Systems and methods for monitoring visual scenes
Patent Information
- Application Number
- ES2023705452T
- Authority / Receiving Office
- ES · ES
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2022-12-29
- Filing Date
- 2023-01-04
- Publication Date
- 2026-09-15
- Estimated Expiration
- 2043-01-04
Smart Images
Figure 00000011_0000 
Figure 00000012_0000 
Figure 00000013_0000
Abstract
Description
Systems and methods for monitoring visual scenes Background This section is intended to introduce the reader to various aspects of the technique that may be related to various aspects of the techniques described and / or claimed below. It is believed that this discussion is helpful in providing the reader with background information to facilitate a better understanding of the various aspects of this disclosure. Accordingly, these claims should be understood to be read in this light, and not as admissions of prior art. Amusement parks and other entertainment venues contain experiences (e.g., ride vehicles, animated figures (e.g., robotic characters), scenes, attractions, and more) to entertain park visitors. As these experiences become more technologically advanced and complex, the components within them can benefit from more robust monitoring and maintenance to ensure visitor safety and optimal or improved operation. Therefore, it is now recognized that utilizing a variety of sensors, machine learning, and multidimensional modeling techniques is advantageous for enabling faster anomaly detection, automated alerting, predictive maintenance, and dynamic remediation of the experience.WO 2015179298 A1 describes a passenger control system comprising a plurality of passenger vehicles positioned along a route. Each vehicle includes a vehicle controller configured to control its movement, a position tracking system configured to facilitate the identification of the vehicle's location, and a vehicle transceiver communicating with the vehicle controller. The passenger control system includes a primary controller and transceiver in communication, and a primary wireless network formed by the vehicle and the primary transceivers, including at least the primary controller and the vehicle controller of each vehicle. The primary controller is configured to receive location data from the respective vehicles via the primary wireless network.The primary and vehicle controllers of each vehicle are configured to provide a control loop for each vehicle based on data indicative of each vehicle's location. Summary Certain embodiments consistent in scope with the subject matter originally claimed are summarized below. These embodiments are not intended to limit the scope of the disclosure; rather, they are intended to provide only a brief summary of certain disclosed embodiments. Indeed, the present disclosure may encompass a variety of forms that may be similar to or different from the embodiments described below. In one embodiment, a method for monitoring an amusement park experience may include receiving, via multiple sensors, multiple layers of first sensor data indicative of experience characteristics. The method may generate an experience profile based on the first sensor data, where the profile includes a baseline and a threshold indicating an acceptable range of characteristics. The method may receive second sensor data and third sensor data via the multiple sensors. The method may determine, in response to identifying characteristics in the second sensor data that deviate from the baseline but do not exceed the threshold, that the experience is operating appropriately. The method may also, in response to identifying characteristics in the third sensor data that deviate from the baseline and exceed the threshold, take corrective action. In one embodiment, a system may include a network and one or more communication hubs communicatively coupled to each other via the network. The system may also include a passenger vehicle comprising one or more passenger vehicle sensors, where the one or more passenger vehicle sensors are communicatively coupled to at least one of the one or more communication hubs. Furthermore, the system may include an animated figure, the animated figure including an actuator and an actuator sensor, where the actuator sensor is communicatively coupled to at least one of the one or more communication hubs. The system may also include a controller capable of receiving data from one or more passenger vehicle sensors and data from the actuator sensor via the one or more communication hubs.The controller can adjust the actuator and control the passenger vehicle based on a discrepancy between a relative baseline value and a currently detected relative value from data from one or more passenger vehicle sensors and actuator sensor data. In one embodiment, one or more tangible, non-transient, computer-readable means are provided in accordance with this disclosure. The one or more tangible, non-transient, computer-readable means comprise instructions that, when executed by at least one processor, cause the at least one processor to receive, via multiple sensors, initial sensor data indicative of features of an amusement park experience. The processor may generate a profile of the amusement park experience based on the initial sensor data, and