Systems and methods for visual scene monitoring - Patents.com

Abstract

The present application is directed to systems and methods for performing anomaly detection, predictive maintenance, and anomaly correction in an amusement park experience. In particular, the present application is directed to a method for monitoring an amusement park experience. The method can include receiving multiple layers of first sensor data via a sensor network indicative of a characteristic of the experience. The method can also include generating a profile of the experience based on the first sensor data, where the profile includes a baseline and a threshold indicative of an acceptable range of the characteristic. The method can also include receiving second sensor data and third sensor data via the sensor network. The method can further include determining, in response to individually recognizing a characteristic of the second sensor data that deviates from the baseline but does not exceed the threshold, that the experience is operating correctly. The method can also include performing a specified corrective action in response to individually recognizing a characteristic of the third sensor data that deviates from the baseline and exceeds the threshold.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims priority to and the benefit of U.S. Provisional Application No. 63 / 296,733, filed January 5, 2022, entitled "System and Method for Visual Scene Monitoring," the entire disclosure of which is hereby incorporated by reference into this specification for all purposes. [Background technology]

[0002] This section is intended to introduce the reader to various technical aspects that may be related to various aspects of the present technology that are described and / or claimed below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. As such, it should be understood that these discussions are to be read in this light, and not as admissions of prior art.

[0003] Amusement parks and other entertainment venues include experiences (e.g., ride vehicle experiences, animated figures (e.g., robotic characters), scenes, attractions, etc.) that entertain guests. As the experiences become more technologically advanced and complex, the components within the experience can benefit from more consistent monitoring and maintenance to ensure guest safety or optimal or improved operation of the experience. As such, it is now recognized that it is advantageous to utilize a variety of sensors, machine learning, and multi-dimensional modeling techniques to enable earlier anomaly detection, automated alerts, predictive maintenance, and dynamic corrections to the experience. Summary of the Invention

[0004] Embodiments that are equivalent within the scope of the originally claimed subject matter are summarized below. These embodiments are not intended to limit the scope of the present disclosure, but rather these embodiments are intended merely to provide a brief summary of certain disclosed embodiments. Indeed, the present disclosure may encompass a variety of aspects that may be similar to or different from the embodiments set forth below.

[0005] In one embodiment, a method for monitoring an amusement park experience can include receiving multiple layers of first sensor data via a plurality of sensors indicative of a characteristic of the experience. The method can generate a profile of the experience based on the first sensor data, the profile including a baseline and a threshold indicating an acceptable range of the characteristic. The method can receive second sensor data and third sensor data via the plurality of sensors. The method can determine that the experience operates appropriately in response to individually identifying a characteristic of the second sensor data that deviates from the baseline but does not exceed the threshold. The method can also perform a corrective action in response to individually identifying a characteristic of the third sensor data that deviates from the baseline and exceeds the threshold.

[0006] In one embodiment, the system can include one or more communication hubs communicatively coupled to the network and one other communication hub via the network. The system can also include a ride vehicle including one or more ride vehicle sensors, the one or more ride vehicle sensors communicatively coupled to at least one of the one or more communication hubs. The system can further include an animated figure, an animated figure including an actuator, and an actuator sensor, the actuator sensor communicatively coupled to at least one of the one or more communication hubs. The system can also include a controller capable of receiving data from the one or more ride vehicle sensors and data from the actuator sensor via the one or more communication hubs. The controller can adjust the actuators to control the ride vehicle based on a difference between a value associated with a baseline and a currently detected associated value of the data from the one or more ride vehicle sensors and data from the actuator sensor.

[0007] In one embodiment, one or more tangible, non-transitory computer readable media are provided in accordance with the present disclosure. The one or more tangible, non-transitory computer readable media include instructions that, when executed by at least one processor, cause the at least one processor to receive, via a plurality of sensors, first sensor data indicative of a characteristic of the amusement park experience. The processor can generate a profile of the amusement park experience based on the first sensor data, the profile including a baseline and a threshold indicative of an acceptable range of the characteristic. The processor can receive, via the plurality of sensors, second sensor data and third sensor data, and can determine that the experience is operating properly in response to individually recognizing a characteristic of the second sensor data that deviates from the baseline but does not exceed the threshold. However, in response to individually recognizing a characteristic of the third sensor data that deviates from the baseline and exceeds the threshold, the processor can perform a corrective action.

