Systems and methods for controlling the operation of a vehicle system based on gestures - Patents.com

Abstract

A ride control system for controlling operation of rides at an amusement park having a ride station area where patrons board and disembark ride vehicles under the supervision of one or more ride operators includes a vision system and a ride control processor. The vision system captures images of one or more of the one or more ride operators at one or more locations within the ride station area. The ride control processor includes a machine learning module configured to receive one or more images from the vision system and recognize one or more valid gestures in the one or more images, where the valid gestures correspond to gestures from at least one of the one or more ride operators, and program logic configured to process the one or more valid gestures in the one or more images to enable ride operation.

Description

[Technical Field]

[0001] The technology described below relates generally to amusement park ride systems, and more particularly to systems and methods for controlling the operation of ride systems based on gestures. [Background technology]

[0002] Operator control consoles are the primary operating points of amusement park ride systems. These consoles include console interfaces (e.g., buttons, switches, sliders, dials) that control the operation of the ride. For example, the consoles include console interfaces that allow for system shutdown and system startup or launch. Consoles are often duplicated or located in ride station areas where operators are constantly stationed to activate the console interfaces that control the ride. This creates overstaffing and inefficiencies by requiring additional employees to perform other operational tasks, such as ensuring passengers are properly seated and restrained in the ride vehicles, while the operators are at the consoles. Furthermore, there is always a debate about having enough consoles or the need to supplement operators with wireless handpacks with shutdown capabilities. This creates numerous additional costs and reliability issues. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] U.S. Patent Application Publication No. 2021 / 0342616 Summary of the Invention

[0004] Aspects of the present disclosure relate to a ride control system for controlling operation of an amusement park ride having a ride station area where patrons board and disembark ride vehicles under the supervision of one or more ride operators. The ride control system includes a vision system and a ride control processor coupled to receive one or more images from the vision system. The vision system is configured to capture one or more images of at least one of the one or more ride operators at one or more locations within the boarding station area. The ride control processor includes a machine learning module configured to recognize one or more valid gestures in the one or more images, where the valid gestures correspond to gestures from at least one of the one or more ride operators. The ride control processor also includes program logic configured to process the one or more valid gestures in the one or more images to enable ride operation.

[0005] Aspects of the present disclosure also relate to a method for controlling operation of an amusement park ride having a ride station area where patrons board and disembark ride vehicles under the supervision of one or more ride operators, the method including capturing one or more images of at least one of the one or more ride operators at one or more locations within the ride station area, recognizing one or more valid gestures in the one or more images, where the valid gestures correspond to gestures from at least one of the one or more ride operators, and processing the one or more valid gestures in the one or more images to enable ride operation.

[0006] The present disclosure also relates to a ride control processor including a machine learning module and program logic. The machine learning module is configured to recognize one or more valid gestures in one or more images. The valid gestures correspond to gestures from at least one of one or more ride operators in a ride station area. The machine learning module includes a first model trained to identify gestures in the images that correspond to gestures in a set of programmed gestures, and a second model trained to determine that the gestures were made by at least one of the one or more ride operators. The program logic is configured to process the one or more valid gestures in the one or more images to enable ride operation.

[0007] It is understood that other aspects of the apparatus and method will become readily apparent to those skilled in the art from the following detailed description, in which various aspects of the apparatus and method are shown and described by way of illustration. As will be understood, these aspects may be embodied in other and different forms, and their several details may be modified in various other respects. Accordingly, the drawings and detailed description are to be regarded as illustrative in nature and not as restrictive.

[0008] Various aspects of the apparatus and methods will now be illustrated in a detailed description, by way of example and not limitation, with reference to the accompanying drawings, in which: [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic diagram of a conventional ride station area of ​​an amusement park ride.

[0010] [Figure 2] FIG. 1 is a schematic diagram of a ride station area of ​​an amusement park ride having a ride control system configured to control ride operation based on valid gestures from a ride operator.

[0011] [Figure 3] FIG. 3 is a block diagram of the vehicle control system of FIG. 2 including a machine learning module configured to recognize gestures and vehicle operators and program logic configured to process valid gestures to control vehicle operation.

