Sentry safety system

Abstract

Certain aspects of the disclosure provide a sentry robot system configured to determine an anomaly in a zone of a medical facility and initiate a corrective action based on the anomaly in the zone of the medical facility. The anomaly is determined based on sensor information captured by one or more sensors associated with a sentry robot of the sentry robot system.

Description

Sentry Safety SystemBACKGROUNDField

[0001] Aspects of the present disclosure relate to sentry safety systems and methods, and in particular to a sentry robot configured to detect anomalies in a medical environment.Description of Related Art

[0002] Medical errors are common and can be devastating. There are many protocols, standards, procedures, and fail-safes to prevent and reduce such errors. However, some errors are more difficult to detect due to the nature of the error.

[0003] For example, an infusion pump may have a kink in the line, but the infusion pump itself continues to pump because it cannot detect the kink. Another example, the infusion pump is set to operate at a specific flow rate, but there is a problem with the pump, and it is pumping at a faster or slower flow rate.

[0004] In another example, the locking system of a medical dispensing system may be tampered with, but the medical dispensing system itself cannot detect the tampering, and thus continues to operate, however, it cannot restrict access to medication properly.

[0005] Thus, there are limitations in such devices in that not all errors may be detected by the device itself, and the device may continue to operate in a faulty manner.

[0006] In some cases, a device may detect there is an issue that needs to be addressed and make an audible alarm, however, the device is in a patient room and a clinician cannot hear it.

[0007] Accordingly, there is a need for improved systems and methods for improved detection of potential anomalies in medical environments.SUMMARY

[0008] Certain aspects provide a computer-implemented method for operating a sentry robot, comprising: directing a sentry robot to monitor a zone of a medical facility based at least in part on medical device information associated with a medical device located in the zone; obtaining information corresponding to sensor information captured by one or more sensors of the sentry robot, the sensor information corresponding to the zone of the medical facility; determining ananomaly in the zone of the medical facility based at least in part on the sensor information; and initiating a corrective action based on the anomaly in the zone of the medical facility.

[0009] Other aspects provide processing systems configured to perform the aforementioned methods as well as those described herein; non-transitory, computer-readable media comprising instructions that, when executed by a processors of a processing system, cause the processing system to perform the aforementioned methods as well as those described herein; a computer program product embodied on a computer readable storage medium comprising code for performing the aforementioned methods as well as those further described herein; and a processing system comprising means for performing the aforementioned methods as well as those further described herein.

[0010] The following description and the related drawings set forth in detail certain illustrative features of one or more aspects.DESCRIPTION OF THE DRAWINGS

[0011] The appended figures depict certain aspects and are therefore not to be considered limiting of the scope of this disclosure.

[0012] FIG. 1 depicts an example sentry system.

[0013] FIG. 2 depicts an example sentry robot.

[0014] FIG. 3 depicts an example workflow for operating a sentry robot.

[0015] FIG. 4 depicts an example workflow for determining corrective actions for an anomaly detected by a sentry robot.

[0016] FIG. 5 depicts an example method for operation a sentry robot.

[0017] FIG. 6 depicts an example computing device with which aspects of the present disclosure can be performed.

[0018] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the drawings. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.DETAILED DESCRIPTION

[0019] Aspects of the present disclosure provide apparatuses, methods, processing systems, and computer-readable mediums for a sentry robot system configured to detect anomalies associated with a medical facility.

[0020] As described herein, there are scenarios in which medical errors cannot be easily detected, especially, when the error relates to a medical device itself.

[0021] For example, in conventional operation of an infusion device, the infusion device is programed by a clinician and then the clinician leaves the patient’s room. Adverse events are then typically detected when the infusion devices itself detects and alerts the event. However, there may be adverse events which the infusion device itself cannot detect, including, incorrect set up, such as were a multi-channel infusion device is utilized and two or more of the channels are misaligned. In such a scenario, the infusion device is correctly programed, but cannot detect that channel A and channel B are swapped.

[0022] As another example, in conventional operation of a medical dispensing device, the dispensing device dispenses a medication, such as based on a medication order. However, once the medication has been dispensed, the dispending device cannot detect a subsequent adverse event, such as when the medication is diverted before being administered to the patient, too much medication is dispensed, or an incorrect medication is dispensed because the medical dispensing device was loaded incorrectly.

[0023] In such scenarios, each device appears to be operating normally to the device itself. Further, casual observation of the device cannot readily detect an adverse condition. However, when the expected conditions of a given device are known, for example, based on the infusion order or the medication order, the adverse condition may be detected.

[0024] Furthermore, in some cases, a medical device may not have functionality to detect and / or alert to an adverse condition, for example, a lost or misplaced food service cart, cleanliness of a patient room, and / or the like.

[0025] Therefore, there is a limitation in medical environments in which medical devices themselves may not be able to detect every adverse condition, as well as other adverse conditions of their environment.

[0026] Aspects described herein overcome such limitations by providing for an external sentry system configured to detect anomalies in a medical facility and, in certain aspects, initiate corrective actions. Beneficially, the sentry system may be distinct and / or separated from one or more medical devices in the medical environment, such that it may detect anomalies not detectable by the medical device itself. Further, the sentry system may detect other anomalies in the medical environment not detectable by the medical device.

[0027] In certain embodiments described herein, a sentry robot may be configured to use one or more sensors to capture information corresponding to aspects of the medical environment, whereby an anomaly may be detected. In some embodiments, the sentry robot may be navigable, such that the sentry robot is configured to navigate through one or more zones of the medical environment to sense aspects of the medical environment. For example, a sentry robot may be configured to navigate to a patient room to capture aspects related to an infusion device.

[0028] In certain embodiments described herein, the sentry system may interface and / or integrate with a medication ordering system, electronic medical record system, or other medical facility system, such that an expected state of the medical facility may be determined. For example, the sentry system may be configured to interface with a medication ordering system, whereby the sentry system may determine expected operational conditions of an infusion system. Beneficially, this enables the sentry system to detect an anomaly based on a determined difference between the expected conditions and the conditions observed by the sentry robot.

[0029] Furthermore, in certain embodiments described herein, the sentry system is configured to determine and initiate one or more corrective actions based on the detected anomaly. In certain aspects, the sentry system may alert a clinician or medical environment staff regarding an anomaly that may otherwise go undetected until an adverse event, thereby earlier intervention and correction may occur.

[0030] In some embodiments, a corrective action may include adjusting operations of a medical device, which may correct an anomaly on the medical device. For example, where an anomaly is associated with incorrect operations of an infusion device, the infusion device operations may be stopped or paused, such as until clinician intervention. Thus, aspects described herein enable earlier detection and, in certain aspects, correction of anomalies in a medical environment.Example Sentry System

[0031] FIG. 1 depicts an example sentry system 100 to facilitate operations of a sentry robot 110 configured to detect and / or correct anomalies in a medical facility. Sentry system 100 is configured to implement systems and methods, for example, workflow 300 in FIG. 3, workflow 400 in FIG. 4 and / or method 500 in FIG. 5, to detect and / or correct anomalies in the medical facility.

[0032] Sentry robot 110 is configured to detect anomalies within a medical facility. Sentry robot 110 includes a navigation component 112 configured to control movement and navigate sentry robot 110 throughout the medical facility. Sentry robot 110 includes one or more motors 120 configured to move sentry robot 110, for example, by rolling, flying, etc. Sentry robot 110 further includes power source 122 configured to power sentry robot 110, include the one or more motors 120. Sentry robot 110 includes one or more sensors 114 configured to sense one or more aspects of the medical facility. Sentry robot 110 includes one or more processors 118 configured to execute instructions stored in one or more memories 116 to operate sentry robot 110. Sentry robot 110 further includes communications component 124 to communicate (e.g., send and / or receive), directly or indirectly via one or more other devices with sentry server 130, such as using network 104 (e.g., a local area network (LAN), internet, etc.). Though sentry robot 110 is shown as including certain components, it should be understood that sentry 110 may not include certain components, or may include additional components.

