Scenic spot control system and method using multi-layer perceptron neural network and machine learning

Abstract

A controller 30, 48 is used to provide a dynamic ride profile for the ride system 10. The controller 30, 48 is for accessing a data set indicative of a condition in an environment of the ride system 10 in response to an alert indicative of an obstacle in the environment to the ride system 10. A controller 30, 48 is configured to determine a classification from a plurality of classifications for the environment via a prediction engine 44, 58 trained using supervised machine learning based on the data set and a ride profile of the ride system 10. A controller 30, 48 is configured to determine, via a prediction engine 44, 58, one or more recommendations based on the data set and the classification, and visually or acoustically present the classification through the one or more recommendations.

Description

Background Art

[0001] The present disclosure relates generally to the field of amusement parks. More specifically, embodiments of the present disclosure relate to methods and apparatus for use in conjunction with an amusement park game, show, or ride.

[0002] Amusement parks often include a variety of attractions that provide unique experiences for patrons. For example, an amusement park may include a variety of rides and shows. As technology has continued to improve, the sophistication and complexity of such attractions has increased. For example, certain rides may provide visitors with an immersive experience, such as a series of vehicles that may carry riders through rooms with various features, including audio, video, and special effects features. With the ever-increasing sophistication and complexity of modern ride attractions and shows, and the corresponding increase in expectations among theme or amusement park patrons, improved and more creative monitoring and control systems are needed for amusement parks.

[0003] Additionally, a ride system or show performance may include complex systems such as multi-axis robots, hydraulic and electric motion bases, transport platforms, and custom assemblies with rapid modes of operation. Traditional techniques for monitoring a ride system or show performance have very stringent operating requirements and very difficult testing methods. It is now recognized that it is desirable to have a dynamic or changing operating environment for a ride system or show performance.

[0004] This section is intended to introduce the reader to various aspects of the technology that may be related to the various aspects of the technology presented, which are described and / or claimed below. It is believed that this discussion is helpful in providing the reader with background information to promote a better understanding of the various aspects of the present disclosure. Therefore, it should be understood that these statements are to be read in this light, and not as an admission of prior art. Summary of the invention

[0005] An overview of certain embodiments disclosed herein is set forth below. It should be understood that these aspects are presented only to provide the reader with a brief overview of these certain embodiments, and these aspects are not intended to limit the scope of the present disclosure. In fact, the present disclosure may encompass a variety of aspects, which may not be set forth below.

[0006] In one embodiment, a controller for a ride system for providing a dynamic ride profile is provided in accordance with the present disclosure. The controller includes a processor and a memory. The memory includes instructions stored thereon, which, when executed by the processor, cause the processor to perform operations, the operations including: accessing a data set indicating a condition in an environment of the ride system in response to an alert indicating an obstacle to the ride system; and determining a classification from a plurality of classifications for the environment via a prediction engine trained using supervised machine learning based on the data set and the ride profile of the ride system. The operations also include: determining one or more recommendations via the prediction engine based on the data set and the classification, and visually or audibly presenting the classification via the one or more recommendations.

[0007] In one embodiment, a method for providing a dynamic ride profile for a ride system is provided in accordance with the present disclosure. The method includes: accessing via a processor a data set indicating conditions in an environment of the ride system in response to an alert indicating an obstacle to the ride system, and determining a classification from a plurality of classifications of the environment via a prediction engine trained using supervised machine learning based on the data set and the ride profile of the ride system. The method also includes: determining via the prediction engine one or more recommendations based on the data set and the classification, and visually or audibly presenting the classification with the one or more recommendations.

[0008] In one embodiment, a ride system for providing a dynamic ride profile is provided according to the present disclosure. The ride system includes a ride vehicle that rides in an environment, and the ride vehicle includes an onboard sensor configured to collect vehicle data from the ride vehicle. The ride system also includes: a dynamic element that is disposed within the environment; and an off-vehicle sensor that is disposed outside the ride vehicle to collect dynamic element data indicating at least one aspect of the dynamic element. The ride system includes a controller. The controller includes one or more processors and a memory. The memory includes instructions stored thereon, which when executed by the one or more processors cause the one or more processors to perform operations, the operations including: accessing a data set indicating a condition in the environment of the ride system in response to an alert indicating an obstacle to the ride system; and determining a classification from a plurality of classifications for the environment via a prediction engine trained using supervised machine learning based on the data set and the ride profile of the ride system. The operations also include: determining one or more recommendations via the prediction engine based on the data set and the classification; and visually or audibly presenting the classification through the one or more recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] These and other features, aspects and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings, in which like characters represent like parts throughout the drawings, and in which:

[0010] Figure 1 is a schematic diagram of an embodiment of a ride system according to an embodiment of the present disclosure;

[0011] Figure 2 is a schematic perspective view and associated diagram of one embodiment of a simulated object in its riding profile according to one embodiment of the present disclosure;

[0012] Figure 3 is a schematic perspective view and associated logic diagram of one embodiment of a simulated object outside of its riding profile according to one embodiment of the present disclosure;

[0013] Figure 4 is a block diagram of an embodiment of a riding environment according to an embodiment of the present disclosure; and

[0014] Figure 5 A riding vehicle according to an embodiment of the present disclosure is Figure 4 A block diagram of an embodiment of a riding environment. DETAILED DESCRIPTION

[0015] One or more specific embodiments will be described below. In an effort to provide a concise description of these embodiments, not all features of an actual implementation are described in the specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, many implementation-specific decisions must be made to achieve the developer's specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. In addition, it should be appreciated that such development work may be complex and time consuming, but will be no more than a routine task of design, fabrication, and manufacturing for a person of ordinary skill having the benefit of this disclosure.