the profile may include a baseline and a threshold indicating an acceptable range of features.The processor can receive a second and a third sensor data point from multiple sensors and determine, based on the identification of characteristics in the second sensor data point that deviate from the baseline but do not exceed the threshold, that the experience is operating appropriately. However, based on the identification of characteristics in the third sensor data point that deviate from the baseline and exceed the threshold, the processor can take corrective action. Brief description of the drawings These and other features, aspects, and advantages of this disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings, in which identical characters represent identical similarities throughout the drawings, where: Figure 1 is a block diagram of an anomaly detection and monitoring system, in accordance with one aspect of this disclosure; Figure 2 is a flowchart of a method for detecting an experience-related anomaly and taking corrective action using the system in Figure 1, in accordance with one aspect of this disclosure; Figure 3 illustrates an experiment in which the system in Figure 1 can be used, in accordance with one aspect of this disclosure; Figure 4 is a block diagram illustrating a system of unlinked, localized sensor networks, in accordance with one aspect of this disclosure; and Figure 5 is a block diagram illustrating a network of interconnected localized sensors and devices, in accordance with one aspect of this disclosure. Detailed description The following section will describe one or more specific realizations of this disclosure. In an effort to provide a concise description of these realizations, not all features of an actual implementation may be described in the memorandum. It should be appreciated that in developing any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific objectives, such as meeting system-related and business-related constraints, which may vary from implementation to implementation. Furthermore, it should be appreciated that such a development effort could be complex and time-consuming, but would nevertheless be a routine design, fabrication, and manufacturing undertaking for the subject matter experts who benefit from this disclosure. When introducing elements from various embodiments of this disclosure, the articles "a," "an," and "the" are intended to mean that there is one or more of the elements. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there may be additional elements other than those listed. Furthermore, references to "embodiment" or "an embodiment" in this disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the listed features. Theme parks and similar entertainment venues are becoming increasingly popular. Furthermore, immersive experiences within these venues are in high demand. To provide novel and exciting experiences, attractions, such as rides and passageways (e.g., visual shows incorporating live action, animated figures, computer-generated imagery, and more), have become increasingly complex, integrating lighting, sound, movement, interactive elements, visual media, and other features. Consequently, the components within these attractions can benefit from more comprehensive and holistic monitoring and maintenance. Conventional monitoring and maintenance systems include disparate sensor clusters or networks and a manual regime of inspections prescribed by technicians.Such conventional systems may fail to detect certain maintenance and / or user experience issues due to human error, or they may fail to detect maintenance and / or user experience issues due to a lack of automated monitoring (e.g., through sensors, cameras, and so on). As can be seen, a system that utilizes a multifaceted, layered, globally connected network of sensors, multidimensional models, and machine learning engines can provide a more robust, accurate, responsive, and intelligent monitoring and maintenance system for amusement park attractions. In light of the above, the present implementations are generally directed toward a method and system for automated monitoring, anomaly detection, correction, mitigation, and / or predictive maintenance in theme park experiences. Specifically, the present implementations are aimed at collecting, through a network of communicatively coupled sensors, data on a variety of aspects and components within an experience, using machine learning to detect and / or predict quantitative and qualitative problems, dynamically addressing the anomaly and / or triggering an alert regarding the anomaly. Visual aspects, control features, audio, animated figure aspects, and monitoring and maintenance components and / or aspects are prepared according to the present techniques to provide multifaceted and layered monitoring and maintenance of the experience.Multifaceted, layered monitoring and maintenance provide robust and intelligent experience monitoring. Layering is achieved, at least in part, by using various data sources or streams (e.g., audiovisual data, infrared data, social media data, and so on) to detect, predict, and / or correct subtle anomalies that can nevertheless affect the quality of a visitor's experience. Due to the complex nature of visitor-experience