[0033] Sentry server 130 includes communications component 140, configured to communicate, directly or indirectly, such as using network 104, with sentry robot 110. Sentry server 130 includes one or more processors 134 configured to execute instructions stored in one or more memories 138 to perform one or more operations of sentry server 130. Sentry server 130 further includes routing component 132 configured to determine a route for sentry robot 110, for example, a route through the medical facility, a destination within the medical facility, etc. Routing component 132 may be further configured to generate a map of the medical facility, and one or more zones of the medical facility based on the map, using sensor information captured by sentry robot 110, and communicated to sentry server 130.

[0034] Sentry server 130 further includes an analytics component 136 configured to make one or more determinations, for example, to detect an anomaly in the medical facility based on sensor information captured by sentry robot 110. Sentry server 130 may store analytics data in analytics database 144, for example related to one or more determinations made by analytics component136. Though sentry server 130 is shown separate from sentry robot 110, in certain embodiments, one or more components of sentry server 130 may be part of sentry robot 110, such that sentry robot 110 may perform one or more functions of sentry server 130 discussed herein.

[0035] In certain aspects, sentry robot 110 and / or sentry server 130 may further communicate, directly or indirectly, such as via network 104, with medical facility information system 108, e.g., including one or more of one or more computing devices, a database, etc. For example, medical facility information system may transmit data related to the medical facility, including information stored in patient database 128. Patient data stored in patient database 128 may include electronic medical records (“EMRs”) for patients associated with the medical facility, such as medication orders, treatment, diagnosis, medical history, or the like or combinations thereof.

[0036] Infusion device 102 is an electromechanical device for infusing therapeutic fluids into a patient in a controlled and precise manner. Exemplary infusion devices may include a syringe pump, a patient-controlled analgesia pump, or a large volume pump. In general operation, therapeutic fluid is loaded into an infusion device, for example, in a syringe, bottle, bag, or other storage container, and the infusion device is configured to pump, or infuse, the therapeutic fluid according to operational parameters of the device, including, for example, flow rate, volume, or time to administer a specific dose of treatment or combinations thereof. Infusion device 102 is further configured to transmit data related to the infusion, for example, infusion parameters, infusion data, operational data, or the like or combinations thereof. Such data may also be stored in infusion database 142.

[0037] Dispensing device 106 is a medical dispensing system for securing and controlling access to medications and / or medical devices in a medical environment. Dispensing devices may include automated dispensing cabinets. In general operation, medication and / or medical devices are contained within the dispensing device, for example, in a cabinet, drawer, or other storage container, and the dispensing device is configured to lock or otherwise restrict access to the medication or medical devices. The dispensing device 106 may be unlocked and accessed with a key or code, or for some devices, through user authentication and authorization. Dispensing device 106 is further configured to transmit data related to dispensing of items, for example, medication or medical device data, user data, access data, dispense data, or the like or combinations thereof.

[0038] Though certain components of sentry system 100 are shown as separate components in communication with one another, such as using network 104, any components may be furthersplit into separate components or integrated into a single component as appropriate. Further, sentry system 100 may have fewer or additional components than shown in FIG. 1.Example Sentry Robot

[0039] FIG. 2 depicts an example block diagram of a sentry robot 200 (e.g., corresponding to sentry robot 110) according to embodiments described herein. Sentry robot 200 is configured to operate in a medical facility. Though sentry robot 200 is shown as including certain components, it should be understood that sentry 200 may not include certain components, or may include additional components.

[0040] Sentry robot 200 comprises one or more sensors 202 configured to sense one or more aspects of a medical facility. Exemplary sensors 202 include camera 204, ultraviolet camera 206, thermal camera 208, Doppler ultrasonic sensor 210, microphone 212, accelerometer 214, location sensor 216, or speaker 218. In certain aspects, a sentry robot described herein may include additional or fewer sensors 202.

[0041] Camera 204 is configured to capture images and / or video of a medical facility. Ultraviolet camera 206 is configured to capture ultraviolet images and / or video of the medical facility. Thermal camera 208 is configured to capture thermal images and / or video of the medical facility. Doppler ultrasonic sensor 210 is configured to use soundwaves to image the medical facility, such as to measure fluid flow. Microphone 212 is configured to capture sound of the medical facility. Accelerometer 214 is configured to capture vibration of the medical facility. Location sensor 216 is configured to capture a location of the sentry robot in the medical facility, for example, through a position sensor, a global positioning system (GPS) sensor, etc. Speaker 218 is configured to emit sounds out of sentry robot 200.

[0042] Sensors 202 are configured to generate sensor information corresponding to a zone of a medical facility. For example, GPS data or other local positioning data may be used to identify coordinates of a location within a facility that are associated with a particular care area (e.g., zone). As another example, a camera may be used to capture images within the medical facility and identify the zone based on analysis of one or more of the images.

[0043] Sentry robot 200 further comprises a detecting component 230 configured to make one or more determinations, for example, based on the sensor information captured by sensors 202. Detecting component 230 comprises one or more rules 236 and / or one or more models 238, which may be used by detecting component 230. In some embodiments, sensor information may beprocessed to detect one or more aspects of the zone of the medical facility, for example, through image-based detection, acoustic-based detection, thermal image-based detection, ultraviolet image-based detection, or ultrasonic Doppler-based detection or a combination thereof.

[0044] Detecting component 230 is configured to determine an anomaly in the zone of the medical facility, such as based on the sensor information. Detecting component 230 may be configured to detect a current state of the zone of the medical facility, determine an expected state of the zone of the medical facility, and detect the anomaly between the current state of the zone of the medical facility and the expected state of the zone of the medical facility.

[0045] In some embodiments, detecting component 230 is configured to determine the expected state of the zone of the medical facility based on external data, for example, a medication order associated with a patient in the zone of the medical facility, or a reference state for one or more devices associated with the zone of the medical facility.

[0046] In some embodiments, detecting component 230 is configured to detect a current state of the zone of the medical facility and detect an anomaly in the current state of the zone of the medical facility based on processing the current state of the medical facility with one or more machine learning models 238.

[0047] Detecting component 230 may be further configured to determine one or more corrective actions based on the anomaly in the zone of the medical facility, for example, as described with respect to workflow 400 in FIG. 4.

[0048] In some embodiments, detecting component 230 is configured to determine the sensor information corresponds to sensitive data and the sentry robot stops capturing the sensor information based on determining the sensor information corresponds to sensitive data. In some aspects, detection component 230 may be in another device communicatively coupled to sentry robot 200, such as sentry server 130 in FIG. 1.

[0049] Sentry robot 200 comprises navigation component 220 configured to navigate sentry robot 200 to one or more zones of a medical facility. Navigation component 220 may be configured to navigate sentry robot 200 based on a map of the one or more zones of the medical facility. The map may be generated by navigation component 220, for example, as sentry robot 200 explores the one or more zones of the medical facility. The map may be generated based on medical facility data, for example, a blueprint or engineering map of the medical facility.

[0050] Sentry robot 200 may be assigned a “home” zone of the medical facility, and navigate through various other zones of the medical facility and return to its home zone. For example, sentry robot 200 may return to its home zone based on a “go home” command. The command may be provided using an input via the sentry robot 200 such as a button or verbal command (e.g., a clinician utters a command that is recognized by the sentry robot 200).

[0051] Navigation component 220 is configured to navigate sentry robot 200 through the one or more zones of the medical facility, for example, based on values of the zones, as described below with respect to step 304 in FIG. 3. In some embodiments, navigation component 220 is configured to navigate sentry robot 200 to one or more zones of the medical facility based on a routine, for example, to navigate to a set of zones, navigate to high value zones, navigate to all zones, and / or the like.

[0052] Navigation component 220 may be further configured to propel sentry robot 200, for example, by rolling or flying. Sentry robot 200 may comprise wheels, treads, legs, arms, or rotors to propel sentry robot 200. In some cases, sentry robot 200 may be unable to navigate to a determined zone, for example, where sentry robot 200 includes one or more wheels and the determined zone is up a set of stairs. Sentry robot 200 may be configured to return to its home and / or generate an alert responsive to determining an unnavigable zone.