[0008] These and other features, aspects and advantages of the present disclosure will be better understood when the following detailed description is read in conjunction with the drawings in which like characters represent like parts throughout the drawings. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram of an anomaly detection and monitoring system according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a flow diagram of a method for detecting anomalies associated with an experience and taking corrective action utilizing the system of FIG. 1, according to an aspect of the disclosure. [Diagram 3] FIG. 3 illustrates an experience that may utilize the system of FIG. 1 in accordance with an embodiment of the present disclosure. [Figure 4] FIG. 4 is a block diagram illustrating a system of disconnected local sensor networks according to the present disclosure. [Diagram 5] FIG. 5 is a block diagram illustrating a network of local interconnected sensors and devices according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] One or more detailed embodiments of the present disclosure will be described below. In an effort to provide a concise description of these embodiments, all features of an actual implementation may not be described in this specification. It should be understood that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the specific goals of the developer, such as compliance with system-related and business-related constraints that vary from implementation to implementation. Moreover, it should be understood that such a development effort may be complex and time-consuming, but would be a routine undertaking for those of ordinary skill in the art having the benefit of this disclosure to design, fabricate, and manufacture.

[0011] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean that there are one or more elements. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there may be additional elements other than the listed elements. In addition, it should be understood that references to "one embodiment" or "an embodiment" of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.

[0012] Theme parks and other such entertainment venues are becoming increasingly popular. Furthermore, immersive experiences within such entertainment venues are in high demand. To provide new and exciting experiences, attractions such as rides and scenic experiences (e.g., visual shows including live action, animated figures, computer generated images, etc.) are becoming increasingly complex and include an incorporation of light, sound, motion, interactive elements, visual media, etc. Thus, components within attractions can benefit from more thorough and holistic monitoring and maintenance. Conventional monitoring and maintenance systems include a bank or network of disparate sensors and manual regimes of inspections ordered by technicians. Such conventional systems may fail to detect certain maintenance and / or user experience issues due to human error or may fail to detect maintenance and / or user experience issues due to lack of automated monitoring (e.g., via sensors, cameras, etc.). As can be seen, a system leveraging a multi-faceted, layered, globally connected network of sensors, multi-dimensional models and machine learning engines can achieve a more robust, accurate, responsive and intelligent monitoring and maintenance system for amusement park attractions.

[0013] In view of the foregoing, the present embodiments are generally directed to methods and systems for automated monitoring, anomaly detection, correction, mitigation, and / or predictive maintenance in a theme park experience. Specifically, the presently disclosed embodiments are directed to collecting data on various aspects of components within the experience, utilizing machine learning to detect and / or predict quantitative and qualitative issues via a communicatively coupled network of sensors, dynamically address anomalies, and / or trigger alerts that identify anomalies. The visual aspects, control features, audio, animated figure aspects, and monitoring and maintenance components and / or aspects are arranged in accordance with current technology to provide multi-faceted and layered experience monitoring and maintenance. The multi-faceted and layered monitoring and maintenance provides robust, intelligent experience monitoring. The layering is achieved, at least in part, by leveraging multiple data sources or streams (e.g., audiovisual data, infrared data, social media data, etc.) to detect, predict, and / or correct subtle anomalies, even though they may impact the quality of a guest's enjoyment of the experience. Due to the complex nature of interactions between guests and experiences, in some embodiments, control instructions from an artificial intelligence (AI) or machine learning engine can adjust sensor data, equipment performance, and the like to detect and address anomalies (e.g., correct or mitigate the impact). Additionally, multiple and variable iterative routines are included to incrementally improve aspects of the monitoring and maintenance system.

[0014] In accordance with this disclosure (as applicable to the procedures described in FIGS. 1-5), a procedure includes a variety of different steps and procedural aspects with respect to monitoring an amusement park experience. Some of these steps or procedures can be performed in parallel or in varying and different orders. Some steps can be processor-based operations and can include controlled devices (e.g., actuators). Additionally, some procedures can be performed iteratively to achieve a desired result. Thus, while various different procedural steps as described in this disclosure may be discussed in a particular order herein, the procedural steps may not necessarily be performed in the order presented. While some specific operational steps may necessarily occur before other specific steps (e.g., as dictated by logic), the listing of some orders of operations is provided primarily for ease of discussion. For example, an indication that a first or initial step includes a particular operation is not intended to limit the scope of the disclosure to such initial steps. Rather, it should be understood that additional steps can be performed, certain steps can be removed, referenced steps can be performed in alternate orders or in parallel as appropriate, and the like. However, the order of operations disclosed when presented as such may be limited.