[0016] The presented embodiments are directed to a dynamic system for analyzing and responding to conditions in an attraction. A dynamic system according to the presented embodiments may be layered with a profile evaluation system (e.g., a lookup table for analyzing a ride profile) to facilitate analysis and operation to obtain more desirable results. Specifically, in certain situations, the dynamic system may override an initial assessment based on a profile evaluation system. This can be particularly useful in an attraction system that allows for user input and selection of options throughout an attraction sequence (such as a ride that allows a rider to direct a ride vehicle). For example, a lookup table for a ride profile (e.g., which may include multiple tables that vary based on rider size, preferences, age) may be used to make determinations about how certain aspects of the ride system should operate based on input made (e.g., sensor data). As a specific example, when a condition outside of a ride profile is detected in a user-directed ride, a correction may be indicated by a profile evaluation system based on exceeding the ride profile. However, in some cases, it may be desirable to continue without making such a correction. Specifically, for example, if a bird is detected as entering the ride path for a vehicle on a dark ride, this may be identified by the profile evaluation system as an event that extends beyond the ride profile, and the initial response may be to shut down the ride. However, a second dynamic layer of analysis may be provided in accordance with the presented embodiments that allows the system to override this initial response so that the ride can continue with slight or no modifications to avoid disrupting the ride experience. Additional details of the operation are discussed below.

[0017] 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 of the elements. The terms "comprising," "including," and "having" are intended to be inclusive, and mean that there may be additional elements besides the listed elements. Additionally, 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.

[0018] As used herein, the terms "connect," "connected," "connected with," and "being connected" are used to mean "directly connected with" or "connected with via one or more elements." Further, the term "set" is used to mean "an element" or "more than one elements." Further, the terms "coupled," "being coupled," "coupled together," and "coupled with" are used to mean "directly coupled together" or "coupled together via one or more elements."

[0019] Furthermore, as used herein, the terms "real time," "real-time," or "substantially real-time" may be used interchangeably and are intended to describe operations (e.g., computing operations) that are performed without any human-perceivable interruptions between operations. For example, as used herein, data associated with the systems described herein may be collected, transmitted, and / or used in control calculations in "substantially real time," such that data reading, data transmission, and / or data processing steps occur once per second, once every 0.1 seconds, once every 0.01 seconds, or even more frequently during operation of the system (e.g., while the system is operating). Furthermore, as used herein, the terms "continuously," "continuously," or "continuously" are intended to describe operations that are performed without any significant interruptions. For example, as used herein, control commands may be transmitted to a device every five minutes, every minute, every 30 seconds, every 15 seconds, every 10 seconds, every 5 seconds, or even more frequently, such that operating parameters of the device may be adjusted without any significant interruption of closed-loop control of the device. Furthermore, as used herein, the terms "automatic," "automated," "autonomous," and the like are intended to describe operations that are, for example, performed or caused to be performed by a computing system (i.e., solely by the computing system, without human intervention). Indeed, while certain operations described herein may not be explicitly described as being continuously and / or automatically performed in substantially real time during operation of a computing system and / or a device controlled by the computing system, it will be appreciated that these operations may in fact be continuously and / or automatically performed in substantially real time during operation of the computing system and / or a device controlled by the computing system to improve the functionality of the computing system (e.g., by not requiring human intervention, thereby facilitating faster operational decision-making, and by, for example, eliminating the possibility for human error to improve the accuracy of operational decision-making), as described in greater detail herein.

[0020] Creating elaborate environments in amusement parks has become more common, including scenery, special effects, audio-visual features, and other media elements that improve the experience of visitors. Visitors walk or ride (e.g., on a ride vehicle) to enter an environment (e.g., a show or scenic spot), and can interact with the environment or have an immersive experience in the environment. In order to keep the experience of visitors at a higher level than the standard and / or solve other problems (e.g., safety) related to the experience of visitors in the amusement park, the amusement park can be operated under certain standards. When the operation of a ride system or environment does not meet (one or more) corresponding standards, an alarm can be transmitted to the control system of visitors and the environment, such as to notify visitors to exit the environment or change their route, close one or more elements in the environment and the like. Due to the entertainment nature of an amusement park, these operating standards can be different for different environments, different ride systems and / or different visitors (e.g., visitors with different heights, weights, ages, etc.), to adapt to the expectations of individual visitors experiencing an amusement park.

[0021] According to the embodiment presented, ride profiles can be used to monitor and / or control the operating standards for certain rides. Ride profiles for various environments and / or ride systems of an amusement park can be provided by a ride designer traditionally, or determined based on historical data (e.g., a golden profile (GP), a CAM profile in a lookup table), and can be stored in a database. When the operation of an environment or a ride system is not within a visitor's ride profile, an alarm can be transmitted to the visitor or environment for a corresponding reaction, such as exiting the environment, changing the route of the ride, closing one or more elements in the environment, and the like. For example, in one embodiment, when a visitor is in an environment, the visitor's condition can be monitored by a sensor (e.g., distributed in the environment, on a ride vehicle, on a device attached to the visitor), and compared with the value of the corresponding ride profile stored in the database. When the visitor's condition is not within the corresponding ride profile, a triggering event can occur, and a corresponding alarm can be transmitted for the visitor associated with the ride profile. For example, a triggering event may be a software error that provides an incorrect value to an actuator in the environment and outputs an incorrect set point, or an actuator malfunctions and attempts to move to an unintended state (e.g., not in the ride profile provided by the ride designer or in the historical data used to determine the ride profile), which may cause the guest's condition in the environment to fall outside the corresponding ride profile. Based on the ride profile associated with the guest, a corresponding alert may be transmitted for the guest associated with the ride profile and request the guest to exit the environment or change the route of the ride.