[0053] Sentry robot 200 further comprises messaging component 240 configured to transmit and receive communications, for example, transmit alerts, alarms, and / or the like. In some embodiments, transmitting or receiving a communication may include transmitting or receiving an indication of an alert, alarm, and / or the like. In certain aspects, messaging component 240 is further configured to transmit and receive communications comprising one or more corrective actions. In certain aspects, messaging component 240 is configured to transmit and receive communications associated with medication orders, reference states and / or the like, of the zone of the medical facility.Example Workflow for Operating a Sentry Robot

[0054] FIG. 3 depicts an example workflow 300 for operating a sentry robot, for example, sentry robot 200 in FIG. 2. In some embodiments, aspects of workflow 300 may be performed by sentry system 100 in FIG. 1.

[0055] Workflow 300 begins at step 302. Optionally at step 304, the sentry robot navigates to a zone of a medical facility, for example where the robot is self-propelling. In some embodiments,the sentry robot is not self-propelling, and workflow 300 proceeds directly to step 306. An example of a sentry robot that is not self-propelling may include a device that can be positioned in the zone such as on a wall, table, cabinet, ceiling, or other fixture.

[0056] The sentry robot may navigate to the zone of the medical facility through navigation component 220 in FIG. 2. In some embodiments, the sentry robot navigates based on a map of the medical facility, wherein the map comprises one or more zones of the medical facility, and the sentry robot navigates to the zone. For example, the sentry robot may generate a map of the medical facility by propelling through the medical facility. The sentry robot may determine multiple zones of the medical facility based on the map. As another example, a map may be generated based on medical facility data, such as provided by medical facility information system 108 in FIG. 1. Further, one or more zones of the medical facility may be determined, for example, based on one or more aspects of the medical facility. Some example zones may include a pharmacy zone, a storage zone, a nurses’ station zone, a patient room zone, a hallway zone, an intensive care unit, an emergency department, a waiting room, or the like.

[0057] The zone of the medical facility for the sentry robot to navigate to may be determined based on the sensor information to be obtained. In some embodiments, the zone is selected based on the type of sensors equipped on the sentry robot. For example, where the sensor information to be obtained in a particular zone is sound information, a sentry robot with a microphone navigates to that zone.

[0058] In some embodiments, the zone is determined based on a value associated with the zone. Each zone of the one or more zones of the medical facility is assigned a value and the value may be based on aspects of the zone. For example, a value may be based on a medication dispensed in the zone, a type of care performed in the zone, a medical device in the zone, and / or the like. Higher values may be assigned to zones where there is an increased risk, for example, of medication diversion, of medical error, less foot traffic, higher patient acuity, clinical complexity (e.g., number of infusion devices located in the zone), scheduled events in the zone (e.g., number of infusions scheduled for a zone), specific clinician(s) working within a zone or the like, or combinations thereof.

[0059] In some embodiments, the zone is determined based on a routine, for example, the sentry robot navigates to one or more zones in an order. In some examples, the sentry robot’s routine may be based on navigating to one or more high value zones, more frequently navigating to high value zones, and / or the like. The order may be identified as a preset route defined by anadministrator. The order may be identified based on machine learning based on historical clinical events. For example, a model or assessment of historical data may determine that higher risk infusions are programmed after 10 PM in a particular care area. In such instances, these areas or zones may be patrolled by the sentry robot more, or more frequently, than other locations or other times.

[0060] At step 306, the sentry robot senses the zone of the medical facility. The sentry robot may use one or more sensors to capture sensor information associated with the zone of the medical facility. In some embodiments, the sentry robot includes sensors such as a camera, e.g., camera 204, a microphone, e.g., microphone 212, a speaker, e.g., speaker 218, a thermal imaging sensor, e.g., thermal camera 208, an ultraviolet camera, e.g., ultraviolet camera 206, a Doppler ultrasonic sensor, e.g., Doppler ultrasonic sensor 210, a microphone, e.g., microphone 212, an accelerometer, e.g., accelerometer 214, or a location sensor, e.g., location sensor 216, of sensors 202 in FIG. 2. In some embodiments, the sentry robot stores the sensor information in the sentry robot memory, e.g., memory 116 in FIG. 1, or communicates the sensor information, such as to sentry server 130. The senor information may further include metadata, including time and / or location data.

[0061] In some embodiments, the sentry robot senses the zone of the medical facility based on receiving a command (being directed) to monitor the zone of the medical facility based at least in part on medical device information associated with a medical device located in the zone of the medical facility.

[0062] In some embodiments, the sentry robot is configured to not capture sensitive information in a zone. The sensor information may be determined to correspond to sensitive data, and the sentry robot stops capturing the sensor information based on this determination. In some cases, the sentry robot stops capturing one or more aspect of the zone corresponding to sensitive data. For example, sensor data associated with the patient may correspond to sensitive data, and the sentry robot stops capturing the patient, but continues to capture a medical dispensing cabinet in the zone. The sentry robot may stop capturing sensor information of a particular type corresponding to sensitive data. For example, sensor data associated with a patient’s image may correspond to sensitive data, and the sentry robot stops a camera, but continues using an acoustic sensor.

[0063] At step 308, the sentry robot, or sentry server, determines if there is an anomaly in the zone of the medical facility. An anomaly may be determined based on comparing the current state of the zone of the medical facility with the expected state of the zone of the medical facility. Thecurrent state of the zone of the medical facility may be determined based on the sensor information captured at step 306. In some embodiments, the current state of the zone may be detected through: image-based detection, acoustic-based detection, thermal image-based detection, ultraviolet image-based detection, or ultrasonic Doppler-based detection or some combination thereof. In some cases, the current state of the zone of the medical facility may be determined based on sensor information associated with two or more sensors, for example, a camera and a microphone.

[0064] The current state of the zone may be one or more aspects of the zone, such as medical devices in the zone, conditions of the zone, activity of the zone, and / or the like. For example, the current state of the zone may be based on the number, type, operating conditions, status and / or the like of the medical devices in the zone. As another example, the current state of the zone may be based on the temperature, acoustic signature, noise level, cleanliness, and / or the like of the zone. In another example, the current state of the zone may be based on other devices in the zone, clinicians in the zone, patients in the zone, and / or the like.

[0065] The expected state of the zone of the medical facility may be determined based on one or more anticipated aspects of the zone. In some embodiments, the expected state of the zone may be based on a medication order for a patient associated with the zone, such as stored in a patient database 128 in FIG. 1. For example, where a patient has a medication order for an infusion through a syringe pump, the expected state of the zone of the patient includes the syringe pump infusing the patient according to the medication order. As another example, where a patient has a medication order for a pain medication dose, the expected state of the zone of the patient includes an administration of the pain medication dose to the patient.

[0066] In some embodiments, the expected state of the zone may be based on a reference state of the one or more devices associated with the zone of the medical facility. For example, a reference state of the zone may be a clean state of the zone. As another example, a reference state of the zone may be a number of patient beds in the zone, such as indicated by medical facility info system 108 in FIG. 1. In another example, a reference state may be an empty hallway.

[0067] In some embodiments, an anomaly may be detected based on a difference (e.g., that satisfies a threshold) between the current state of the zone and the expected state of the zone. The anomaly may be one or more differences between the current state of the zone and the expected state of the zone. For example, where the expected state is a syringe pump infusing a patient according to a medication order and the current state is the patient not connected to any infusion device, the anomaly may be the erroneous syringe pump status. Example erroneous statuses of aninfusion device may include an incorrect number of active channels on an infusion system; switched lines on an infusion system; an incorrect container volume for the infusion system; an incorrect head height of a syringe loaded into a syringe pump; an incorrect flow rate of a line of an infusion system; an overheating of an infusion device motor; an incorrect acoustic signature of the infusion device motor; and / or the like.

[0068] In another example, the expected state may be administration of a patient’s medication dose and the current state is no dose, the anomaly may be an incorrect medication administration. The current state may further include a medical dispensing cabinet accessed and medication removed, however, an image of the zone indicates the pill being placed in a clinician’s pocket.