[0015] FIG. 1 is a block diagram of an anomaly detection and monitoring system (e.g., system) 100 according to the present disclosure. As described, the system 100 includes an electronic device 102, which can be present in any suitable electronic computing device type, such as a computer, laptop, PC, server, mobile device, smartphone, tablet, wearable device, etc. The electronic device 102 can include a controller 104, which includes one or more processors 106 and one or more memory and / or storage devices 108. The one or more processors 106 (e.g., microprocessors) can execute software programs and / or instructions (e.g., stored in memory 108) to facilitate determining the likelihood and / or occurrence of a change in an amusement experience (e.g., related to a baseline experience) and adjusting controls appropriately. Additionally, the one or more processors 106 can include multiple microprocessors, one or more “general purpose” microprocessors, one or more special purpose microprocessors and / or one or more application specific integrated circuits (ASICs), or some combination thereof. For example, the one or more processors 106 may include one or more reduced instruction set computer (RISC) processors.

[0016] The one or more memory devices 108 can store information such as control software, look-up tables, configuration data, and the like. In some embodiments, the one or more processors 106 and / or the one or more memory devices 108 can be external to the controller 104 and / or the electronic device 102. The one or more memory devices 108 can include a tangible, non-transitory, machine-readable medium such as volatile memory (e.g., random access memory (RAM)) and / or non-volatile memory (e.g., read-only memory (ROM)). The one or more memory devices 108 can store a variety of information that can be used for a variety of purposes. For example, the one or more memory devices 108 may store machine-readable and / or processor-executable instructions (e.g., firmware or software) for the one or more processors 106 to execute, such as instructions related to determining the likelihood that an entertainment experience (e.g., automated positioning of an animated figure) is tending to exceed a threshold or limit of acceptable operation (e.g., due to wear, part failure, degradation of control) and adjusting the operation or control characteristics appropriately. The one or more memory devices 108 may include one or more storage devices (e.g., non-volatile storage devices), which may include read-only memory (ROM), flash memory, hard drives, or any other suitable optical, magnetic, or solid-state storage medium, or combinations thereof.

[0017] The electronic device 102 may also include an electronic display 110 that enables graphical and / or visual output for display to a user. The electronic display 110 may use any suitable display technology and may include an electroluminescent (ELD) display, a liquid crystal (LCD) display, a light emitting diode (LED) display, an organic light emitting diode (OLED) display, an active matrix organic light emitting diode (OLED) display, a plasma display panel (PDP), a quantum dot LED (QLED) display, etc.

[0018] As described, the electronic device 102 may include a data acquisition system (DAQ) 112 operable to transmit and receive information to and from the sensor network 120. For example, the electronic device 102 may include a communication interface that enables the controller 104 to communicate with a server and / or other computing resources of the sensor network 120 via a communication network (e.g., a mobile communication network WiFi network, a local area network (LAN), a wide area network (WAN), the Internet, etc.). In some cases, at least a portion of the information received from the sensor network 120 may be downloaded and stored in a memory or storage device 108 of the electronic device 102. The sensor network 120 may include an ultraviolet sensor 122, an infrared sensor 124, a vibration sensor 126, an imaging sensor 128, an audio sensor 130, a biometric sensor 132, etc. It should be noted that while a list of the preceding sensors are illustrated in Figure 1, any other suitable sensors may be used in the system 100, such as acceleration sensors, speed sensors, gyrometers, torque sensors, position sensors, pressure sensors, humidity sensors, light sensors, voltage sensors, current sensors, humidity sensors, particle sensors, etc. It should further be understood that the sensors illustrated in Figure 1 represent any sensor type that may be used in an attraction.

[0019] The sensor network 120 may enable the system 100 to collect a wide amount of data regarding the amusement park attraction so that the system 100 can obtain a fine-grained view of various aspects of the components within the system 100. For example, the infrared sensor 124 may detect whether the wheels or motor of the ride vehicle radiate heat above a heat threshold, and if so, may provide a warning to a technical operator (e.g., via the controller 104), may stop operation of the ride vehicle, or may take any other appropriate action. The combination of inputs may also be evaluated using algorithms, look-up tables, or artificial intelligence. For example, data from the infrared sensor 124 may be analyzed in combination with the vibration sensor 126 to detect sources of heat associated with imbalance of the wheels of the ride vehicle or the like. The sensor network 120 may enable the system 100 to address quantitative and qualitative problems in the amusement park attraction. As used herein, a quantitative problem may be defined as a problem that can be quantified, counted, or measured. For example, a temperature sensor may detect that the temperature in a room is 85 degrees Fahrenheit when the expected temperature is 75 degrees Fahrenheit. Qualitative problems, on the other hand, can be defined as problems related to the look, sound, and impression of the experience or components within the experience, particularly as they relate to a guest's enjoyment of the experience.