[0022] However, under certain unexpected circumstances (e.g., not in the ride profile provided by the ride designer or in the historical data used to determine the ride profile), the operating criteria associated with the ride profile of the visitor in a particular situation (e.g., associated with different environments, different ride vehicles, and / or desired experiences) may not be accurate because it is determined based on the iterative approach and / or historical data of the ride designer used to ultimately determine the desired ride profile. In particular, due to the entertainment nature of an amusement park, the operating criteria may be different for different environments, different ride systems, and / or different visitors (e.g., visitors of different heights, weights, ages, etc.). Therefore, real-time re-evaluation of the visitor's condition and determination of a dynamic ride profile may be desirable to improve the experience of visitors in an amusement park (e.g., within a particular attraction). For example, in one embodiment, an alert may be transmitted to a visitor, which may request the visitor to exit the environment (due to a certain obstacle in the environment). However, the prediction engine may determine that it is unnecessary for the visitor to exit the environment, and provide a corresponding recommendation to the visitor, and the experience of the visitor in the environment may not be interrupted. Therefore, the present disclosure is directed to determining dynamic ride profiles for guests in an amusement park environment by using a multi-layer perceptron ML (machine learning) model trained with labeled data. The multi-layer perceptron model can be used to solve real-time classification problems involving a small number of input features with high accuracy.

[0023] According to the presented embodiments, a dynamic ride profile may be determined for an environment or a ride system of an amusement park. A dynamic ride profile may be determined based on the characteristics or attributes of a particular ride system (including ride vehicles and the environment). A dynamic ride profile may also be determined based on the condition of an individual visitor (e.g., physical condition, height, weight, age) and the expectations (e.g., relaxation, excitement, standard) of the experience for the amusement park or for a particular attraction (e.g., a particular ride). For the same visitor, the dynamic ride profile may be different for different environments or different ride systems of an amusement park. For different visitors, the dynamic ride profile may be different for the same environment or the same attraction of an amusement park. For example, different sizes, ages, or preferences of visitors may correspond to different profiles.

[0024] As an example of how the presented embodiments can operate, we shall discuss a scenario in which a visitor walks or rides (e.g., on a ride vehicle) in an environment within a system that uses a lookup table provided by a ride designer or determined based on historical data to monitor the visitor's ride profile. One or more sensors (e.g., motion sensors, orientation sensors, weight sensors, light sensors, sound sensors, image cameras, radio frequency identification (RFID) sensors) may be distributed in one or more locations of the environment to monitor the operation of the environment. In addition, one or more elements may be present in the environment, which may have one or more sensors installed to monitor the operation of the one or more elements. In addition, one or more sensors may be present to monitor the conditions associated with visitors in the environment. For example, the one or more sensors may be installed on a device (e.g., a handheld device, a wearable device, a tag) attached to a visitor or on a ride vehicle in which the visitor is sitting. A controller may be installed in the device or on a ride vehicle or in a control center to receive data from a sensor that monitors the conditions associated with a visitor, or the operation of the environment, or the operation of one or more elements in the environment. The controller may analyze the data to evaluate the operation of the condition associated with the visitor, the environment or one or more elements in the environment. The controller may use the data to determine whether the condition of the visitor meets the corresponding standard associated with the visitor's ride profile stored in the lookup table. When there is an obstacle in the environment (e.g., something detected on the ride track, a software error, input from a ride engineer) and the condition of the visitor does not meet the corresponding standard associated with the visitor's ride profile, the controller may sound an alarm. The alarm may include an action requesting the visitor to exit the environment or change to another route or an instruction for the control system of the environment to close or adjust the operation of one or more elements in the environment. However, as explained above, some actions in the action (e.g., exiting the environment) may not be necessary and may not be desired by the visitor.

[0025] In one embodiment, the controller may receive a trigger signal associated with an alarm, which trigger signal may cause the controller to begin re-evaluating the data using a prediction engine that implements a multi-layer perceptron model and can be trained using supervised machine learning to generate a dynamic ride profile. The prediction engine may provide recommendations associated with the alarm based on the generated dynamic ride profile, which may conflict with the action associated with the alarm. For example, the recommendation provided by the prediction engine may allow the visitor to remain in the environment or route (whereas the alarm includes an action requesting the visitor to exit the environment or change to another route) or allow the environment to continue operating (rather than shutting down one or more elements in the environment). For example, the alarm may be caused by an element in the environment or some unexpected change in the environment (e.g., not in the ride profile provided by the ride designer or in the historical data used to determine the ride profile), which may be identified as not meeting the operating standards within the visitor's ride profile. However, the unexpected change may not affect the visitor's overall experience in the environment, and requesting the visitor to exit the environment or change the route or controlling (e.g., shutting down) one or more elements in the environment may not be necessary, and may sometimes make the visitor's experience in the environment undesirable. Thus, by employing a predictive engine to evaluate unexpected changes using a predictive model, a guest may have a dynamically changed ride profile that may be larger or more relaxing than it would have been prior to implementation of the predictive model, and the guest may have a better experience at the amusement park.

[0026] In one embodiment, one or more additional effects may be used to create an additional experience associated with the recommendation. The controller may operate additional devices or sensors and / or receive additional signals (e.g., by means of communication, over a network) to coordinate with the recommendation to improve the visitor's experience and support the specific narrative of the environment. For example, a recommendation may be associated with a portion of a story or scene, and it may be controlled to operate in a mode with other attractions in the amusement park. In some embodiments, when a problem with a ride profile not meeting the desired criteria for a particular visitor is identified, an alternative experience may be provided in a seamless manner to provide a desirable experience for the visitor.