[0069] As another example, the expected state may be an empty hallway, but the current state is a hallway with a medication dispensing cabinet, the erroneous presence of the medication dispensing cabinet may be the anomaly.

[0070] As another example, some facilities include a patient status display that presents status information for a series of patients under care within an associated zone. The status information may include vital signs, pending drug orders, attending physician, assigned clinician(s) (e.g., nursing staff), or other information about the patient or therapy therefor. In some facilities, there may be 10, 20, 40, 50 or more patients under care. The usefulness of these boards is, in part, based on a human’s ability to pay attention and notice patterns or anomalies. However, not all clinicians are equally trained or experienced and may miss early warnings that are presented. In contrast, the sentry robot may capture images of the status display and, using image recognition, extract information that can be used to identify unexpected information. For example, if a patient is shown on the status board at a first time as having a nominal heart rate and undergoing an infusion of a drug that is known to increase heart rate, if at a second time after the infusion, the same patient has the same or lower than nominal heart rate, the sentry robot may adjust the system to indicate the unexpected condition. Because machine learning models can identify patterns and anomalies that are not readily evident to humans and in a more efficient manner than humans, the sentry robot may help avoid adverse events by providing early alerts which can afford more time to prevent or respond to precursor conditions.

[0071] In some embodiments, an anomaly may be detected based on processing the current state of the zone of the medical facility with a machine learning model. For example, a machine learning model may be trained to detect an anomaly based on a current state of the zone.

[0072] At step 310, the sentry robot, or sentry server, initiates a corrective action based on the anomaly in the zone of the medical facility. A corrective action may include, for example, transmitting an alert or submitting a work order based on the anomaly. In some embodiments, a corrective action may include controlling a medical device in the zone of the medical facility, by, for example, transmitting one or more operation parameters to the medical device. For example, where an anomaly is an erroneous medical device status, the medical device operations may be stopped, paused, started, or adjusted, such as to correct the erroneous status.

[0073] In some embodiments, a corrective action may include searching for a device when the device is not found in a zone. The search for the device may be based on historical sensor information, for example, associated with a different zone where the device may be found.

[0074] At step 312, the sentry robot, or sentry server, determines if there are additional zones for the sentry robot to navigate to. If there are additional zones, workflow 300 proceeds to step 304. If there are not additional zones, workflow 300 ends at step 314.

[0075] Note that workflow 300 is just one example, and other flows including fewer, additional, or alternative steps, consistent with this disclosure, are possible.Example Workflow for Determining Corrective Actions for Detected Anomalies

[0076] FIG. 4 depicts an example workflow 400 for determining one or more corrective actions, for example, for initiation at step 310 of workflow 300 in FIG. 3, based on a determined anomaly of a zone of a medical facility.

[0077] One or more corrective actions may be initiated based on the anomaly detected, such as at step 308 in FIG. 3.

[0078] One or more aspects of the anomaly may indicate one or more corrective actions to be taken, for example, the type of anomaly, the device or system the anomaly is associated with, the zone the anomaly is associated with, and / or the like. In certain aspects, one or more corrective action may be taken based on the anomaly.

[0079] At block 404, a corrective action may be determined based on the type of anomaly. As described herein, the anomaly detected may be associated with a medication or medical treatment, a medical device, a patient, status of the zone, and / or the like. In cases where the anomaly is associated with an effect on a patient, block 414 = YES, such as a medication or medical treatment, a medical device, and / or a patient, a corrective action may be to transmit an alert to a clinician atblock 424, such as through a remote clinician device. In cases where the anomaly is not associated with an effect on a patient, block 414 = NO, then a corrective action may be to transmit an alert to a medical facility at block 434.

[0080] At block 406, a corrective action may be determined based on the device affected by the anomaly. As described herein, the anomaly detected may be associated with a medical device or other device in the medical facility. If, at block 416, the device affected is connected (i.e., block 416 = YES), for example, through a network connection, then a corrective action may be to transmit an alert to the device at block 426.

[0081] Further, if an adjustment of one or more operations of the device may resolve the anomaly, (i.e., block 436 = YES), then at block 456, an adjustment is transmitted to the device. For example, where an anomaly is associated with flow rate of an infusion pump, and the infusion pump is connected, and then an indication to adjust the flow rate may be transmitted to the infusion pump, or the sentry robot may make manual adjustments to the infusion pump. If, at block 436, the anomaly may not be resolved through adjustment of one or more operations of the device, (i.e., block 436 = NO), then at block 446, an alert is transmitted to a clinician. For example, where an anomaly is associated with a key missing from a medication dispensing cabinet, then an alert may be transmitted to a clinician.

[0082] Returning to block 416, if the device affected is not connected (i.e., block 416 = NO), then an alert may be transmitted to a clinician at block 466. Further, in some cases, at optional block 476, the sentry robot may also alert, for example, an audible alert on the sentry robot. In some cases, at optional block 486, the sentry robot may also use self-help. For example, where the device affected is a missing food cart, the sentry robot may search for the missing food cart in different zones, for example, navigating based on historic sensing data. Where the sentry robot finds the missing food cart misplaced in a different zone, the sentry robot may alert to the found food cart, enabling return of the food cart.

[0083] At block 408, a corrective action may be determined based on the zone affected by the anomaly. As described herein, different zones may be assigned different values based on aspects of the zone. For example, patient care zones may be assigned high values. If, at block 418, the zone with the detected anomaly is a high value zone (i.e., block 418 = YES), then at block 428, an alert may be immediately transmitted. For example, a clinician may be immediately notified where the zone affected is a high value zone. However, if at block 418, the zone affected is a low value zone, (i.e., block 418 = NO), then at block 438 the alert may be delayed. For example, wherea device is to present an alert, the alert may not be presented until a clinician next accesses the device.

[0084] In some embodiments, one or more corrective actions may be determined, for example, corrective actions may be determined at some, all, or none, of blocks 404, 406, and / or 408. Further, one or more additional aspects of an anomaly may also be used to determine corrective actions.

[0085] Note that workflow 400 is just one example, and other flows including fewer, additional, or alternative steps, consistent with this disclosure, are possible.Example Method for Operating a Sentry Robot

[0086] FIG. 5 depicts an example method 500 for operating a sentry robot, for example, sentry robot 200 in FIG. 2, such as to detect and correct anomalies of a medical facility.

[0087] Initially, method 500 begins at step 502 with directing the sentry robot to a zone of the medical facility based, at least in part, on medical device information associated with a medical device located in the zone.

[0088] Method 500 then proceeds to step 504 with obtaining information corresponding to sensor information captured by one or more sensors, such as sensors 202 in FIG. 2, of the sentry robot, the sensor information corresponding to a zone of a medical facility.

[0089] Method 500 proceeds to step 506 with determining an anomaly in the zone of the medical facility based at least in part on the sensor information.

[0090] Method 500 then proceeds to step 508 with initiating a corrective action based on the anomaly in the zone of the medical facility.

[0091] In some embodiments, the one or more sensors comprise one or more of: a camera, e.g., camera 204, a microphone, e.g., microphone 212, a speaker, e.g., speaker 218, a thermal imaging sensor, e.g., thermal camera 208, an ultraviolet camera, e.g., ultraviolet camera 206, or a Doppler ultrasonic sensor, e.g., Doppler ultrasonic sensor 210, of sensors 202 in FIG. 2.

[0092] In some embodiments, directing the sentry robot includes causing the sentry robot to navigate to the zone of the medical facility, for example, by navigation component 220 in FIG. 2. In some embodiments, causing the sentry robot to navigate to the zone of the medical facility, comprises: generating a map of the medical facility; determining one or more zones of the medical facility based on the map of the medical facility; and determining the zone of the medical facility from the one or more zones of the medical facility.

[0093] In some embodiments, determining the zone of the medical facility from the one or more zones of the medical facility, comprises: selecting the zone of the medical facility based on a type of the one or more sensors of the sentry robot.