interactions, in some implementations, control instructions from an artificial intelligence (AI) or machine learning engine can coordinate sensor data, equipment performance, and similar information to detect and address (e.g., correct or mitigate the effects of) an anomaly. Furthermore, numerous iterative and variable routines are included to incrementally improve aspects of the monitoring and maintenance system. Procedures, according to this disclosure (applicable to procedures illustrated in Figures 1-5), for monitoring an amusement park experience include several different procedural stages and aspects. Some of these stages or procedures may be performed in parallel or in different orders. Some stages may be processor-based operations and may involve controlled equipment (e.g., actuators). In addition, some procedures may be performed iteratively to achieve a desired result. Therefore, while several different procedural stages may be discussed in a particular order herein, the procedural stages may not necessarily be performed in the order presented in this disclosure.While some specific stages of an operation may necessarily occur before other specific stages (e.g., as logic dictates), the list of certain operation orders is provided primarily to facilitate discussion. For example, stating that a first or initial stage includes a particular operation is not intended to limit the scope of disclosure to such initial stages. Rather, it should be understood that additional stages may be performed, certain stages may be omitted, referenced stages may be performed in an alternative order or in parallel where appropriate, and so on. However, the disclosed operation orders may be restrictive when stated as such. Figure 1 is a block diagram of an anomaly detection and monitoring system 100 (e.g., the system), in accordance with this disclosure. As illustrated, the system 100 includes an electronic device 102, which may take the form of any suitable electronic computing device, such as a computer, laptop, personal computer, server, mobile device, smartphone, tablet, handheld device, and so forth. The electronic device 102 may include a controller 104 comprising one or more processors 106 and one or more memory and / or storage devices 108.One or more processors (e.g., microprocessors) may execute software programs and / or instructions (e.g., stored in memory) to facilitate the determination of probabilities and / or occurrences of changes in leisure experiences (e.g., relative to a baseline experience) and adjust control accordingly. Furthermore, one or more processors may 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, one or more processors may include one or more reduced instruction set processors (RISC). The one or more memory devices 108 may store information such as control software, lookup tables, configuration data, and so forth. In some embodiments, the one or more processors 106 and / or the one or more memory devices 108 may be external to the controller 104 and / or the electronic device 102. The one or more memory devices 108 may include a tangible, non-transient, 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 may store a variety of information and may be used for various purposes.For example, one or more memory devices 108 may store machine-readable and / or processor-executable instructions (e.g., firmware or software) for execution by one or more processors 106, such as instructions for determining the probability that an entertainment experience (e.g., automated positioning of an animated figure) will tend to exceed an acceptable operating threshold or envelope (e.g., due to wear, component failure, control degradation, or the like) and adjusting operating or control characteristics accordingly. 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, a hard disk, or any other suitable optical, magnetic, or solid-state storage medium, or a combination thereof. The electronic device 102 may also include an electronic display 110 that enables a graphical and / or visual output to be displayed to a user. The electronic display 110 may use any suitable display technology and may include an electroluminescent display (ELD), a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic LED display (OLED), an active-matrix OLED display, a plasma display panel (PDP), a quantum dot LED display (QLED), and others. As illustrated, the electronic device 102 may include a data acquisition (DAQ) system 112 operable for sending and receiving information to and from a sensor network 120. For example, the electronic device 102 may include a communication interface that enables the controller 104 to communicate with servers and / or other computing resources of the sensor network 120 by means of a communication network (for example, a mobile communication network, a WiFi network, a local area network (LAN), a wide area network (WAN), the Internet, and the like). In some cases, at least some of the information received from the sensor network 120 can be downloaded and stored in the memory or storage devices 108 of the electronic device 102. The sensor network 120 may include ultraviolet sensors 122, infrared sensors 124, vibration sensors 126, image sensors 128, audio sensors 130, biometric sensors 132, and others.Although