[0027] Figure 11 is a block diagram of a system 10 that includes a visitor 11 traveling on a ride vehicle 12 in an environment 14. There may be onboard sensors 16 (e.g., motion sensors, orientation sensors, weight sensors, light sensors, sound sensors, image sensors, cameras, RFID sensors) mounted or positioned on the ride vehicle 12 to collect vehicle data 18 from the ride vehicle 12, and the vehicle data 18 may include information associated with the visitor 11 (e.g., image data). The onboard sensors 16 may also collect data from the environment 14. There may be elements 20 positioned within the environment 14, and element sensors 22 (e.g., motion sensors, orientation sensors, weight sensors, light sensors, sound sensors, image cameras, RFID sensors) may be mounted or positioned on the elements 20 to collect element data 24 from the elements 20. There may be off-vehicle sensors 26 (e.g., motion sensors, orientation sensors, weight sensors, light sensors, sound sensors, image cameras, RFID sensors) mounted or positioned in the environment 14 to monitor and collect environmental data 28 from the environment 14. The off-vehicle sensors 26 may collect data associated with other operating parameters of the vehicle 12, the element 20, and / or the environment 14. An on-vehicle controller 30 may be mounted on the vehicle 12 to receive and analyze data from the on-vehicle sensors 16, the element sensors 22, and / or the off-vehicle sensors 26.

[0028] The onboard controller 30 may include various types of components that can assist the onboard controller 30 in performing various types of computer tasks and operations. For example, the onboard controller 30 may include a communication component 32, a processor 34, a memory 36, a storage device 38, an input / output (I / O) port 40, a display 42, a prediction engine 44 that implements a multilayer perceptron machine learning model, and the like. The prediction engine 44 may utilize one or more prediction models to evaluate the conditions of the visitors 11 in the environment 14 and determine the dynamically changing ride profile of the visitors 11. Various types of prediction models can be used to analyze data from sensors (e.g., onboard sensors 16, element sensors 22, off-board sensors 26) and generate prediction outputs. The prediction engine 44 is trained by supervised machine learning techniques, that is, the prediction model is trained by training data including input data and expected prediction outputs (e.g., labeled data sets). The amount of training data that may be required to train the prediction model can be large.

[0029] The communication component 32 may be a wireless or wired communication component that facilitates communication between the onboard controller 30 and various other controllers and devices via a network, the Internet, or the like. For example, the communication component 32 may allow the onboard controller 30 to obtain data from various data sources, such as the vehicle data 18. The communication component 32 may use a variety of communication protocols, such as, Open Database Connectivity (ODBC), TCP / IP protocol, Distributed Relational Database Architecture (DRDA) protocol, Database Change Protocol (DCP), HTTP protocol, other suitable current or future protocols, or combinations thereof.

[0030] The processor 34 may process instructions for execution within the onboard controller 30. The processor 34 may include (one or more) single-threaded processors, (one or more) multi-threaded processors, or both. The processor 34 may process instructions stored in the memory 36. The processor 34 may also include (one or more) hardware-based processors, each of which includes one or more cores. The processor 34 may include (one or more) general-purpose processors, (one or more) special-purpose processors, or both. The processor 34 may be communicatively coupled to other internal components (such as, communication component 32, storage device 38, I / O port 40 and display 42).

[0031] The memory 36 and storage device 38 may be any suitable article of manufacture that can act as a medium for storing processor executable code, data, or the like. These articles of manufacture may represent computer readable media (e.g., any suitable form of memory or storage device) that can store processor executable code used by the processor 34 to perform the currently disclosed techniques. As used herein, an application may include any suitable computer software or program that can be installed on the onboard controller 30 and executed by the processor 34. The memory 36 and storage device 38 may represent non-transitory computer readable media (e.g., any suitable form of memory or storage device) that can store processor executable code used by the processor 34 to perform the various techniques described herein. It should be noted that non-transitory simply indicates that the medium is tangible and is not a signal.

[0032] The I / O port 40 may be an interface that may be coupled to other peripheral components, such as input devices (e.g., keyboard, mouse), sensors, input / output (I / O) modules, and the like. The display 42 may operate as a human-machine interface (HMI) to depict visualizations associated with software or executable code being processed by the processor 34. In one embodiment, the display 42 may be a touch display capable of receiving input from an operator of the onboard controller 30. The display 42 may be any suitable type of display, such as, for example, a liquid crystal display (LCD), a plasma display, or an organic light emitting diode (OLED) display. Additionally, in one embodiment, the display 42 may be provided in conjunction with a touch-sensitive mechanism (e.g., a touch screen) that may serve as part of a control interface for the onboard controller 30.

[0033] It should be noted that the components described above with respect to the onboard controller 30 are examples, and that the onboard controller 30 may include additional or fewer components relative to the illustrated embodiment.

[0034] Further, the system 10 may include network features that facilitate data communication within the system 10 and with external devices. For example, data (e.g., image data, video data, sound data, position data, and weight data) collected by sensors (e.g., onboard sensors 16, component sensors 22, offboard sensors 26) may be transmitted to the onboard controller 30 via the network 46. Further, external data (e.g., data related to a particular user, local weather / news) may be collected from a remote system and transmitted to the onboard controller 30 via the network 46. However, in some embodiments, the data collected by the sensors may be transmitted directly from the sensors (e.g., onboard sensors 16, component sensors 22, offboard sensors 26) to the onboard controller 30. In fact, according to the presented embodiment, the onboard controller 30 may communicate with the sensors or other devices directly and / or via the network 46.

[0035] The off-board controller 48 may be located in a location other than the vehicle 12 (e.g., a control center of an amusement park), and may include various types of components that may assist the off-board controller 48 in performing various types of computer tasks and operations. The off-board controller 48 may include components similar to those included in the on-board controller 30. For example, the off-board controller 48 may include a communication component 50, a processor 52, a memory 53, a storage device 54, an input / output (I / O) port 55, a display 56, a prediction engine 58 similar to the prediction engine 44, and the like.