[0012] [Figure 4A] FIG. 1 is a schematic diagram of gestures that can be recognized by a machine learning module. [Figure 4B] FIG. 1 is a schematic diagram of gestures that can be recognized by a machine learning module. [Figure 4C] FIG. 1 is a schematic diagram of gestures that can be recognized by a machine learning module. [Figure 4D] FIG. 1 is a schematic diagram of gestures that can be recognized by a machine learning module. [Figure 4E] FIG. 1 is a schematic diagram of gestures that can be recognized by a machine learning module.

[0013] [Figure 5] 4 is a diagram of the logic flow executed by the ride control system of FIG. 3 to initiate outgoing ride actions based on valid gestures from multiple ride operators.

[0014] [Figure 6] FIG. 4 is a diagram of the logic flow executed by the vehicle control system of FIG. 3 to initiate an emergency stop based on a valid gesture from a single vehicle operator.

[0015] [Figure 7] 4 is a flowchart of a method for controlling amusement park operation implemented in the ride control system of FIG. 3. DETAILED DESCRIPTION OF THE INVENTION

[0016] The detailed description set forth below in connection with the accompanying drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. Although aspects and embodiments are described herein by way of example with respect to several examples, those skilled in the art will appreciate that additional implementations and use cases may arise in many different configurations and scenarios. The inventions described herein may be implemented in many different platform types, devices, and systems.

[0017] FIG. 1 is a schematic diagram of a conventional ride station area 100 of an amusement park ride. The ride station area 100 is an area where passengers board and disembark a ride vehicle 102 before the ride vehicle 102 is launched into the ride area. In the configuration shown in FIG. 1, passenger 104a enters (or boards) the ride vehicle 102 at the same location as passenger 104b exits (or disembarks) the ride vehicle. In other ride station configurations (not shown), passengers exit the ride vehicle in one area, and the ride vehicle is advanced to another area where passengers enter the ride vehicle. In some ride station configurations, the ride vehicle 102 comes to a complete stop before loading and unloading passengers. In other configurations, the ride vehicle moves continuously through the ride station area at a speed slow enough to allow passengers to board and unload.

[0018] In either configuration, operator control consoles 106a, 106b within the ride station area 100 are used by ride operators 108a, 108b, 108c to perform various ride functions. The operator control consoles 106a, 106b are typically fixed in place, with at least one ride operator 108a, 108b at each operator control console 106a, 106b. Most operations involving initiating movement of a ride vehicle 102 from the ride station area 100 to a ride area require a minimum of two ride operators 108a, 108b to press and hold the dispatch console interface 114 on their respective operator control consoles 106a, 106b. Thus, the ride operators within the ride station area are within line of sight of one another, and each ride operator at an operator control console provides a visual signal to the other operator and, upon observing the same visual signal from the other operator, the ride operation is initiated.

[0019] FIG. 2 is a schematic diagram of a ride station area 200 of an amusement park ride having a ride control system 300 according to embodiments disclosed herein. FIG. 3 is a block diagram of the ride control system 300 according to embodiments disclosed herein. In the configuration shown in FIG. 2, patron 204a enters (or boards) ride vehicle 202 at the same location as patron 204b exits (or disembarks) the ride vehicle. A single operator control console 206 in ride station area 200 is operated by a single ride operator 108a to perform various ride functions. Thus, in this ride station area 200, there is a single operator control console 206, requiring only a single console interface 214 press by one operator 108a, instead of multiple console interface presses as in the conventional ride station area of ​​FIG. 1. In some embodiments, the single operator control console 206 is fixed in place. In some embodiments, the single operator control console 206 is a wireless handheld roaming console that allows the operator 108 a to move around within the ride station area 200 .

[0020] 2 and 3, ride control system 300 includes a vision system 302 and a ride control processor 304. Vision system 302 is configured to capture video images of ride operators 208a, 208b, 208c at different locations within ride station area 200 and provide the video images to ride control processor 304 in real time. Ride system 302 includes as many cameras as necessary to capture a panoramic view of ride station area 200. In ride control system 300 of FIGS. 2 and 3, vision system 302 includes four video cameras 210a, 210b, 210c, 210d. Ride control processor 304 may be coupled to or integrated into operator control console 206, as shown in FIG. 2, or may be a separate component from operator control console 206 and in wired or wireless communication with operator control console 206.