[0020] For example, the sensor network 120 can enable the system 100 to address quality issues such as when one bulb in a set of multiple incandescent light bulbs burns out during a show or scene, negatively impacting the quality of the user's experience. However, if a camera or other imaging sensor (e.g., 130) detects a difference in the lighting of the scene, such as a deviation from a scheduled profile, the electronic device 102 can adjust the brightness or direction of other bulbs in the set to compensate for the malfunctioning bulb. The scheduled profile can be defined by utilizing a machine learning engine (e.g., 114), as will be discussed in more detail below. Additionally, the sensor network 120 can enable the system 100 to detect qualitative deviations, such as a guest being in an area where guests are not expected to be. Upon making this determination, the system 100 can alert a technical operator or take other corrective action (e.g., stopping and pausing operation of the experience), or perform such action automatically.

[0021] In addition to the sensor network 120, the DAQ 112 can collect web data 134 using software applications such as a web crawler to obtain information about anomalies or other problems within the attraction. For example, if a scene experiences a problem that may not be easily detected by a sensor (e.g., an animated character's wig comes off or an animated character experiences a costume malfunction), guests may notice the problem and post about it on social media. The DAQ 112 can detect the social media posts via the web crawler and trigger an alert.

[0022] Through the use of one or more centralized processing servers (e.g., electronic device 102), machine learning (ML) algorithms (e.g., executed via ML engine 114), and anomaly detection algorithms, system 100 can achieve improvements in computer-related technology by improving the accuracy and efficiency of anomaly detection, predictive analysis, and intelligent maintenance in an amusement park anomaly detection and maintenance system. Sensor network 120 along with other data sources such as web data 134 can provide a hierarchical structure for anomaly detection and maintenance. Sensors in sensor network 120 can provide redundancy to ensure anomaly detection that may go unnoticed in traditional monitoring and maintenance systems. For example, spotlights at an attraction can be equipped with current or voltage sensors that, when considered in conjunction with other detection values ​​provided to system 100 (e.g., light level values ​​in the production area), allow system 100 to determine if an electrical problem is causing the spotlight to be dimmed or switched off. The imaging sensor 128 can also be fixed on an area illuminated by the spotlight light, and the system 100 can be trained (e.g., via the ML engine 114) to detect the luminance or luminosity based on the imaging sensor 128. In this way, lighting problems of the spotlight can be detected by the system 100 based on the current or voltage sensor, the imaging sensor 128, or a combination thereof.

[0023] In some embodiments, the electronic device 102 may include a (ML) engine 114. While the ML engine 114 may be implemented outside of the controller 104 as described in FIG. 1, in other embodiments, the ML engine 114 may be implemented in other electrical circuitry (e.g., the controller 104 or the processor 106). Referring now to FIG. 2, a flow diagram of a method 200 for detecting anomalies associated with an experience and taking corrective action is described according to an embodiment of the present disclosure. At process block 202, the method 200 receives multiple layers of sensor data (e.g., the sensor network 120) indicative of characteristics of the experience. The sensor data may include quantitative information such as timing information regarding activating lights, audio equipment, and ride vehicle movement. The sensor data may also include qualitative information such as light levels of ambient lighting of the attraction or experience. Such information may be obtained from the attraction or experience as described in FIG. 3.

[0024] 3 illustrates an attraction or experience 300 in which the system 100 can be used, according to an embodiment of the present disclosure. The experience can feature a ride vehicle 310 equipped with vibration sensors 126 and temperature sensors 304, an animated figure 312, environmental components 314 (e.g., blowers to simulate wind on guests), audio equipment 306, stage lighting 302, audio sensors 130, temperature sensors 304, imaging sensors 128 (e.g., cameras or other imaging sensors), other sensors, and various DAQs 112 (e.g., communication hubs) for collecting and sharing data (e.g., over a network) of the electronic device 102, etc. The animated figure 312 can have multiple actuators to enable movement of the animated figure 312. The actuators of the animated figure 312 can be equipped with various sensors, such as torque sensors, pressure sensors, temperature sensors, gyrometers, motion sensors, speed sensors, vibration sensors, infrared sensors, etc. Additionally, guests may wear biometric sensors 132 to enable monitoring and / or collection of certain biometric data. While the sensors mentioned above are described in experience 300, it should be noted that any suitable sensors may be included in experience 300. For example, ride vehicle 310 may include any suitable sensors (e.g., a motion sensor, a speed sensor, a weight sensor, a gyrometer, a temperature sensor 304, a vibration sensor 126, an acceleration sensor, or any combination thereof).