[0094] In some embodiments, determining the zone of the medical facility from the one or more zones of the medical facility, comprises: assigning a value to each zone of the one or more zones of the medical facility; and selecting the zone of the medical facility based on the value of the zone of the medical facility. In some embodiments, the value is based on one or more of: a drug dispensed in the zone, a type of care performed in the zone, a patient in the zone, or a medical device in the zone.

[0095] In some embodiments, determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility based at least in part on the sensor information; determining an expected state of the zone of the medical facility; and detecting the anomaly between the current state of the zone of the medical facility and the expected state of the zone of the medical facility.

[0096] In some embodiments, determining the expected state of the zone of the medical facility comprises receiving a medication order associated with a patient in the zone of the medical facility, for example, a medication order from the medical facility info system 108 in FIG. 1.

[0097] In some embodiments, determining the expected state of the zone of the medical facility comprises receiving a reference state for one or more devices associated with the zone of the medical facility, for example, a reference state of an infusion device 102 or a reference state of a dispensing device 106 in FIG. 1.

[0098] In some embodiments, determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility based at least in part on the sensor information; and detecting the anomaly in the current state of the zone of the medical facility based on processing the current state of the zone of the medical facility with a machine learning model, for example, one of models 238 in FIG. 2, wherein the machine learning model accepts a set of values representing the current state as an input and provides a set of output values representing the anomaly and optionally a likelihood of the anomaly.

[0099] In some embodiments, the corrective action may be determined, at least in part by, a likelihood of the anomaly. For example, where the likelihood of the anomaly does not satisfy a threshold (e.g., the likelihood of the anomaly is less than a threshold likelihood), the correctiveaction may include delaying an alert, silencing an alert, or otherwise altering presentation of an alert.

[0100] In some embodiments, detecting the current state of the zone of the medical facility comprises one or more of: image-based detection; acoustic-based detection; thermal image-based detection; ultraviolet image-based detection; or ultrasonic Doppler-based detection, for example, by detecting component 230 in FIG. 2.

[0101] In some embodiments, initiating the corrective action comprises transmitting an alert based on the anomaly, for example, by messaging component 240 in FIG. 2.

[0102] In some embodiments, initiating the corrective action further comprises controlling a medical device in the zone of the medical facility based on the alert, for example, based on a transmission of one or more control signals by messaging component 240 in FIG. 2. In some embodiments, controlling a medical device in the zone of the medical facility based on the alert, comprises one or more of: stopping operations of the medical device, pausing operations of the medical device, or operating the medical device, for example, dispensing device 106 or infusion device 102 in FIG. 1.

[0103] In some embodiments, method 500 further comprises determining the sensor information corresponds to sensitive data; and causing the sentry robot to stop capturing the sensor information based on determining the sensor information corresponds to sensitive data, for example, through one or more rules 236 or models 234.

[0104] In some embodiments, wherein initiating the corrective action comprises submitting a work order based on the anomaly, for example, submitting a work order to medical facility information system 108 in FIG. 1.

[0105] In some embodiments, wherein: the anomaly is the presence of a device in the zone, or lack of presence of the device in the zone, and initiating the corrective action, comprises at least one of: generating an alert; determining, based on historical sensor information another zone where the device is located; or causing the sentry robot to navigate to one or more other zones to search for the device.

[0106] In some embodiments, the anomaly comprises an incorrect number of channels of an infusion system, for example, on infusion device 102 in FIG. 1.

[0107] In some embodiments, the anomaly comprises an infusion system error status, for example, on infusion device 102 in FIG. 1.

[0108] In some embodiments, the anomaly comprises an incorrect syringe head height in a syringe pump, for example, on infusion device 102 in FIG. 1.

[0109] In some embodiments, the anomaly comprises a patient-controlled analgesia pump lock box error status, for example, on infusion device 102 in FIG. 1.

[0110] In some embodiments, the anomaly comprises an error status of one or more patient vitals displayed on a patient vitals dashboard.[OHl] In some embodiments, the anomaly comprises an error status of a medical dispensing device, for example, of dispensing device 106 in FIG. 1.

[0112] In some embodiments, wherein the anomaly comprises an erroneous action at a medical dispensing device, for example, at dispensing device 106 in FIG. 1.

[0113] In some embodiments, the anomaly comprises an audible alert, for example, an audible alert generated by one or more of: dispensing device 106, infusion device 102, or clinician device 146 in FIG. 1.

[0114] In some embodiments, wherein the anomaly comprises an anomalous sound, for example, a sound of a patient falling.

[0115] In some embodiments, the anomaly comprises an erroneous acoustic signature of an infusion pump, for example, on infusion device 102 in FIG. 1.

[0116] In some embodiments, the anomaly comprises an overheating infusion pump, for example, on infusion device 102 in FIG. 1.

[0117] In some embodiments, the anomaly comprises an out-of-range temperature associated with a medical dispensing device, for example, on dispensing device 106 in FIG. 1.

[0118] In some embodiments, the anomaly comprises an erroneous flow rate of a fluid line associated with an infusion system, for example, on infusion device 102 in FIG. 1.

[0119] Note that method 500 is just one example, and other methods including fewer, additional, or alternative steps, consistent with this disclosure, are possible.Example Computing Device

[0120] FIG. 6 depicts an example computing device 600, such as a sentry robot, that implements various features and processes described herein, such as sentry robot 110 in FIG. 1. For example, the computing device 600 may perform one or more steps of any of flow 400 or method 500. The computing device 600 may include one or more processors 604, one or more memories 606, one or more input components 610, one or more output components 612, and one or more communication interfaces 608. Each of these components may be coupled by a bus 602.

[0121] Computing device 600 may perform these processes based on one or more processors 604 executing software instructions stored by a computer-readable medium, such as one or more memories 606. In certain embodiments, one or more processors 604 may be programmed / designed / configured to perform these processes. A computer-readable medium (e.g., a non-transitory computer-readable medium) is defined herein as a non-transitory memory device. A memory device includes memory space located inside of a single physical storage device or memory space spread across multiple physical storage devices. Software instructions may be read into one or more memories from another computer-readable medium or from another device via communication interface 608. When executed, software instructions stored in one or more memories may cause one or more processors 604 to perform one or more processes described herein.

[0122] A memory 606 may include data storage or one or more data structures (e.g., a database, etc.). Computing device 600 may be capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage or one or more data structures in one or more memories 606.

[0123] A memory 606 may include random access memory (RAM), read only memory (ROM), and / or other types of dynamic or static storage devices (e.g., flash memory, magnetic memory, optical memory, etc.), that stores information and / or instructions for use by one or more processors 604. For example, a memory 606 may include all forms of non-volatile memory, including by way of example semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magnetooptical disks; and CD-ROM and DVD-ROM disks.

[0124] One or more memories 606 may include a sensor component 614 configured to process sensor data 624, for example, obtained by one or more sensors, such as described in FIG. 3 andFIG. 5. Sensor component 614 may be configured to receive sensor data 624 from one or more remote sensors.

[0125] One or more memories 606 may include a navigation component 616 configured to navigate a sentry robot, and determine one or more zones of a medical facility, based on navigation data 622, such as described in FIG. 3, FIG. 4, and FIG. 5.

[0126] One or more memories 606 may include a determination component 618 configured to determine an anomaly in the zone of the medical facility, such as described in FIG. 3 and FIG. 5. Determination component 618 may include one or more machine learning models.

[0127] One or more memories 606 may include corrective action component 620 configured to determine and / or initiate one or more corrective actions based on a determined anomaly in the zone of the medical facility, such as in described in FIG. 3, FIG. 4, and FIG. 5.

[0128] One or more processors 604 may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and / or any processing component (e.g., a field- programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.), that may be programmed to perform a function, such as described herein.

[0129] One or more input components 610 may include a component that permits computing device 600 to receive information, such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, etc.). Further, one or more input components 610 may include a sensor for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.).

[0130] One or more output components 612 may include a component that provides output information from computing device 600 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.).