[0021] Ride control processor 304 is coupled to vision system 302 to receive images captured by vision system 302. Ride control processor 304 is also coupled to operator control console 206 to receive ride operation signals resulting from manual activation (e.g., mechanical activation, electrical activation, electromechanical activation, hydraulic activation, pneumatic activation) by a ride operator. Ride control processor 304 includes a machine learning module 308 and program logic 310. Machine learning module 308 is configured to recognize one or more valid gestures in one or more images captured by vision system 302. As used herein, a valid gesture corresponds to a gesture made by at least one of one or more ride operators, as opposed to a gesture made by someone other than the ride operator, such as passengers 204a, 204b.

[0022] The program logic 310 is configured to process one or more valid gestures in the images to automatically enable or disable vehicle operation. In some configurations, the program logic 310 is configured to process one or more valid gestures in one or more images, along with activation of the console interface 214 originating from the operator control console 206, to enable or disable vehicle operation.

[0023] The machine learning module 308 comprises custom gesture-based recognition software. In one configuration, the machine learning module 308 comprises one or more convolutional neural network (CNN) models. A first CNN model is trained to recognize a set of ride control gestures that a ride operator can perform using their hands or arms. For example, with reference to FIGS. 4A-4E, the first CNN model can be trained to recognize a set of ride control gestures including a single-hand thumbs-up 402 (FIG. 4A), hands crossed above the head making an X 404 (FIG. 4B), arms in an L 406 shape (see FIG. 4C), a single hand placed above the head 408 (FIG. 4D), and one or more hands with thumbs down 410 (FIG. 4E).

[0024] The second CNN model is trained to recognize features associated with the vehicle operator. For example, referring to FIG. 2 , the second CNN model can be trained to recognize features 212 (e.g., emblems (e.g., retroreflective emblems), patterns, patches, or symbols (e.g., barcodes, quick response (QR) codes)) as part of a uniform that the vehicle operator may be wearing. For example, the retroreflective emblems can be placed in one or more locations on the operator's uniform such that the retroreflective emblems can always be detected by the vision system 302. The emblems must either 1) be a recognizable shape, such as a circle, square, triangle, etc., or 2) have a minimum detectable surface area (e.g., 100 cm) of retroreflective surface to be detected. 2) can be recognized by either a facial recognition system or a machine learning module 308 that recognizes valid gestures, i.e., vehicle control gestures performed by a vehicle operator. Additional logic can be incorporated, such as only considering retro-reflective emblems on shirts of certain colors, e.g., red, blue, orange, etc. A second CNN model can be trained to recognize vehicle operators based on facial recognition. In either case, the second CNN model prevents the vehicle control processor 304 from processing gestures made by people within the ride station area 200 who are not ride operators. The first and second CNN models combine to provide the machine learning module 308 that recognizes valid gestures, i.e., vehicle control gestures performed by a vehicle operator.

[0025] In another configuration, the vision system 302 may include an optical recognition camera configured to recognize the vehicle operator based on a light pattern produced by an identifier worn by the vehicle operator. One example of a technology enabling such recognition is disclosed in U.S. Patent Application Publication No. 2021 / 0342616, which is incorporated herein by reference. In this configuration, instead of having a second CNN model, the vehicle control processor 304 includes a filter function that extracts images of gestures associated with the recognized vehicle operator from the real-time video image feed of the vision system 302 and provides the extracted images to the first CNN model of the machine learning module 308.

[0026] In either configuration, the machine learning module 308 provides a signal indicative of each valid gesture to the program logic 310. The program logic 310 processes the valid gestures and provides a control signal that initiates a specific vehicle action if certain logic conditions are met. Examples of two different logic flows of the program logic 310 for two different gestures and vehicle operators are provided below.

[0027] FIG. 5 is a flow diagram of an exemplary operation of the machine learning module 308 and program logic 310 to initiate vehicle dispatch.

[0028] In block 502, the machine learning module 308 recognizes one or more valid gestures and provides a signal indicative of each valid gesture to the program logic 310. In this example, a valid gesture 402 in the form of a thumbs-up is recognized from three ride operators.