[0025] The electronic device 102, and in particular the controller 104 of the electronic device 102, can receive data from various components (e.g., the ride vehicle 310, the animated character 312, the stage lights 302, the environmental components 314, etc.) and / or can receive data from sensors of the sensor network 120 that are communicatively coupled to or otherwise monitoring the various components and / or conditions. The controller 104 can receive the data and adjust actuators of the animated character 312, adjust lighting, adjust thermostats, control effects, adjust airflow, control the ride vehicle 310, etc. (including combinations thereof). For example, based on the data received regarding the animated character 312, the controller 104 can adjust actuators to cause the animated character 312 to move in a direction, to orient toward a particular guest or group of guests, or to interact with an element of the experience 300. Based on the data received regarding the ride vehicle 310, the controller 104 can cause the ride vehicle 310 to speed up, slow down, stop, turn, activate hydraulic systems of the ride vehicle 310, etc. The controller 104 can adjust the stage lighting 302 (e.g., adjusting position, brightness, color, etc.), control environmental components 314, etc.

[0026] In process block 202 of method 200, the experience 300 may undergo several cycles under normal operating conditions (e.g., as inspected by a human technical operator) to acquire this data. For example, cycling may include movement of the ride vehicle experience to determine appropriate initiation and response to verify that the ride vehicle experience is not only operating as originally intended, but also that the ride vehicle experience responds to the presence of guests and / or the exact location intended. In this phase, the ML engine 114 may collect and train on the data gathered through cycling to determine the required operating parameters of the experience. Upon collecting a sufficient amount of training data, the ML engine 114 may begin to process and classify the data. In the processing and classification phase, supervised and / or unsupervised machine learning may be performed by the ML engine 114. Based on the results of the processing and classification phase, the ML engine 114 may determine and code the parameters of the normally functioning experience.

[0027] The experience can be cycled repeatedly to allow the ML engine 114 to execute multiple layered processing passes, gradually learning additional aspects and parameters of the observed experience. For example, there can be a processing pass in which the color and intensity of the lighting (e.g., detected via the imaging sensor 128 or the characteristics of the stage lights 302) are learned and accumulated over the system 100. By sampling the experience 300 frame by frame over a known time unit, the system 100 can determine whether the stage lights 302 are functioning properly to specifications and targeted as intended. The system 100 can detect anomalies such as flickering, stalling, quality degradation, or timing and start-up errors. Another processing pass can determine whether the animated figures 312, environmental elements 314, and / or other action equipment are starting properly, moving within expected movement profiles, and where and when movement is expected to occur under normal conditions.

[0028] Based on the information acquired at process block 202, the method 200 may generate a profile of the experience 300 based on the sensor data received at process block 204. The profile may include baselines and thresholds that indicate expected ranges of features or aspects of the experience 300. For example, a profile in which the equipment in the experience 300 (e.g., the stage lights 302, the audio equipment 306, the environmental components 314, and the animated figures 312) have been determined to operate according to specifications and expectations may be designated as an A profile. However, a profile in which the equipment in the experience 300 has been determined to operate outside of specifications and expectations may be designated as a B profile. Additional profiles of different features or available features (e.g., profiles in warm or cold climates) may similarly be designated as a profile type (e.g., a C profile, a D profile, etc.).

[0029] In query block 206, method 200 can determine whether experience 300 is functioning properly according to specifications and expectations. That is, data 207 from the current experience (e.g., essentially real-time data from experience 300) can be compared to a defined profile, established as part of process block 204. Throughout the cycling and processing passes of experience 300, thresholds for the profile can be determined, outside of which the profile can receive different designations, within which the designations can remain even if differences in aspects and characteristics of experience 300 are detected. For example, if during operation of experience 300, system 100 detects that stage lighting 302 is dim due to an expected technical error, system 100 can determine this as being a deviation from profile A, although it does not exceed the thresholds of profile A. Under these conditions, it can be determined in query block 206 that experience 300 is operating correctly, and thus method 200 can continue to receive sensor data indicative of the characteristics of experience 300 (e.g., in process block 202). However, if animated figure 312 experiences a technical issue that renders it completely immobile, this can cause the profile of experience 300 to be assigned to B profile, C profile, etc. (e.g., exceeding the A profile threshold and entering a separate profile). Furthermore, individual identification of data 207 as corresponding to an unacceptable profile (e.g., profile X) can result in the shutting down of the actual usable features of experience 300, while individual identification of data 207 as corresponding to a less than optimal profile (e.g., B profile) can result in the mere adjustment of the usable features of experience 300.