[0131] Communication interface 608 may include a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, etc.) that enables computing device 600 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 608 may permit computing device 600 to receive information from another device and / or provide information to another device. For example, communication interface 608 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, auniversal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, and / or the like.Example Clauses

[0132] Implementation examples are described in the following numbered clauses:

[0133] Clause 1 : A computer-implemented method for operating a sentry robot, comprising: directing a sentry robot to monitor a zone of a medical facility based at least in part on medical device information associated with a medical device located in the zone; obtaining information corresponding to sensor information captured by one or more sensors of the sentry robot, the sensor information corresponding to the zone of the medical facility; determining an anomaly in the zone of the medical facility based at least in part on the sensor information; and initiating a corrective action based on the anomaly in the zone of the medical facility.

[0134] Clause 2: The computer-implemented method of clause 1, wherein the one or more sensors comprise one or more of: a camera, a microphone, a speaker, a thermal imaging sensor, an ultraviolet camera, or a Doppler ultrasonic sensor.

[0135] Clause 3: The computer-implemented method of any one of clauses 1-2, directing the sentry robot comprises causing the sentry robot to navigate to the zone of the medical facility.

[0136] Clause 4: The computer-implemented method of clause 3, wherein causing the sentry robot to navigate to the zone of the medical facility, comprises: generating a map of the medical facility; determining one or more zones of the medical facility based on the map of the medical facility; and determining the zone of the medical facility from the one or more zones of the medical facility.

[0137] Clause 5: The computer-implemented method of clause 4, wherein determining the zone of the medical facility from the one or more zones of the medical facility, comprises: selecting the zone of the medical facility based on a type of the one or more sensors of the sentry robot.

[0138] Clause 6: The computer-implemented method of any one of clauses 4-5, wherein determining the zone of the medical facility from the one or more zones of the medical facility, comprises: assigning a value to each zone of the one or more zones of the medical facility; and selecting the zone of the medical facility based on the value of the zone of the medical facility.

[0139] Clause 7: The computer-implemented method of clause 6, wherein the value is based on one or more of: a drug dispensed in the zone, a type of care performed in the zone, a patient in the zone, or a medical device in the zone.

[0140] Clause 8: The computer-implemented method of any one of clauses 1-7, wherein determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility based at least in part on the sensor information; determining an expected state of the zone of the medical facility; and detecting the anomaly between the current state of the zone of the medical facility and the expected state of the zone of the medical facility.

[0141] Clause 9: The computer-implemented method of clause 8, wherein determining the expected state of the zone of the medical facility comprises receiving a medication order associated with a patient in the zone of the medical facility.

[0142] Clause 10: The computer-implemented method of clause 8, wherein determining the expected state of the zone of the medical facility comprises receiving a reference state for one or more devices associated with the zone of the medical facility.

[0143] Clause 11 : The computer-implemented method of any one of clauses 1-7, wherein determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility based at least in part on the sensor information; and detecting the anomaly in the current state of the zone of the medical facility based on processing the current state of the zone of the medical facility with a machine learning model, the machine learning model accepting a set of values representing the current state as an input and providing a set of output values representing the anomaly and a likelihood of the anomaly.

[0144] Clause 12: The computer-implemented method of any one of clauses 8-11, wherein detecting the current state of the zone of the medical facility comprises one or more of: imagebased detection; acoustic-based detection; thermal image-based detection; ultraviolet image-based detection; or ultrasonic Doppler-based detection.

[0145] Clause 13: The computer-implemented method of any one of clauses 1-12, wherein initiating the corrective action comprises transmitting an alert based on the anomaly.

[0146] Clause 14: The computer-implemented method of clause 13, wherein initiating the corrective action further comprises controlling a medical device in the zone of the medical facility based on the alert.

[0147] Clause 15: The computer-implemented method of clause 14, wherein controlling a medical device in the zone of the medical facility based on the alert, comprises one or more of: stopping operations of the medical device, pausing operations of the medical device, or operating the medical device.

[0148] Clause 16: The computer-implemented method of any one of clauses 1-15, further comprising: determining the sensor information corresponds to sensitive data; and causing the sentry robot to stop capturing the sensor information based on determining the sensor information corresponds to sensitive data.

[0149] Clause 17: The computer-implemented method of any one of clauses 1-16, wherein initiating the corrective action comprises submitting a work order based on the anomaly.

[0150] Clause 18: The computer-implemented method of any one of clauses 1-17, wherein: the anomaly is the presence of a device in the zone, or lack of presence of the device in the zone, and initiating the corrective action, comprises at least one of: generating an alert; determining, based on historical sensor information another zone where the device is located; or causing the sentry robot to navigate to one or more other zones to search for the device.

[0151] Clause 19: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an incorrect number of channels of an infusion system.

[0152] Clause 20: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an infusion system error status.

[0153] Clause 21 : The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an incorrect syringe head height in a syringe pump.

[0154] Clause 22: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises a patient-controlled analgesia pump lock box error status.

[0155] Clause 23: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an error status of one or more patient vitals displayed on a patient vitals dashboard.

[0156] Clause 24: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an error status of a medical dispensing device.

[0157] Clause 25: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an erroneous action at a medical dispensing device.

[0158] Clause 26: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an audible alert.

[0159] Clause 27: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an anomalous sound.

[0160] Clause 28: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an erroneous acoustic signature of an infusion pump.

[0161] Clause 29: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an overheating infusion pump.

[0162] Clause 30: The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an out-of-range temperature associated with a medical dispensing device.

[0163] Clause 31 : The computer-implemented method of any one of clauses 1-17, wherein the anomaly comprises an erroneous flow rate of a fluid line associated with an infusion system.

[0164] Clause 32: A processing system, comprising: a memory comprising computerexecutable instructions; and a processor configured to execute the computer-executable instructions and cause the processing system to perform a method in accordance with any one of Clauses 1-31.

[0165] Clause 33: A processing system, comprising means for performing a method in accordance with any one of Clauses 1-31.

[0166] Clause 34: A non-transitory computer-readable medium storing program code for causing a processing system to perform the steps of any one of Clauses 1-31.

[0167] Clause 35: A computer program product embodied on a computer-readable storage medium comprising code for performing a method in accordance with any one of Clauses 1-31.Additional Considerations

[0168] The preceding description is provided to enable any person skilled in the art to practice the various embodiments described herein. The examples discussed herein are not limiting of the scope, applicability, or embodiments set forth in the claims. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments. For example, changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure.Various examples may omit, substitute, or add various procedures or components as appropriate. For instance, the methods described may be performed in an order different from that described, and various steps may be added, omitted, or combined. Also, features described with respect to some examples may be combined in some other examples. For example, an apparatus may be implemented or a method may be practiced using any number of the aspects set forth herein. In addition, the scope of the disclosure is intended to cover such an apparatus or method that is practiced using other structure, functionality, or structure and functionality in addition to, or other than, the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of a claim.

[0169] As used herein, a phrase referring to “at least one of’ a list of items refers to any combination of those items, including single members. As an example, “at least one of a, b, or c” is intended to cover a, b, c, a-b, a-c, b-c, and a-b-c, as well as any combination with multiples of the same element (e.g., a-a, a-a-a, a-a-b, a-a-c, a-b-b, a-c-c, b-b, b-b-b, b-b-c, c-c, and c-c-c or any other ordering of a, b, and c).

[0170] As used herein, the term “determining” encompasses a wide variety of actions. For example, “determining” may include calculating, computing, processing, deriving, investigating, looking up (e.g., looking up in a table, a database or another data structure), ascertaining and the like. Also, “determining” may include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory) and the like. Also, “determining” may include resolving, selecting, choosing, establishing and the like.

[0171] The methods disclosed herein comprise one or more steps or actions for achieving the methods. The method steps and / or actions may be interchanged with one another without departing from the scope of the claims. In other words, unless a specific order of steps or actions is specified, the order and / or use of specific steps and / or actions may be modified without departing from the scope of the claims. Further, the various operations of methods described above may be performed by any suitable means capable of performing the corresponding functions. The means may include various hardware and / or software component(s) and / or module(s), including, but not limited to a circuit, an application specific integrated circuit (ASIC), or processor. Generally, where there are operations illustrated in figures, those operations may have corresponding counterpart means-plus-function components with similar numbering.