the above list of sensors is illustrated in Figure 1, it should be noted that any other appropriate sensor, such as an accelerometer, speed sensor, gyrometer, torque sensor, location sensor, pressure sensor, humidity sensor, light sensor, voltage sensor, current sensor, particle sensor, and so forth, may be employed in System 100. Furthermore, it should be understood that the sensors illustrated in Figure 1 represent any type of sensor that may be used in an attraction. The sensor network 120 enables system 100 to collect a vast amount of data related to an amusement park attraction, allowing system 100 to gain a granular view of the various aspects and components within the system. For example, the infrared sensor 124 can detect whether the wheels or engine of a passenger vehicle are emitting heat beyond a certain threshold. If so, it can trigger an alert (e.g., via controller 104) to technical operators, disable the passenger vehicle, or take any other appropriate action. Input combinations can also be evaluated using algorithms, lookup tables, or artificial intelligence. For example, data from the infrared sensor 124 can be analyzed in conjunction with vibration sensors 126 to detect a heat source related to wheel misalignment on a passenger vehicle, or similar issues.The sensor network 120 can enable system 100 to address both quantitative and qualitative issues in an amusement park attraction. As used herein, quantitative problems can be defined as problems that can be quantified, counted, or measured. For example, a temperature sensor that detects a room temperature of 85 degrees Fahrenheit (29.4°C) when the expected temperature is 75 degrees Fahrenheit (23.9°C). Conversely, qualitative problems can be defined as problems related to the appearance, sound, or feel of the experience or components within the experience, particularly as they relate to a visitor's enjoyment of the experience. For example, the sensor network 120 can enable system 100 to address qualitative issues if a bulb in a light cluster burns out during a show or scene, negatively impacting the user experience. However, if a camera or other image sensor (e.g., 130) detects a difference, such as a deviation from a predetermined profile, in the lighting of a scene, the electronic device 102 can adjust the brightness or direction of other bulbs in the light cluster to compensate for the malfunctioning bulb. The predetermined profile can be established using a machine learning engine (e.g., 114), as discussed in more detail below. Furthermore, the sensor network 120 can enable system 100 to detect qualitative deviations, such as a visitor being in an area where they are not expected to be.Upon making this determination, the 100 system can alert a technical operator or take other corrective action (e.g., stop or pause the operation of the experience) or automatically perform such actions. In addition to the sensor network 120, the DAQ 112 can collect public network data 134 using software applications such as public network crawlers to gather information about anomalies or other problems within an attraction. For example, if a scene experiences a problem that might not be easily detected by a sensor (e.g., an animated character's wig falls off or the animated character's costume malfunctions), a visitor might notice the problem and post it on social media. The DAQ 112 can detect the social media post via the public network crawler and trigger an alert. Through the use of one or more centralized processing servers (e.g., the electronic device 102), machine learning (ML) algorithms (e.g., executed by the ML engine 114), and anomaly detection algorithms, system 100 can enhance computer-related technologies by increasing the accuracy and efficiency of anomaly detection, predictive analytics, and intelligent maintenance in amusement park anomaly detection and maintenance systems. The sensor network 120, along with other data resources such as public network data 134, can provide a layered anomaly detection and maintenance system. The sensors in the sensor network 120 can provide redundancy to ensure the detection of anomalies that might go unnoticed in a conventional monitoring and maintenance system.For example, a spotlight on an attraction might be equipped with a current or voltage sensor that allows system 100 to determine whether an electrical problem is causing the spotlight to dim or turn off when considered in conjunction with other detected values (e.g., lighting level values in a parking area) provided to system 100. An image sensor 128 might also be fixed over an area illuminated by the spotlight, and system 100 might be trained (e.g., by means of the ML engine 114) to detect variations in luminance or brightness based on the image sensor 128. In this way, a lighting problem with the spotlight can be detected by system 100 based on the current or voltage sensor, the image sensor 128, or combinations thereof. In some embodiments, the electronic device 102 may include the (ML) motor 114. Although the ML motor 114 may be implemented outside of the controller 104, as illustrated in Figure 1, in other embodiments the ML motor 114 may be implemented in other circuits (for example, in the controller 104 or in the processor 106). Turning to Figure 2, a flowchart