[0036] The off-board controller 48 can receive and analyze data from the on-board sensors 16, the component sensors 22, and / or the off-board sensors 26. The data (e.g., image data, video data, sound data, position data, and weight data) collected by the sensors (e.g., on-board sensors 16, component sensors 22, off-board sensors 26) can be transmitted to the off-board controller 48 via the network 46. Further, external data collected from a remote system (e.g., data related to a specific visitor, local weather / news) can be transmitted to the off-board controller 48 via the network 46. However, in some embodiments, the data collected by the sensors can be transmitted directly from the sensors (e.g., on-board sensors 16, component sensors 22, off-board sensors 26) to the off-board controller 48. In fact, according to the presented embodiment, the off-board controller 48 can communicate with the sensors or other devices directly and / or through the network 46. The off-board controller 48 can also communicate with a database 59, which can store information associated with attractions (e.g., environment 14) and / or specific customers in the amusement park. The database 59 can be used to store external data.

[0037] In one embodiment, the onboard controller 30 and / or the offboard controller 48 may analyze data collected by sensors (e.g., onboard sensors 16, element sensors 22, offboard sensors 26) and / or external data (e.g., data related to the guest 11 on the vehicle 12, local weather / news) to evaluate conditions associated with the vehicle 12, the operation of the environment 14, or the operation of elements in the environment 14. The onboard controller 30 and / or the offboard controller 48 may determine measured conditions for the guest 11 with the vehicle 12 (or in some embodiments, without the vehicle 12) and compare the measured conditions to a lookup table 60 maintained in the onboard controller 30 and / or the offboard controller 48, which defines a corresponding ride profile for the guest 11 having an acceptable range of operating conditions (e.g., taking into account customer physical characteristics, preferences, and the like). When there is an obstruction in the environment 14 (e.g., something detected on the ride track or attraction route, a software error, input from a ride engineer) and the measured conditions for the guest 11 do not meet the corresponding criteria associated with the ride profile of the guest 11, the onboard controller 30 and / or the offboard controller 48 may issue an alert. For example, the onboard controller 30 and / or the offboard controller 48 may receive an alert for a ride vehicle that is traveling too slowly for the preferences of a particular guest. The alert may include instructions for the guest 11 (e.g., change route, buckle up, remain seated, or exit the environment 14), control certain features (e.g., shut down one or more elements (e.g., element 20) in the environment 14, speed up the ride vehicle 12), instructions for the operator (e.g., adjust rider parameters, communicate with customers), or the like.

[0038] exist Figure 2 61 illustrates an object 62 moving in a space having a coordinate axis system XYZ. The object 62 is within a ride profile 63 having an acceptable operating condition / orientation between a first boundary surface 64 and a second boundary surface 66. These are not physical surfaces, but rather represent the edges or boundaries of a volume within which the object 62 is allowed or expected to travel. When the object 62 moves between the first boundary surface 64 and the second boundary surface 66 (i.e., its expected operating range), the object 62 is inside its ride profile 63 (e.g., the golden profile (GP)). When the object 62 moves outside of the first boundary surface 64 or the second boundary surface 66, the object 62 is outside of its ride profile 63, as shown in FIG. Figure 3 As previously noted, the ride profile 63 may vary based on conditions. As an example, for a tall occupant, the first boundary surface 64 and the second boundary surface 66 may be closer together than for a short occupant because the occupant's physical characteristics may be taken into account.

[0039] Figure 2 70 in FIG. 70 illustrates the relative orientation of the first boundary surface 64, the object 62, and the second boundary surface 66. Curve 72 in FIG. 70 illustrates the orientation of the first boundary surface 64 on the XZ plane, curve 74 illustrates the orientation of the object 62 on the XZ plane, and curve 76 illustrates the orientation of the second boundary surface 66 on the XZ plane. In an embodiment, the boundary surfaces 64, 66 may change as the object 62 is positioned, as illustrated by curves 72 and 76 in FIG. 70. The ride profile 63 of the object 62 limits the orientation of the object 62 to be between the first boundary surface 64 and the second boundary surface 66, and therefore, curve 74 is between curves 72 and 76, thereby indicating that the object 62 is located within the limits. The ride profile 63 of the object 62 may be determined by implementing a lookup table, or utilizing a machine learning algorithm trained by historical data, or other recognition techniques that use data sets collected by sensors that are used to detect the condition of the object 62 and its environment to evaluate the condition associated with the object 62. When the object 62 moves out of its ride profile 63, instructions may be provided by consulting a lookup table or based on the results of a machine learning algorithm. For example, the lookup table may include a mapping between the position of the object 62 and the corresponding notification of the position. The notification of the position of the object 62 may indicate whether the object 62 is inside its ride profile 63 or outside its ride profile 63, and may also include corresponding instructions for the object 62 to avoid being outside its ride profile 63. For example, when the object 62 is outside its ride profile 63, the instructions may include a request or alert for the object 62 to be moved back to its ride profile 63. Although only two boundary surfaces (e.g., surfaces 64, 66) are in Figure 2, it should be noted that object 62 may have more than two boundary surfaces that define the boundaries of its ride profile 63. It should also be noted that the boundary surfaces may be different for different guests / vehicles due to adaptation of the individual guest's personal conditions (e.g., physical characteristics) and desired experience type, vehicle characteristics and attributes of vehicle 12, and / or the like.