[0172] The following claims are not intended to be limited to the embodiments shown herein, but are to be accorded the full scope consistent with the language of the claims. Within a claim,reference to an element in the singular is not intended to mean “one and only one” unless specifically so stated, but rather “one or more.” Unless specifically stated otherwise, the term “some” refers to one or more. No claim element is to be construed under the provisions of 35 U.S.C. §112(f) unless the element is expressly recited using the phrase “means for” or, in the case of a method claim, the element is recited using the phrase “step for.” All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims.

Claims

Claims1. A sentry system, comprising: one or more memories comprising computerexecutable instructions; and one or more processors configured to execute the computerexecutable instructions and cause the sentry system to: direct a sentry robot to monitor a zone of a medical facility based at least in part on medical device information associated with a medical device located in the zone; obtain information corresponding to sensor information captured by one or more sensors of the sentry robot, the sensor information corresponding to the zone of the medical facility; determine an anomaly in the zone of the medical facility based at least in part on the sensor information; and initiate a corrective action based on the anomaly in the zone of the medical facility.

2. The sentry system of claim 1, wherein the one or more sensors comprise one or more of: a camera, a microphone, a speaker, a thermal imaging sensor, an ultraviolet camera, or a Doppler ultrasonic sensor.

3. The sentry system of any one of claims 1-2, wherein to direct the sentry robot, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to cause the sentry robot to navigate to the zone of the medical facility.

4. The sentry system of claim 3, wherein to cause the sentry robot to navigate to the zone of the medical facility, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to: generate a map of the medical facility; determine one or more zones of the medical facility based on the map of the medical facility; and determine the zone of the medical facility from the one or more zones of the medical facility.

5. The sentry system of claim 4, wherein to determine the zone of the medical facility from the one or more zones of the medical facility, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to:select the zone of the medical facility based on a type of the one or more sensors of the sentry robot.

6. The sentry system of any one of claims 4-5, wherein to determine the zone of the medical facility from the one or more zones of the medical facility, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to: assign a value to each zone of the one or more zones of the medical facility; and select the zone of the medical facility based on the value of the zone of the medical facility.

7. The sentry system of claim 6, wherein the value is based on one or more of: a drug dispensed in the zone, a type of care performed in the zone, a patient in the zone, or a medical device in the zone.

8. The sentry system of any one of claims 1-7, wherein to determine the anomaly in the zone of the medical facility, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to: detect a current state of the zone of the medical facility based at least in part on the sensor information; determine an expected state of the zone of the medical facility; and detect the anomaly between the current state of the zone of the medical facility and the expected state of the zone of the medical facility.

9. The sentry system of claim 8, wherein to determine the expected state of the zone of the medical facility, the one or more processors are further configured to execute the computerexecutable instructions and cause the sentry system to receive a medication order associated with a patient in the zone of the medical facility.

10. The sentry system of claim 8, wherein to determine the expected state of the zone of the medical facility, the one or more processors are further configured to execute the computerexecutable instructions and cause the sentry system to receive a reference state for one or more devices associated with the zone of the medical facility.

11. The sentry system of any one of claims 1-7, wherein to determine the anomaly in the zone of the medical facility, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to: detect a current state of the zone of the medical facility based at least in part on the sensor information; and detect the anomaly in the current state of the zone of the medical facility based on processing the current state of the zone of the medical facility with a machine learning model, the machine learning model accepting a set of values representing the current state as an input and providing a set of output values representing the anomaly and a likelihood of the anomaly.

12. The sentry system of claim 11, wherein to detect the current state of the zone of the medical facility, the one or more processors are further configured to execute the computerexecutable instructions and cause the sentry robot to use one or more of: image-based detection; acoustic-based detection; thermal image-based detection; ultraviolet image-based detection; or ultrasonic Doppler-based detection.

13. The sentry system of any one of claims 1-12, wherein to initiate the corrective action, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to transmit an alert based on the anomaly.

14. The sentry system of claim 13, wherein to initiate the corrective action, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to control a medical device in the zone of the medical facility based on the alert.

15. The sentry system of claim 14, wherein to control a medical device in the zone of the medical facility based on the alert, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to one or more of: stop operations of the medical device, pause operations of the medical device, or operate the medical device.

16. The sentry system of any one of claims 1-15, wherein the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to: determine the sensor information corresponds to sensitive data; and cause the sentry robot to stop capturing the sensor information based on determining the sensor information corresponds to sensitive data.

17. The sentry system of any one of claims 1-16, wherein to initiate the corrective action, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to submit a work order based on the anomaly.

18. The sentry system of any one of claims 1-17, wherein: the anomaly is presence of a device in the zone, or lack of presence of the device in the zone, and to initiate the corrective action, the one or more processors are further configured to execute the computer-executable instructions and cause the sentry system to perform at least one of: generate an alert; determine, based on historical sensor information another zone where the device is located; or cause the sentry robot to navigate to one or more other zones to search for the device.

19. The sentry system of any one of claims 1-17, wherein the anomaly comprises an incorrect number of channels of an infusion system.

20. The sentry system of any one of claims 1-17, wherein the anomaly comprises an infusion system error status.

21. The sentry system of any one of claims 1-17, wherein the anomaly comprises an incorrect syringe head height in a syringe pump.

22. The sentry system of any one of claims 1-17, wherein the anomaly comprises a patient-controlled analgesia pump lock box error status.

23. The sentry system of any one of claims 1-17, wherein the anomaly comprises an error status of one or more patient vitals displayed on a patient vitals dashboard.

24. The sentry system of any one of claims 1-17, wherein the anomaly comprises an error status of a medical dispensing device.

25. The sentry system of any one of claims 1-17, wherein the anomaly comprises an erroneous action at a medical dispensing device.

26. The sentry system of any one of claims 1-17, wherein the anomaly comprises an audible alert.

27. The sentry system of any one of claims 1-17, wherein the anomaly comprises an anomalous sound.

28. The sentry system of any one of claims 1-17, wherein the anomaly comprises an erroneous acoustic signature of an infusion pump.

29. The sentry system of any one of claims 1-17, wherein the anomaly comprises an overheating infusion pump.

30. The sentry system of any one of claims 1-17, wherein the anomaly comprises an out-of-range temperature associated with a medical dispensing device.

31. The sentry system of any one of claims 1-17, wherein the anomaly comprises an erroneous flow rate of a fluid line associated with an infusion system.

32. A non-transitory computer-readable medium storing program code, that when executed by a sentry system, cause the sentry system to perform operations comprising: directing a sentry robot to monitor a zone of a medical facility based on medical device information associated with a medical device located in the zone; obtaining information corresponding to sensor information captured by one or more sensors of a sentry robot, the sensor information corresponding to the zone of the medical facility; determining an anomaly in the zone of the medical facility based at least in part on the sensor information; andinitiating a corrective action based on the anomaly in the zone of the medical facility.

33. The non-transitory computer-readable medium of claim 32, wherein the one or more sensors comprise one or more of: a camera, a microphone, a speaker, a thermal imaging sensor, an ultraviolet camera, or a Doppler ultrasonic sensor.

34. The non-transitory computer-readable medium of any one of claims 32-33, wherein directing the sentry robot comprises causing the sentry robot to navigate to the zone of the medical facility.

35. The non-transitory computer-readable medium of claim 34, wherein causing the sentry robot to navigate to the zone of the medical facility, comprises: generating a map of the medical facility; determining one or more zones of the medical facility based on the map of the medical facility; and determining the zone of the medical facility from the one or more zones of the medical facility.

36. The non-transitory computer-readable medium of claim 35, wherein determining the zone of the medical facility from the one or more zones of the medical facility, comprises: selecting the zone of the medical facility based on a type of the one or more sensors of the sentry robot.