[0030] Depending on the parameters and boundaries specified by the user of the system 100, it may be determined that the B profile or the C profile is an improper operation of the experience 300, and thus, corrective action may be determined and executed in process block 208. The corrective action may include performing automated maintenance on the malfunctioning equipment, such as having the controller 104, based on the information received from the ML engine 114, cause the experience 300 to adjust the current to a malfunctioning stage light 302 that is outputting less brightness than expected, or send a command to the controller 104 to cause the experience 300 to adjust other equipment that is the primary cause of the malfunctioning equipment (e.g., adjusting the brightness of another stage light 302 to compensate for the malfunctioning stage light 302).

[0031] As discussed above, the controller 104 can receive data from various components, such as the ride vehicle 310 and / or the animated character 312, and can adjust actuators of the animated character 312 and / or control the ride vehicle 310 as appropriate. Additionally or alternatively, the controller 104 can adjust actuators of the animated character 312 and / or control the ride vehicle 310 based on the profile designation of the experience 300. For example, if the method 200 designates the profile of the experience 300 as an A profile, the controller 104 can cause actuators to be adjusted to cause the animated character 312 to move in a certain direction, look towards a particular guest or group of guests, interact with elements of the experience 300, and the controller can cause the ride vehicle 310 to accelerate at a particular location of the experience 300. However, if the method 200 specifies the profile of the experience 300 as an X file, the controller 104 can prevent the actuators from being adjusted to move the animated character 312, can prevent the ride vehicle 310 from accelerating, and can stop the ride vehicle 310 at a particular location in the experience 300.

[0032] Corrective actions can also include sending an alert (e.g., to the alert panel 308) to notify a technical operator about the malfunction. If the malfunction requires urgent action, the ML engine 114 can send an urgent alert to the technical operator and cause the experience 300 to stop or pause operation.

[0033] Through method 200, ML engine 114 can learn to individually recognize known and new anomalies, as well as predict anomalies that will occur in the future. For example, if ML engine 114 determines that a stage light 302 is gradually decreasing in brightness prior to the bulb burning out, ML engine 114 can provide an alert to a technical operator, and if ML engine 114 detects that a stage light 302 is gradually decreasing in brightness, the alert can include an estimate of how long it will take for the bulb in the stage light 302 to burn out. In this manner, system 100 can enable predictive maintenance within experience 300, allowing a technical operator to take corrective action prior to a malfunction, thereby maintaining the quality of experience 300.

[0034] System 100 can also apply the machine learning performed in experience 300 to a different experience through ML engine 114. Data learned from experience 300 can be extrapolated and retargeted to another sufficiently similar experience by implementing a deep learning process known as transfer learning. Transfer learning allows a well-trained ML model to be reused and repurposed to make observations or predictions for a different but related problem setting. For example, using data learned about the operational characteristics of stage lights 302 in experience 300, ML engine 114 can uniquely identify and predict issues that may arise with stage lights in a different experience.

[0035] In some embodiments, the system 100 and the experience 300 can utilize local sensor networks that are not linked together via a single network. FIG. 4 is a block diagram illustrating a system 400 of a local unlinked sensor network, according to an embodiment of the present disclosure. Sensors 404A, 404B, 404C, and 404D (collectively referred to as sensors 404) can be various sensors in the experience 300. These sensors can communicate data to a communications hub 402 (e.g., electronic device 102). The communications hub 402 can receive sensor data (e.g., controller 104), analyze sensor data from the sensors 404 (e.g., ML engine 114), and send commands (e.g., via controller 104) to the sensors 404 or other components within the experience 300. Additionally, the sensors 404 can communicate among themselves. The communications hub 402 and the sensors 404 can be components of a sensor network 406. Similarly, the communications hub 410 can receive signals from devices 412 communicatively coupled to sensors 414A and 414B (collectively referred to as sensors 414) (e.g., electronic devices (e.g., 102) and / or controllers (e.g., 104) communicatively coupled to the animated figures 312 or ride vehicles 310). The communications hub 10 can communicate with the devices 412 and the sensors 414 within the devices 412, and the communications hub 410 can be components of a sensor network 416. The communications hub 410 can communicate with the devices 412 and the sensors 414, but cannot communicate with the communications hub 402, and thus the sensor network 416 can be unable to communicate with the sensor network 406.