[0040] Figure 3 An embodiment is illustrated in which an object 62 has moved outside its ride profile 63 (or ride envelope). Specifically, FIG. 80 shows that the object 62 has moved beyond the first boundary surface 64. According to the presented embodiment, such movement beyond the ride profile 63 causes corresponding instructions to be generated (e.g., via the onboard controller 30 or the offboard controller 48). The instructions may cause the object 62 to be repositioned within the first boundary surface 64, cause the presentation of a request to a user or operator for repositioning the object 62, provide an alert indicating that the object 62 is outside the ride profile 63, or the like. The ride profile 63 of the object 62 is an indicator and guide for keeping the object 62 within the desired range of motion when moving or repositioning the object 62 to avoid problems (e.g., potential collisions) that may cause downtime or other undesirable events. In other words, the ride profile 63 of the object 62 can be used to keep the object 62 inside a certain space or to avoid undesirable events caused by walls and / or scenery props intruding into the ride envelope of the object 62 for a given environment in an amusement park. Again, it should be noted that the boundary surface can move with the object 62, such as Figure 2 As illustrated in Figure 70.

[0041] However, unexpected changes may occur to the object 62 and / or the surrounding environment (e.g., environment 14), such as an obstacle (e.g., something detected in or near the path of the object 62, a software error, an input associated with the object 62). The lookup table may not have a corresponding entry for the unexpected change (e.g., because the unexpected change has not been accounted for in the lookup table). Therefore, for the object 62, it is desirable to have a ride profile that changes dynamically in the time domain.

[0042] According to the presented embodiments, a prediction engine implementing a multi-layer perceptron machine learning model may be employed (using supervised machine learning), either alone or in addition to the lookup table, to quickly make one or more determinations based on unexpected changes. The prediction engine may utilize one or more prediction models to determine a dynamically changing ride profile of object 62, and determine a classification from a plurality of classifications for the environment based on the dynamically changing ride profile of object 62. For example, the plurality of classifications may include some classifications indicating that unexpected changes may place object 62 outside of a threshold orientation range, and some classifications indicating that unexpected changes may not place object 62 outside of a threshold orientation range. The prediction engine may provide recommendations based on the classifications.

[0043] Figure 3 FIG. 82 in FIG. 82 illustrates predictive modeling as performed by one or more controllers (e.g., onboard controller 30) of system 10 according to the presented embodiment. Predictive modeling generally refers to computer-based techniques, algorithms, systems, and the like for extracting information from data to build a model that is capable of predicting an output from a given input. For example, given certain measurements (e.g., from sensors), predictive modeling is capable of predicting future results that can be predicted to occur within a short period of time when the measurements are obtained. In FIG. 82 , block diagram 84 illustrates the use of a single input 85 via logic 86 to obtain a single output 87. Also in FIG. 82 , block diagram 88 illustrates the use of two inputs 85 (which can be related via logic 86) to obtain two outputs 87, each of which may be affected by both of the two inputs 85. Various types of predictive models can be used to analyze data and generate predicted outputs. For supervised machine learning techniques, predictive models are trained by training data, which includes input data and expected predicted outputs (e.g., labeled data sets). The amount of training data that may be required to train a predictive model can be very large.

[0044] Now refer to it again Figure 1 , the vehicle 12 moves in the environment 14, similar to Figure 2The object 62 in the lookup table 60 moves along the XYZ coordinates. Unexpected changes (i.e., not included in the lookup table 60) may occur to the visitor 11, the vehicle 12, the environment 14 (e.g., element 20). Examples of unexpected changes may include mechanical wear (e.g., mechanical wear on the vehicle 12, element 20, other elements in the environment 14), uncontrollable factors (e.g., weather, policy or economic situation, earthquake, hurricane), unexpected operation of the vehicle 12, and / or any combination of the above. The detection of such unexpected changes may cause the system 10 to generate instructions, alarms, and / or initiate actions. For example, in response to the detection of an unexpected event, the on-board controller 30 or the off-board controller 48 or other controllers associated with the system 10 may be operated to shut down one or more elements in the environment 14 (e.g., element 20). As another example, the vehicle 12 may receive an alarm indicating an unexpected change to the system 10 (e.g., an obstacle on the ride path). Such an alarm may include a request that the visitor 11 on the vehicle 12 change to a different route or exit the environment 14.

[0045] Data and / or instructions related to unexpected events may be generated by any of the various aspects of the system 10. For example, the vehicle 12 may receive an alert or instruction from the onboard controller 30, a feature of the environment 14, or an off-board controller 48, either directly or via the network 46. The alert may be provided using various methods via light, sound, vibration, image, and the like. For example, speakers, lighting, haptics, and the like on the vehicle 12, in the environment 14, or on a device (e.g., a wearable device, a tag) carried by the visitor 11 may be used by the system 10 to provide alerts, instructions, or other communications.