37. The non-transitory computer-readable medium of any one of claims 35-36, wherein determining the zone of the medical facility from the one or more zones of the medical facility, comprises: assigning a value to each zone of the one or more zones of the medical facility; and selecting the zone of the medical facility based on the value of the zone of the medical facility.

38. The non-transitory computer-readable medium of claim 37, wherein the value is based on one or more of: a drug dispensed in the zone, a type of care performed in the zone, a patient in the zone, or a medical device in the zone.

39. The non-transitory computer-readable medium of any one of claims 32-38, wherein determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility based at least in part on the sensor information; determining an expected state of the zone of the medical facility; and detecting the anomaly between the current state of the zone of the medical facility and the expected state of the zone of the medical facility.

40. The non-transitory computer-readable medium of claim 39, wherein determining the expected state of the zone of the medical facility comprises receiving a medication order associated with a patient in the zone of the medical facility.

41. The non-transitory computer-readable medium of claim 39, wherein determining the expected state of the zone of the medical facility comprises receiving a reference state for one or more devices associated with the zone of the medical facility.

42. The non-transitory computer-readable medium of any one of claims 32-38, wherein determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility based at least in part on the sensor information; and detecting the anomaly in the current state of the zone of the medical facility based on processing the current state of the zone of the medical facility with a machine learning model, the machine learning model accepting a set of values representing the current state as an input and providing a set of output values representing the anomaly and a likelihood of the anomaly.

43. The non-transitory computer-readable medium of claim 42, wherein detecting the current state of the zone of the medical facility comprises one or more of: image-based detection; acoustic-based detection; thermal image-based detection; ultraviolet image-based detection; or ultrasonic Doppler-based detection.

44. The non-transitory computer-readable medium of any one of claims 32-43, wherein initiating the corrective action comprises transmitting an alert based on the anomaly.

45. The non-transitory computer-readable medium of claim 44, wherein initiating the corrective action comprises controlling a medical device in the zone of the medical facility based on the alert.

46. The non-transitory computer-readable medium of claim 45, wherein controlling a medical device in the zone of the medical facility based on the alert, comprises one or more of: stopping operations of the medical device, pausing operations of the medical device, or operating the medical device.

47. The non-transitory computer-readable medium of any one of claims 32-46, wherein the operations further comprise: determining the sensor information corresponds to sensitive data; and causing the sentry robot to stop capturing the sensor information based on determining the sensor information corresponds to sensitive data.

48. The non-transitory computer-readable medium of any one of claims 32-47, wherein initiating the corrective action comprises submitting a work order based on the anomaly.

49. The non-transitory computer-readable medium of any one of claims 32-48, wherein: the anomaly is presence of a device in the zone, or lack of presence of the device in the zone, and initiating the corrective action, comprises at least one of: generating an alert; determining, based on historical sensor information another zone where the device is located; or causing the sentry robot to navigate to one or more other zones to search for the device.

50. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an incorrect number of channels of an infusion system.

51. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an infusion system error status.

52. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an incorrect syringe head height in a syringe pump.

53. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises a patient-controlled analgesia pump lock box error status.

54. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an error status of one or more patient vitals displayed on a patient vitals dashboard.

55. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an error status of a medical dispensing device.

56. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an erroneous action at a medical dispensing device.

57. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an audible alert.

58. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an anomalous sound.

59. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an erroneous acoustic signature of an infusion pump.

60. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an overheating infusion pump.

61. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an out-of-range temperature associated with a medical dispensing device.

62. The non-transitory computer-readable medium of any one of claims 32-48, wherein the anomaly comprises an erroneous flow rate of a fluid line associated with an infusion system.

63. A computer-implemented method for operating a sentry robot, comprising: obtaining information corresponding to sensor information captured by one or more sensors of the sentry robot, the sensor information corresponding to a zone of a medical facility; determining an anomaly in the zone of the medical facility; and initiating a corrective action based on the anomaly in the zone of the medical facility.

64. The computer-implemented method of claim 63, wherein the one or more sensors comprise one or more of: a camera, a microphone, a speaker, a thermal imaging sensor, an ultraviolet camera, or a Doppler ultrasonic sensor.

65. The computer-implemented method of any one of claims 63-64, further comprising causing the sentry robot to navigate to the zone of the medical facility.

66. The computer-implemented method of claim 65, wherein causing the sentry robot to navigate to the zone of the medical facility, comprises: generating a map of the medical facility; determining one or more zones of the medical facility; and determining the zone of the medical facility from the one or more zones of the medical facility.

67. The computer-implemented method of claim 66, wherein determining the zone of the medical facility from the one or more zones of the medical facility, comprises: selecting the zone of the medical facility based on a type of the one or more sensors of the sentry robot.

68. The computer-implemented method of any one of claims 66-67, wherein determining the zone of the medical facility from the one or more zones of the medical facility, comprises: assigning a value to each zone of the one or more zones of the medical facility; andselecting the zone of the medical facility based on the value of the zone of the medical facility.

69. The computer-implemented method of claim 68, wherein the value is based on one or more of: a drug dispensed in the zone, a type of care performed in the zone, a patient in the zone, or a medical device in the zone.

70. The computer-implemented method of any one of claims 63-69, wherein determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility; determining an expected state of the zone of the medical facility; and detecting the anomaly between the current state of the zone of the medical facility and the expected state of the zone of the medical facility.

71. The computer-implemented method of claim 70, wherein determining the expected state of the zone of the medical facility comprises receiving a medication order associated with a patient in the zone of the medical facility.

72. The computer-implemented method of claim 70, wherein determining the expected state of the zone of the medical facility comprises receiving a reference state for one or more devices associated with the zone of the medical facility.

73. The computer-implemented method of any one of claims 63-72, wherein determining the anomaly in the zone of the medical facility, comprises: detecting a current state of the zone of the medical facility; and detecting the anomaly in the current state of the zone of the medical facility based on processing the current state of the zone of the medical facility with a machine learning model.

74. The computer-implemented method of claim 73, wherein detecting the current state of the zone of the medical facility comprises one or more of: image-based detection; acoustic-based detection; thermal image-based detection; ultraviolet image-based detection; orultrasonic Doppler-based detection.

75. The computer-implemented method of any one of claims 63-74, wherein initiating the corrective action comprises transmitting an alert based on the anomaly.

76. The computer-implemented method of claim 75, wherein initiating the corrective action further comprises controlling a medical device in the zone of the medical facility based on the alert.

77. The computer-implemented method of claim 76, wherein controlling a medical device in the zone of the medical facility based on the alert, comprises one or more of: stopping operations of the medical device, pausing operations of the medical device, or operating the medical device.

78. The computer-implemented method of any one of claims 63-77, further comprising: determining the sensor information corresponds to sensitive data; and causing the sentry robot to stop capturing the sensor information based on determining the sensor information corresponds to sensitive data.

79. The computer-implemented method of any one of claims 63-78, wherein initiating the corrective action comprises submitting a work order based on the anomaly.

80. The computer-implemented method of any one of claims 63-79, wherein: the anomaly is presence of a device in the zone, or lack of presence of the device in the zone, and initiating the corrective action, comprises at least one of: generating an alert; determining, based on historical sensor information another zone where the device is located; or causing the sentry robot to navigate to one or more other zones to search for the device.

81. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an incorrect number of channels of an infusion system.

82. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an infusion system error status.

83. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an incorrect syringe head height in a syringe pump.

84. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises a patient-controlled analgesia pump lock box error status.

85. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an error status of one or more patient vitals displayed on a patient vitals dashboard.

86. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an error status of a medical dispensing device.

87. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an erroneous action at a medical dispensing device.

88. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an audible alert.

89. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an anomalous sound.

90. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an erroneous acoustic signature of an infusion pump.

91. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an overheating infusion pump.

92. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an out-of-range temperature associated with a medical dispensing device.

93. The computer-implemented method of any one of claims 63-79, wherein the anomaly comprises an erroneous flow rate of a fluid line associated with an infusion system.

Images