of a method 200 for detecting an anomaly related to an experience and taking corrective action, according to one embodiment of this disclosure, is illustrated. In process block 202, method 200 receives multiple layers of sensor data (for example, from the sensor network 120) indicative of characteristics of the experience. The sensor data may include quantitative information, such as timing information regarding the activation of lights, audio equipment, and passenger vehicle movement.Sensor data can also include qualitative information such as the ambient light level of an attraction or experience. Such information can be acquired from an attraction or experience, as illustrated in Figure 3. Figure 3 illustrates an attraction or experience 300 in which the system 100 may be used, according to an embodiment of this disclosure. The experience may feature a passenger vehicle 310 equipped with a vibration sensor 126 and a temperature sensor 304, an animated figure 312, environmental components 314 (e.g., a fan to simulate wind blowing on visitors), audio equipment 306, stage lights 302, an audio sensor 130, a temperature sensor 304, image sensors 128 (e.g., a camera or other image sensors), several DAQs 112 for collecting and sharing data (e.g., via a network) with other sensors and electronic devices 102 (e.g., communication concentrators), and so forth. The animated figure 312 may 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, and others. Additionally, visitors can wear biometric sensors 132 to allow for the monitoring and / or collection of certain biometric data. Although the sensors mentioned above are illustrated in experience 300, it should be noted that any appropriate sensor can be included in experience 300. For example, the passenger vehicle 310 can include any appropriate sensor (e.g., a motion sensor, a speed sensor, a weight sensor, a gyrometer, temperature sensor 304, vibration sensor 126, an accelerometer, or any combination thereof). The electronic device 102, in particular the controller 104 of the electronic device 102, can receive data from various components (e.g., passenger vehicle 310, animated character 312, stage lights 302, environmental components 314, and so forth) and / or can receive data from sensors of the sensor network 120 that are communicatively coupled or otherwise monitoring the various components and / or conditions. The controller 104 can receive the data and adjust the actuators of the animated character 312, adjust the lighting, adjust the climate control, control the effects, adjust the airflow, control the passenger vehicle 310, and the like (including combinations thereof).For example, controller 104 can, based on data received regarding animated character 312, adjust the actuators to make animated character 312 move in a certain direction, face a particular visitor or group of visitors, or interact with elements of experience 300. Controller 104 can, based on data received regarding passenger vehicle 310, accelerate, decelerate, stop, change direction, couple to a hydraulic system of passenger vehicle 310, and so on. Controller 104 can adjust stage lights 302 (e.g., adjust position, brightness, color, and so on), control environmental components 314, and so on. In process block 202 of method 200, experience 300 can be subjected to several cycles under normal operating conditions (e.g., as verified by a human technical operator) to obtain this data. For example, the cyclic operation might include moving a passenger vehicle experience to determine the appropriate triggering and response in order to verify not only that the passenger vehicle experience is operating according to the original creative intent, but also that the experience is sensitive to the visitor's presence and / or precise location as intended. In this phase, the ML 114 engine can collect and train the data accumulated through cyclic operation to determine the desired operating parameters of the experience. After collecting a sufficient amount of training data, the ML 114 engine can begin processing and labeling the data.In the processing and labeling phase, the ML 114 engine will perform supervised and / or unsupervised machine learning. Based on the results of the processing and labeling phase, the ML 114 engine can determine and encode the parameters of a normal operating experience. The experience can be run cyclically repeatedly to enable the ML engine 114 to perform multiple layered processing passes, gradually learning additional aspects and parameters from the observed experience. For example, there might be a processing pass in which the color and intensity of the lighting (e.g., detected by the image sensors 128 or the characteristics of the stage lights 302) are learned and stored by system 100. By sampling the experience 300 frame by frame at known time intervals, system 100 can determine whether the stage lights 302 are functioning properly according to specifications and are being directed as intended. System 100 can detect anomalies such as flickering, interruptions, degradation, or timing and triggering errors.Another processing pass can determine if the animated figure 312, environmental components 314 and / or other action equipment are being triggered appropriately, moving within expected motion