[0036] In comparison to FIG. 4, in some embodiments, the system 100 can leverage an interconnected system of local sensor networks. As discussed above, in some embodiments, the system 100 can leverage and report data to other systems within the experience 300. FIG. 5 is a block diagram illustrating an interconnected local sensor and device network 500, according to an embodiment of the present disclosure. In FIG. 5, a central communication hub 502 can collect and communicate data from sensors 504A, 504B, 504C (collectively referred to as sensors 504 or network sensors). The sensors 504 can also communicate with each other. One sensor (e.g., 504A) can act as a smaller communication hub with respect to other sensors (e.g., 504B), collecting information and sending commands to the other sensors. The local communication hub 506 can also collect data from the sensors 504 as well as from devices 508 equipped with sensors 510A, 510B, and 510C, collectively referred to as sensors 510 (or device sensors 510). In this manner, the devices 508 and the sensors 510 within the devices 508 can communicate with each other and with the sensors 504. The central communications hub 502 can also communicate with the local communications hubs 506 via wired or wireless communications (e.g., via WiFi, a cellular network, etc.). While only one local communications hub 506 is shown, it should be understood that there can be any number of local communications hubs in the system 100. Additionally, local communications hubs can be assigned to areas of the experience 300, to particular pieces of equipment of the experience 300 (e.g., animated character 312), or to subsystems of particular equipment (e.g., a set of actuators within animated character 312).

[0037] Utilizing the network 500, a problem detected at one sensor (e.g., 504B) in the network 500 can be communicated to other sensors (e.g., 504A, 504C, 510) in the network 500 as well as other equipment (e.g., device 508) such as the controller in the animated figure 312, the environmental components 314, etc. For example, if an increase in temperature above a threshold is detected by the temperature sensor 304, the temperature sensor 304 can connect the increase in temperature across the network 500 and the ML engine 114, via the controller 104, can activate one or more fans, adjust settings on a central air conditioning unit, or reduce the output of certain heat-producing elements within the experience 300.

[0038] 4 and 5, the communication hubs 402 and 502 described may incorporate artificial intelligence, control, diagnostic programs, algorithms, look-up tables, and combinations thereof to analyze and control the characteristics of the experience 300. These control characteristics (e.g., artificial intelligence or learning algorithms) of the communication hubs 402 and 502 may be trained based on real or virtual data. In some embodiments, the training data may be augmented with three-dimensional (3D) (e.g., via the 3D modeling engine 116) information about the observed experience 300. By informing the system 100 of the global positions of sensors in the sensor network 120 in relation to known computer-based, time-varying 3D data, it may be permitted to reposition, remove, or add additional sensors, devices, and other equipment from certain observation angles without retraining. For example, given the pixel data of image sensor 128 and knowledge of where a particular pixel aligns in the 3D set, image sensor 128 can be retrained from a new angle, reducing or eliminating the time normally required to add, remove, move or remount a new image sensor. Thus, by using an interconnected network of sensors, devices and equipment, such as network 500 depicted in FIG. 5, in conjunction with the transfer learning process and 3D modeling engine 116 discussed above, system 100 can reduce or eliminate the time and / or processing power normally required in adding, removing, moving and / or reconfiguring sensors, devices and equipment.

[0039] Additionally, using the 3D modeling engine 116, the system 100 can be enabled to detect and correct some positional errors of the equipment and sensors. For example, if the system 100 (e.g., via the ML engine 114) detects an unexpected reading from an image sensor 128, one or more other image sensors 128 can observe the position of the problematic image sensor 128, compare the position against an expected position based on the global 3D model, determine that the problematic image sensor 128 is misaligned, and send feedback to the system 100, thereby allowing the system 100 to correct the position of the problematic image sensor 128. Indeed, the system 100 can be trained based on the 3D modeling and / or function using the 3D modeling as a baseline template for comparison with ongoing data (e.g., essentially real-time data from an attraction or experience).

[0040] While only certain features of the disclosure have been shown and described herein, many modifications and changes will occur to those skilled in the art. It is therefore understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the disclosure. It should be understood that any features described and depicted in connection with the above-discussed aspects may be combined in any suitable manner. The technology described and claimed herein clearly advances the state of the art, and thus reference is made to and applied to tangible objects and specific examples of a practical nature that is not abstract, vague, or purely theoretical. Furthermore, if any claim appended at the end of this specification includes one or more elements specified as a "method of [performing] [function]" or "step of [performing] [function]," it is intended that such elements be construed under 35 U.S.C. § 112(f). However, with respect to any claim that contains an element specified in any other manner, such element is not to be construed under 35 USC 352(f).