[0046] The detection of an unexpected event may trigger the onboard controller 30 and / or the offboard controller 48 to employ one or more prediction engines to analyze unexpected changes through data collected by sensors (e.g., onboard sensors 16, element sensors 22, offboard sensors 26) and / or external data (e.g., data related to the visitor 11 on the vehicle 12, local weather / news) to evaluate the condition associated with the vehicle 12, the operation of the environment 14, or the operation of the elements in the environment 14. The prediction engine may use one or more prediction models as described above to evaluate the unexpected changes and determine a dynamically changing ride profile for the visitor 11, which may be greater or more relaxed than the profile before the implementation of the prediction model. The prediction engine may determine a classification for the environment 14 regarding the unexpected change from a plurality of classifications based on the dynamically changing ride profile of the visitor 11. For example, the plurality of classifications may include some classifications with conclusive states indicating that the unexpected change may affect the experience of the visitor 11 in the environment 14, and specific actions may need to be completed to avoid the undesirable experience of the visitor 11 caused by the unexpected change in the environment. The multiple classifications may also include some classifications with optional states indicating that unexpected changes may not affect the experience of the visitor 11 in the environment 14, and any action associated with the visitor 11 regarding the unexpected changes may be unnecessary or optional. The prediction engine may provide recommendations to the system 10 based on the classifications. For example, some unexpected changes may not be predicted to affect the overall experience of the visitor in the environment 14 (e.g., classifications with optional states). When such predictions are dominant (e.g., selected or determined to be possible results), instructions or requests that may damage the experience of the visitor (e.g., requiring the visitor 11 to exit the environment 14 or change the route, or shut down one or more elements in the environment 14) may be avoided. For example, in one embodiment, an alarm may be transmitted for the visitor 11, and the alarm may request the visitor 11 to exit the environment 14 (due to obstacles occurring in the environment 14), however, the prediction engine may determine that it is unnecessary for the visitor 11 to exit the environment 14, and provide corresponding recommendations for the visitor 11 (e.g., providing the visitor 11 with the option of staying in the environment 14). On the other hand, some unexpected changes may be predicted to affect the visitor's overall experience in the environment 14 (e.g., classification with a conclusive state). When such predictions are dominant (e.g., selected or determined as a possible outcome), certain instructions or requests that may harm the visitor's experience (e.g., requiring the visitor 11 to exit the environment 14 or change the route, or shut down one or more elements in the environment 14) may be necessary, and the prediction engine may provide corresponding recommendations to the visitor 11. For example, in the example described above, the prediction engine may provide a recommendation to confirm the request in the alert requiring the visitor 11 to exit the environment 14.

[0047] Thus, the recommendation may include instructions to allow actions that are not allowed or prohibited in the alert, because the dynamically changing ride profile of the visitor 11 may be greater or more relaxed than the profile before the implementation of the predictive model. In some embodiments, the recommendation may be sent to the visitor 11 on the vehicle 12, and the visitor 11 may select the recommended action in the recommendation, which may not be allowed in the alert (e.g., continue the route instead of changing the route, or stay in the environment 14 instead of exiting). In some embodiments, one or more actions in the recommendation may be automatically implemented by the system 10 (e.g., the alert may request the system 10 to turn off one or more elements in the environment 14, but the recommendation may include an action requesting the system 10 not to turn off the one or more elements in the environment 14). By using the predictive engine to evaluate unexpected changes using the predictive model, the visitor 11 may have a dynamically changing ride profile that may be greater or more relaxed than the profile before the implementation of the predictive model. And the visitor 11 may have a better experience in the amusement park.

[0048] Figure 4 and Figure 5 An example of using a prediction engine in environment 14 is shown. Figure 4 is a block diagram of one embodiment of an environment 14 having one or more attractions separated into different rooms. For example, Figure 4 The six rooms in environment 14 are shown. Specifically, Figure 4 The environment 14 in the vehicle includes a first room 14a, a second room 14b, a third room 14c, a fourth room 14d, a fifth room 14e, and a sixth room 14f. These six rooms may be collectively referred to as rooms 14a-f. Further, in the illustrated embodiment, the environment 14 includes an exit 15, which may be a parking location for the vehicle 12. The rooms 14a-f in the environment 14 may be connected, and the vehicle 12 may travel from one room to another. The off-board controller 48 may collect data from sensors distributed in the rooms 14a-f. Each room may be connected to one or more other rooms in the environment 14. In one embodiment, at least one room in the environment 14 may be connected to other locations outside the environment 14.

[0049] Figure 51 is a perspective view of a guest 11 riding a vehicle 12 through a room 14a that is being monitored and analyzed by a predictive model (according to the embodiment presented). In the illustrated embodiment, the element 20 includes a robotic arm that is operable to move around in the environment 14 for entertainment purposes. When an object 92 (e.g., an unexpected bird) flies into the environment 14 and lands on the element 20, unexpected changes to the element 20 may occur. The on-board sensor 16, the element sensor 22, and / or the off-board sensor 26 can detect the object 92 and send relevant information to the on-board controller 30 and / or the off-board controller 48.

[0050] Visitor 11 may have a ride profile associated with room 14a, and the unexpected change may be identified as interfering with the visitor's ride profile based on a lookup table associated with room 14a. In response to identifying this interference, an alarm or instruction may be issued by the onboard controller 30 and / or the offboard controller 48 and sent to room 14a (e.g., room 14a may have a speaker 94), vehicle 12, and / or visitor 11, requesting visitor 11 to exit room 14a. The alarm may trigger the onboard controller 30 and / or the offboard controller 48 to analyze the unexpected change using data collected by sensors (e.g., onboard sensors 16, element sensors 22, offboard sensors 26) and / or external data (e.g., data related to visitor 11 on vehicle 12, local weather / news) to evaluate the condition associated with vehicle 12, the operation of room 14a, or the operation of element 20 in room 14a. The prediction engine 44 and / or 58 may use one or more prediction models as described above and determine a dynamically changing ride profile for the visitor 11 in the room 14a. The prediction engine 44 and / or 58 may determine a classification from a plurality of classifications of the conditions of the visitor 11 based on the dynamically changing ride profile of the visitor 11 in the room 14a. For example, the plurality of classifications may include some classifications indicating that unexpected changes may affect the experience of the visitor 11 in the room 14a, and some classifications indicating that unexpected changes may not or may not substantially affect the experience of the visitor 11. The plurality of classifications may also include some classifications indicating that unexpected changes may affect the experience of the visitor 11 in the room 14a but may not affect the experience of the visitor 11 in other rooms (e.g., room 14b, room 14c, room 14d, room 14f) of the environment 14. The prediction engine may provide recommendations to the system 10 based on the classifications. For example, some unexpected changes may not be predicted to affect or substantially affect the overall experience of the visitor in the room 14a. When such predictions are dominant (eg, selected or determined as a likely outcome), providing instructions or requests that may detract from the visitor's experience (eg, requiring visitor 11 to exit room 14a) may be avoided.