profiles, and determine where and when motion is expected to appear under normal conditions. Based on the information obtained in process block 202, method 200 can, in process block 204, generate profiles of experience 300 based on the received sensor data. The profiles can include a baseline and a threshold that indicate an expected range of the characteristics or aspects of experience 300. For example, a profile where it is determined that the equipment in experience 300 (e.g., stage lights 302, audio equipment 306, environmental components 314, and animated figure 312) operates according to the specification and expectation can be designated as profile A. However, a profile where it is determined that the equipment in experience 300 operates outside of the specification and expectation can be designated as profile B.Additional airfoils with different characteristics or operational aspects (e.g., a hot weather airfoil or a cold weather airfoil) may also be designated as certain airfoil types (e.g., C airfoil, D airfoil, and so on). In query block 206, method 200 can determine whether experience 300 is operating appropriately according to the specification and expectation. That is, data 207 from a current experience (e.g., essentially real-time data from experience 300) can be compared with established profiles set as part of process block 204. Through the processing passes and cyclical operation of experience 300, profile thresholds can be determined outside of which the profile may receive a different designation, but within which a designation may remain even if a deviation is detected in the aspects and characteristics of experience 300.For example, if during the operation of experience 300, system 100 detects that the stage lights 302 are dimmer than expected due to a technical error, system 100 can determine that this is a deviation from profile A, but not a deviation that exceeds the threshold of profile A. Under these conditions, it can be determined in query block 206 that experience 300 is operating properly, and thus method 200 can continue to receive sensor data indicative of characteristics of experience 300 (for example, in processing block 202). However, if animated figure 312 experiences a technical problem that renders it completely immobile, this can cause the profile of experience 300 to be designated as profile B, profile C, and so on (for example, beyond a threshold of profile A and into a separate profile).Furthermore, identifying data 207 as corresponding to a suboptimal profile (e.g., profile B) may result in a mere adjustment to operational aspects of experience 300, whereas identifying data 207 as corresponding to an unacceptable profile (e.g., profile X) may result in a halt to substantial operational aspects of experience 300. Depending on the parameters and limits designated by a system user 100, a B or C profile can be determined to be an inappropriate operation of the experiment 300, and thus, in process block 208, a corrective action can be determined and performed. The corrective action may include performing automated maintenance on the malfunctioning equipment, such as having controller 104, based on information received from the ML 114 motor, send a command that causes the experiment 300 to adjust the current to a malfunctioning stage light 302 that is emitting less brightness than expected, or having controller 104 send a command that causes the experiment 300 to adjust other equipment to account for the malfunctioning equipment (for example, adjusting the brightness of another stage light 302 to compensate for the malfunctioning stage light 302). As discussed earlier, controller 104 can receive data from various components, such as passenger vehicle 310 and / or animated character 312, and adjust the actuators of animated character 312 and / or control passenger vehicle 310 accordingly. Additionally or alternatively, controller 104 can adjust the actuators of animated character 312 and / or control passenger vehicle 310 based on the profile designation of experience 300. For example, if method 200 designates the profile of experience 300 as profile A, controller 104 can adjust the actuators to make animated character 312 move in a certain direction, face a particular visitor or group of visitors, or interact with elements of experience 300, and the controller can cause passenger vehicle 310 to accelerate at a particular location within experience 300.However, if method 200 designates the experience profile 300 as an X profile, controller 104 can prevent the actuators from adjusting to move the animated character 312 and can prevent the passenger vehicle 310 from accelerating or can stop the passenger vehicle 310 at the particular location of experience 300. Corrective action may also include sending an alert (for example, to a 308 alert panel) that informs technical operators of the malfunction. If the malfunction requires urgent action, the ML 114 engine may send an urgent alert to technical operators and cause the 300 experience to stop or pause its operation. Through method 200, the ML 114 engine can learn to identify known and new anomalies, as well as anticipate anomalies that may occur in the future. For example, if the ML 114 engine determines that stage lights 302 gradually experience