Claims

1. 1. A method for monitoring an amusement park, comprising: receiving, via a plurality of sensors, multiple layers of first sensor data characteristic of the experience; generating a profile of the experience based on the first sensor data, the profile including a baseline and a threshold indicating acceptable ranges of characteristics; receiving second sensor data and third sensor data via the plurality of sensors; determining that the experience operates appropriately in response to individually recognizing characteristics of the second sensor data that deviate from the baseline but do not exceed the threshold; and performing corrective action in response to individually recognizing a characteristic of the third sensor data that deviates from the baseline and exceeds the threshold.

2. the plurality of sensors may include cameras and / or other optical sensors, audio sensors, vibration sensors, UV sensors, tactile sensors, weight sensors, motion sensors, temperature sensors, humidity sensors, or any combination thereof; The method of claim 1.

3. the deviation includes a qualitative deviation from the profile. The method according to claim 1 .

4. The corrective action includes triggering an alert notification. The method according to claim 3.

5. the corrective action includes dynamically adjusting one or more components qualitatively associated with the deviation to correct or mitigate a cause of the deviation. The method according to claim 3.

6. one or more sensors of the plurality of sensors are disposed on and / or within a ride vehicle of the experience; The method of claim 1.

7. one or more sensors of the plurality of sensors are disposed on and / or within an animated figure associated with the experience; The method of claim 1.

8. using machine learning on the sensor data to detect the deviations quantitatively and qualitatively from the profile of experience. The method of claim 1.

9. applying the machine learning from the experience to a second experience. The method according to claim 8.

10. A machine learning engine is trained on a multi-dimensional model of the experience. The method according to claim 8.

11. the multi-dimensional model of the experience uniquely identifies the location of one or more sensors of the plurality of sensors within the experience; The method of claim 10.

12. Network and one or more communication hubs communicatively coupled to one other communication hub via the network; 1. A ride vehicle including one or more ride vehicle sensors, the one or more vehicle sensors are communicatively coupled to at least one of the one or more communication hubs; An animated figure having an actuator and an actuator sensor, the actuator sensor is communicatively coupled to at least one of the one or more communications hubs; a controller configured to receive data from the ride vehicle sensors and data from the actuator sensors via the one or more communications hubs, the controller further configured to adjust actuators to control the ride vehicle based on a difference between a baseline relevant value and a currently detected relevant value of data from the one or more ride vehicle sensors and data from the actuator sensors. Visual scene monitoring system.

13. The vehicle sensor includes a vibration sensor, a temperature sensor, a motion sensor, a speed sensor, an acceleration sensor, or a combination thereof. The system of claim 12.

14. the actuator sensor includes a vibration sensor, a temperature sensor, a torque sensor, a pressure sensor, or any combination thereof; The system of claim 12.

15. The one or more communications hubs, via the controller, collecting sensor data from the vehicle sensors; Analyzing vehicle sensor data; and configured to send a command, send an alert notification, or both, to the actuator sensor of the animated figure based on the analyzed ride vehicle sensor data. The system of claim 12.

16. via the controller, the one or more communications hubs: collecting sensor data from the actuator sensor; Analyzing the actuator sensor data; and and configured to send a command, send an alert notification, or both to the ride vehicle based on the analyzed actuator sensor data. The system of claim 12.

17. A tangible, non-transitory computer-readable medium, comprising computer-readable instructions; When executed by a processor of one or more electronic devices, the electronic devices are receiving first sensor data indicative of an amusement park experience via a plurality of sensors; generating a profile of the amusement park experience based on the first sensor data; The profile includes baselines and thresholds that indicate acceptable ranges of features; receiving second sensor data and third sensor data via a plurality of sensors; determining that an experience is operating appropriately in response to individually recognizing a characteristic of the second sensor data that deviates from the baseline but does not exceed a threshold; performing corrective action in response to identifying a characteristic of the third sensor data that deviates from the baseline and exceeds a threshold. Tangible, non-transitory computer-readable medium.

18. The corrective action may include dynamically adjusting one or more components associated with the deviation in a qualitative manner to correct or mitigate the cause of the deviation.

20. The tangible, non-transitory computer readable medium of claim 17.

19. and computer readable instructions that, when executed by one or more processors of an electronic device, cause the electronic device to use machine learning on the first sensor data, the second sensor data, the third sensor data, or any combination thereof, to detect the deviations quantitatively and qualitatively from the profile of the amusement park experience.

20. The tangible, non-transitory computer readable medium of claim 17.

20. and computer readable instructions that, when executed by one or more processors of an electronic device, cause the electronic device to apply the machine learning from the amusement park experience to a second amusement park experience.

20. The tangible, non-transitory computer readable medium of claim 19.

Images