[0051] In one embodiment, due to the less data transmission time required by the on-board controller 30, the on-board controller 30 can provide recommendations faster than the off-board controller 48. Therefore, when timing is sensitive and real-time data analysis may be beneficial, the on-board controller 30 can be used to provide recommendations. For example, when the article 92 is not identified as causing an undesirable experience for the visitor 11, the on-board controller 30 may take less time than the off-board controller 48 to provide a recommendation that the visitor 11 does not exit the room 14a, regardless of the alarm requesting the visitor 11 to exit the room 14a. Therefore, the experience of the visitor 11 in the room 14a may not be interrupted or not interrupted for a longer time in the above example. On the other hand, since the off-board controller 48 has access to more data, the off-board controller 48 can provide more selected recommendations or more accurate recommendations. For example, the off-board controller 48 can receive data from all rooms in the environment 14 (i.e., rooms 14a, 14b, 14c, 14d, 14e and 14f), and can analyze the overall situation of the environment 14 to obtain more prediction results and more accurate prediction results. Thus, the off-board controller 48 may be used to provide a greater selection of recommendations or more accurate recommendations. For example, the off-board controller 48 may provide a recommendation suggesting that the visitor 11 move to another room (e.g., room 14b, 14c, 14d, 14e, or 14f) rather than exiting the environment 14 (e.g., back to exit 15) because the off-board controller 48 may be able to collect data from all rooms in the environment 14.

[0052] Although only certain features of the present invention have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. It is therefore to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.

[0053] The technology presented and claimed herein is cited and applied to specific examples and substantial objects that arguably improve the practical nature of the art, and is therefore not abstract, intangible, or purely theoretical. Further, if any claim appended to the end of this specification contains one or more elements designated as "a component for [performing] ... [function]" or "a step for [performing] ... [function]," it is intended that such elements be interpreted in accordance with 35 U.S.C. 112(f). However, for any claim containing elements designated in any other manner, it is intended that such elements not be interpreted in accordance with 35 U.S.C. 112(f).

Claims

1. A controller for a ride system, the controller comprising: processor; as well as a memory storing instructions that, when executed by the processor, cause the controller to perform operations comprising: responsive to an alert indicating an obstruction to the ride system, accessing a data set indicative of conditions in an environment of the ride system; determining, via a prediction engine trained using supervised machine learning, a classification from a plurality of classifications for the environment based on the data set and the ride profile or envelope; determining, via the prediction engine, one or more recommendations based on the data set and the classification; and The classification is presented visually or audibly with the one or more recommendations.

2. The controller according to claim 1, wherein: The predictive engine is trained using the supervised machine learning based on a plurality of labeled data, wherein the plurality of labeled data is associated with the environment.

3. The controller according to claim 1, wherein: The plurality of categories include optional states and conclusive states.

4. The controller according to claim 1, wherein: At least one of the one or more recommendations is inhibited based on the alert indicating the obstacle, and wherein the obstacle is an environmental obstacle to the ride system.

5. The controller according to claim 1, wherein: The processor is located on a vehicle of the ride system.

6. The controller according to claim 1, wherein: The processor is configured to access the data set via a set of sensors.

7. The controller according to claim 6, wherein: The collection of sensors is positioned in the environment.

8. A method of controlling a ride system, the method comprising: responsive to an indication of an obstruction to the ride system, accessing, via a processor, a data set indicative of a condition in an environment; determining, via a prediction engine trained using supervised machine learning, a classification from a plurality of classifications for the environment based on the dataset and a ride envelope for the ride system; determining, via the prediction engine, one or more recommendations based on the data set and the classification; as well as The classification is presented audibly or visually with the one or more recommendations.

9. The method of claim 8, wherein: The predictive engine is trained using the supervised machine learning based on a plurality of labeled data, wherein the plurality of labeled data is associated with the environment.

10. The method of claim 8, wherein: The plurality of categories include optional states and conclusive states.

11. The method of claim 8, wherein: At least one of the one or more recommendations is inhibited based on the indication that the obstacle to the ride system is an environmental obstacle.

12. The method of claim 8, wherein: The processor is located on a vehicle of the ride system.

13. The method of claim 8, wherein: The processor is configured to access the data set via a set of sensors.

14. The method of claim 13, wherein: The collection of sensors is positioned in the environment.

15. A riding system comprising: a ride vehicle configured to travel in an environment, wherein the ride vehicle includes an onboard sensor configured to collect vehicle data from the ride vehicle; a dynamic element, the dynamic element being disposed within the environment; an off-board sensor disposed on an exterior of the ride vehicle and configured to collect dynamic element data indicative of at least one aspect of the dynamic element; and A controller comprising one or more processors and a memory storing instructions that, when executed by the one or more processors, cause the controller to perform operations comprising: responsive to an indication of an obstruction to the ride system, accessing a data set from the onboard sensor and the offboard sensor, the data set including the vehicle data and the dynamic element data; determining, based on the data set, via a prediction engine trained using supervised machine learning and a ride envelope of the ride system, a classification from a plurality of classifications for the environment; determining, via the prediction engine, one or more recommendations based on the data set and the classification; and The classification is presented by the one or more recommendations.

16. The controller of claim 15, wherein: The onboard sensors are configured to collect environmental data from the environment of the ride system, and the data set includes the environmental data.

17. The controller of claim 15, wherein: The dynamic elements include path control equipment, automated personnel, maintenance equipment or a combination thereof.

18. The controller of claim 15, wherein: At least one of the one or more recommendations is inhibited based on the indication of the impairment to the ride system.

19. The controller of claim 15, wherein: The off-vehicle sensor is integrated with the dynamic element.

20. The controller of claim 19, wherein: The dynamic element includes an automated character configured to interact with the ride vehicle during operation of the ride system.

Images