a reduction in brightness before a bulb burns out, the ML 114 engine can trigger an alert to technical operators if it detects that a stage light 302 has gradually experienced a reduction in brightness, and it can include in the alert an estimate of how long it may take for the stage light 302 bulb to burn out. In this way, system 100 can enable predictive maintenance within experience 300 and can allow technical operators to take corrective action before a malfunction occurs, preserving the quality of experience 300. System 100, through the ML engine 114, can also apply the machine learning performed in experience 300 to a different experience. The data learned from experience 300 can be extrapolated and redirected to another sufficiently similar experience by implementing a deep learning process known as transfer learning. Transfer learning allows a sufficiently trained ML model to be repurposed and reused to make observations or predictions about a different but related set of problems. For example, using the data learned about the operational characteristics of stage lights 302 in experience 300, the ML engine 114 may be able to identify and anticipate problems that the stage lights might experience in a different experience. In certain embodiments, System 100 and Experiment 300 may utilize multiple localized sensor networks that are not linked to each other by a single network. Figure 4 is a block diagram illustrating a System 400 of unlinked localized sensor networks, according to one embodiment of this disclosure. Sensors 404A, 404B, 404C, and 404D (collectively referred to as Sensors 404) may be various sensors in Experiment 300. These sensors may communicate data to a communication concentrator 402 (e.g., Electronic Device 102). The communication hub 402 can receive sensor data (e.g., via controller 104) and can analyze sensor data from sensors 404 (e.g., via ML engine 114) and send commands (e.g., via controller 104) to sensors 404 or other components within the experience 300.Additionally, the 404 sensors can communicate with each other. The communication concentrator 402 and the 404 sensors can constitute a 406 sensor network. Similarly, a communication concentrator 410 can receive signals from a device 412 (e.g., an electronic device (e.g., 102) and / or a controller (e.g., 104) communicatively coupled to the animated figure 312 or the passenger vehicle 310) communicatively coupled to the 414A and 414B sensors (collectively referred to as the 414 sensors). Communication concentrator 10, device 412, and sensors 414 within device 412 can constitute a sensor network 416. Communication concentrator 410 can communicate with device 412 and sensors 414, but may not communicate with communication concentrator 402; therefore, sensor network 416 may not communicate with sensor network 406. In contrast to Figure 4, in certain embodiments, System 100 can utilize an interconnected network of local sensors. As discussed earlier, in certain embodiments, System 100 can utilize and report data to other systems within Experience 300. Figure 5 is a block diagram illustrating a network 500 of interconnected local sensors and devices, according to one embodiment of this disclosure. In Figure 5, a central communication concentrator 502 can collect data from and communicate with sensors 504A, 504B, and 504C (collectively referred to as sensors 504 or network sensors). The sensors 504 can also communicate with each other. Certain sensors (e.g., 504A) can act as smaller communication concentrators for other sensors (e.g., 504B), collecting information and sending commands to the other sensors.A local communication concentrator 506 can also collect data from sensors 504, as well as from a device 508 equipped with a sensor 510A, a sensor 501B, and a sensor 510C, collectively referred to as sensors 510 (or device sensors 510). In this way, device 508 and the sensors 510 within device 508 can communicate with each other and with sensors 504. The central communication concentrator 502 can also communicate with local communication concentrator 506 via wired or wireless communication (e.g., Wi-Fi, via a cellular network, etc.). Although only one local communication concentrator 506 is shown, it should be understood that there can be any number of local communication concentrators in system 100.In addition, a local communication hub can be assigned to an area of experience 300, a particular piece of equipment in experience 300 (e.g., animated character 312), or a subsystem of a particular piece of equipment (e.g., a set of actuators within animated character 312). Using network 500, a problem detected by a sensor (e.g., 504B) on network 500 can be communicated to other sensors (e.g., 504A, 504C, 510) on network 500, as well as to other equipment (e.g., device 508) such as controllers in animated figures 312, environmental components 314, and so on. For example, if temperature sensor 304 detects a temperature rise above a threshold, it can communicate this rise via network 500, and the ML motor 114 can, through controller 104, activate one or more fans, adjust the setting of a central air conditioning unit, or reduce the output of certain heat-producing elements within experience 300. With regard to Figures 4 and 5, the illustrated communication