claim are still deemed to fall within the scope of that claim. Moreover, in the following claims, the terms “first,” “second,” and “third,” etc. are used merely as labels, and are not intended to impose numerical requirements on their objects.

[0080] Method examples described herein may be machine or computer- implemented at least in part. Some examples may include a computer- readable medium or machine-readable medium encoded with instructions operable to configure an electronic device to perform methods as described in the above examples. An implementation of such methods may include code, such as microcode, assembly language code, a higher-level language code, or the like. Such code may include computer readable instructions for performing various methods. The code may form portions of computerAttorney Docket No. 5983.542WO1 program products. Further, in an example, the code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer- readable media, such as during execution or at other times. Examples of these tangible computer-readable media may include, but are not limited to, hard disks, removable magnetic disks, removable optical disks (e.g., compact discs and digital video discs), magnetic cassettes, memory cards or sticks, random access memories (RAMs), read only memories (ROMs), and the like.

[0081] The above description is intended to be illustrative, and not restrictive. For example, the above-described examples (or one or more claims thereof) may be used in combination with each other. Other embodiments may be used, such as by one of ordinary' skill in the art upon reviewing the above description. The Abstract is provided to comply with 37 C.F.R. §1.72(b), to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Also, in the above Detailed Description, various features may be grouped together to streamline the disclosure. This should not be interpreted as intending that an unclaimed disclosed feature is essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that such embodiments may be combined with each other in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

Attorney Docket No. 5983.542WO1CLAIMSWhat is claimed is:

1. A mobile workstation including a collision detection system for detecting a collision using a previously trained machine learning model, the mobile workstation comprising: a frame having a front, a back, a right side, and a left side; an inertial measurement unit (IMU) coupled with the frame and configured for generating motion data; and the collision detection system including: a first processor in communication with the IMU, the processor configured for: receiving the motion data from the IMU; applying the previously trained machine learning model to the motion data; using the previously trained machine learning model, identifying and classifying the collision; and in response to the previously trained machine learning model identifying and classifying the collision, generating and transmitting a collision signal; and a second processor configured for: receiving the collision signal, wherein the collision signal includes data representing the classification of the collision; and transmitting, in response to receiving the collision signal, an asset management signal, including the data representing the classification of the collision to an asset management system, wherein the collision detection system provides real-time collision detection and classification for the mobile workstation to the asset management system.

2. The mobile workstation of claim 1, wherein the asset management signal includes data that identifies the mobile workstation.Attorney Docket No. 5983.542WO13. The mobile workstation of claim 1, wherein classifying the collision includes identifying the collision as one of: a front collision; a back collision; a right side collision; and a left side collision.

4. The mobile workstation of claim 1, further comprising: a wireless communication device configured to transmit the asset management signal to the asset management system.

5. The mobile workstation of claim 4, wherein the wireless communication device forms part of a mesh network.

6. The mobile workstation of claim 1, wherein the asset management signal includes at least one of: a time and date of the collision; a floor location; a mobile workstation identification; and an impact location.

7. The mobile workstation of claim 1, further comprising: a plurality of wheels coupled with the frame, wherein the IMU is configured for sampling vibration data generated from a movement of the mobile workstation; and a state machine configured for: analyzing the acceleration data over a specified distance to identify patterns indicative of a problem with at least one of the wheels; and generating and transmitting a wheel issue signal when a wheel problem is detected; wherein the second processor is further configured for: receiving the wheel issue signal; and transmitting, in response to receiving the wheel issue signal, a maintenance alert signal to the asset management system.

8. The mobile workstation of claim 7, wherein the specified distance is 9 feet.Attorney Docket No. 5983.542WO19. A method for detecting a collision of a mobile workstation, the method comprising: generating motion data using an inertial measurement unit (IMU) coupled with a frame of the mobile workstation, wherein the frame has a front, a back, a right side, and a left side; receiving, by a first processor in communication with the IMU. the motion data from the IMU; applying, by the first processor, a previously trained machine learning model to the motion data; using the previously trained machine learning model, identify ing and classifying the collision; and in response to the previously trained machine learning model identifying and classifying the collision, generating and transmitting, by the first processor, a collision signal; receiving, by a second processor, the collision signal, wherein the collision signal includes data representing the classification of the collision; and transmitting, by the second processor in response to receiving the collision signal, an asset management signal, including the data representing the classification of the collision to an asset management system, where the collision detection system provides real-time collision detection and classification for the mobile workstation to the asset management system.

10. The method of claim 9. wherein the asset management signal includes data that identifies the mobile workstation.

11. The method of claim 9, wherein classifying the collision includes identifying the collision as one of: a front collision; a back collision: a right side collision; and a left side collision.

12. The method of claim 9, further comprising: transmitting the asset management signal to the asset management system using a wireless communication device.Attorney Docket No. 5983.542WO113. The method of claim 12, wherein transmitting the asset management signal includes transmitting via a wireless communication device that forms part of a mesh network.

14. The method of claim 9, wherein the asset management signal includes at least one of: a time and date of the collision; a floor location; a mobile workstation identification; and an impact location.

15. The method of claim 9, further comprising: sampling, using the 1MU, vibration data generated from a movement of the mobile workstation over a plurality of wheels coupled with the frame; analyzing, using a state machine, the acceleration data over a specified distance to identify patterns indicative of a problem with at least one of the wheels; generating and transmitting a wheel issue signal when a wheel problem is detected; receiving, by the second processor, the wheel issue signal; and transmitting, by the second processor in response to receiving the wheel issue signal, a maintenance alert signal to the asset management system.

Images