hubs 402 and 502 can incorporate artificial intelligence, controls, diagnostics, algorithms, lookup tables, and combinations thereof to analyze and control aspects of the 300 experience. These control features (e.g., artificial intelligence or learning algorithms) of the communication hubs 402 and 502 can be trained on real or virtual data. In certain embodiments, the training data can be augmented with three-dimensional (3D) information (e.g., by means of a 3D modeling engine 116) about the 300 experience.By informing system 100 of the global positions of the sensors in the sensor network 120 with respect to known, time-changing, computer-assisted 3D data, it becomes possible to reposition, remove, or add sensors, devices, and other additional equipment without retraining from certain viewing angles. For example, given the pixel data of an image sensor 128 and knowledge of where particular pixels align with the 3D scene, the image sensor 128 can retrain from a new angle, shortening or eliminating the time normally required to add, remove, move, or remount new image sensors.Thus, by using an interconnected network of sensors, devices, and equipment, such as the network 500 depicted in Figure 5, together with the previously discussed transfer learning processes and the 3D modeling engine 116, the system 100 can reduce or eliminate the time and / or processing power normally required to add, remove, move, and / or reconfigure sensors, devices, and equipment. Additionally, using the 3D modeling engine 116, system 100 can detect and correct certain positional errors in equipment or sensors. For example, if system 100 (e.g., via the ML engine 114) detects unexpected readings from an image sensor 128, one or more image sensors 128 can observe the position of the problematic image sensor 128, compare its position to an expected position based on the global 3D model, determine that the problematic image sensor 128 is misaligned, and send feedback to system 100, thereby enabling system 100 to correct the position of the problematic image sensor 128. In fact, system 100 can be trained on 3D modeling and / or operate using 3D modeling as a baseline template for comparison with ongoing data (e.g., essentially real-time data from an attraction or experience). Although only certain features of the disclosure have been illustrated and described herein, those skilled in the art will think of many modifications and changes. The scope of the invention is defined by the appended claims. It should be appreciated that any of the features illustrated or described with respect to the figures discussed above may be combined in any suitable manner.
Claims
1. A method for monitoring an amusement park experience, the method comprising: receiving, via a plurality of sensors (120), multiple layers of first sensor data indicative of experience characteristics; generating an experience profile based on the first sensor data, wherein the profile comprises a baseline and a threshold indicating an acceptable range of characteristics; receiving second sensor data and third sensor data via the plurality of sensors (120); determining, in response to identifying characteristics in the second sensor data that deviate from the baseline but do not exceed the threshold, that the experience is operating appropriately; and in response to identifying characteristics in the third sensor data that deviate from the baseline and exceed the threshold, taking corrective action. 2.The method of claim 1, wherein the plurality of sensors (120) comprises a camera and / or other optical sensor, an audio sensor, a vibration sensor, an ultraviolet radiation sensor, a touch sensor, a weight sensor, a motion sensor, a temperature sensor, a humidity sensor, or any combination thereof.
3. The method of claim 1, wherein the deviation comprises a qualitative deviation from the profile.
4. The method of claim 3, wherein the corrective action comprises: A) triggering an alert notification; or B) dynamically adjusting one or more components associated with the qualitative deviation in order to correct or mitigate a cause of the deviation.
5. The method of claim 1, wherein one or more sensors of the plurality of sensors (120) are arranged in and / or within: A) a passenger vehicle (310) of the experience; or B) an animated figure (312) associated with the experience. 6.The method of claim 1, comprising using machine learning on sensor data to detect quantitative and qualitative deviations from the experience profile.
7. The method of claim 6, comprising applying machine learning from the experience to a second experience.
8. The method of claim 6, wherein a machine learning engine (114) is trained on a multidimensional model of the experience.
9. The method of claim 8, wherein the multidimensional model of the experience identifies a location of one or more sensors from the plurality of sensors (120) within the experience. 10.A monitoring system (100) comprising: - a plurality of sensors (120) configured to detect: multiple layers of first sensor data indicative of experience characteristics; second sensor data; and third sensor data; - a processor (106) configured to: receive the first sensor data; generate an experience profile based on the first sensor data, wherein the profile comprises a.