[0029] In block 504, the AND operator of the program logic 310 determines when a predetermined number of valid gestures corresponding to a send operation have been recognized by the machine learning module 308. In the example of FIG. 5, the predetermined number of valid gestures is three. Thus, in block 504, if at least three valid send gestures are input to the AND operator, the AND operator outputs a logic state indicative of that condition, in which case the logic flow continues. In block 504, if fewer than three valid send gestures are input to the AND operator, the AND operator outputs a logic state indicative of that condition, in which case the logic flow ends and the vehicle is not sent.

[0030] For certain vehicle actions, including vehicle dispatch, program logic 310 includes duration criteria. For example, when a particular gesture is first recognized by machine learning module 308, the gesture may be required by program logic 310 to be continuously maintained or held for a number of seconds by the vehicle operator. To this end, at block 506, program logic 310 starts a delay timer if the AND operation at block 504 of program logic 310 determines that a predetermined number of valid dispatch gestures have been recognized by machine learning module 308.

[0031] In block 508, a logic state corresponding to the state of the timer in block 506 is provided to an AND operator. The logic state of the timer indicates either that the timer is running or that the timer has expired. The logic state of the AND operator in block 504 is also provided to the AND operator in block 508. The logic state of the sending console interface 214 on the operator control console 206 is also provided to the AND operator in block 508. This logic state indicates whether the sending console interface 214 on the operator control console 206 is in a released state or a pressed state. If the logic state input to the AND operator in block 508 indicates that the sending console interface 214 on the operator control console 206 is activated, the timer has expired, and all operators are still holding their sending gestures, the logic flows to block 510.

[0032] At block 510, program logic 310 outputs a control signal to ride control system 300 to dispatch the ride vehicle, thereby completing the dispatch logic operation of ride control system 300. At this point, the ride operator can release the dispatch gesture without affecting the operation of the ride.

[0033] Returning to the AND operator at block 508, if the logic state input to the AND operator indicates either: 1) the dispatch console interface 214 has not been activated in the operator control console 206, 2) the timer is still running, or 3) all of the predetermined number of ride operators have not yet retained their respective valid dispatch gestures, the logic flow ends and the ride is not dispatched.

[0034] The delay timer in block 506 is a safety feature that prevents any send activation that may be initiated at the operator control console 206 before the timer expires from affecting the operation of the ride. The delay timer also ensures that nothing is happening in the ride station area that would cause the ride operator to release the send gesture. In one embodiment, the send delay time is two seconds.

[0035] FIG. 6 is a flow diagram of an example operation of the machine learning module 308 and program logic 310 to initiate an emergency stop of a ride vehicle.

[0036] In block 602, the machine learning module 308 recognizes at least a single valid gesture and provides a signal indicative of the valid gesture to the program logic 310. In this example, a valid emergency stop gesture in the form of crossing forearms above the head to form an X404 is recognized from one of the three ride operators.

[0037] In block 604, an OR operator in the program logic 310 determines when at least one valid emergency stop gesture is recognized by the machine learning module 308. If no valid emergency stop gesture is input to the OR operator, the logic flow ends and the ride vehicle is not stopped.

[0038] For emergency stops, program logic 310 includes a duration criteria. For example, once a valid emergency stop gesture is first recognized by machine learning module 308, the valid emergency stop gesture may be required by program logic 310 to be continuously maintained or held for a number of seconds by the vehicle operator. To this end, in block 606, program logic 310 starts a delay timer when the OR operation of program logic 310 determines that at least one valid emergency stop gesture has been recognized by machine learning module 308.

[0039] In block 608, a logic state corresponding to the state of the timer in block 606 is provided to an AND operator. The logic state of the timer indicates either that the timer is running or that the timer has expired. The logic state of the OR operator in block 604 is also provided to an AND operator in block 608. If the logic state input to the AND operator in block 608 indicates that the timer has expired and the vehicle operator still has an emergency stop gesture in effect, the logic flows to block 610.

[0040] At block 610, program logic 310 outputs a control signal to ride control system 300 to stop the ride vehicle, thereby terminating the emergency stop logic operation of ride control system 300. At this point, the ride operator can release the emergency stop gesture without affecting the operation of the ride vehicle.

[0041] Returning to the AND operator at block 608, if the logic state input to the AND operator indicates either 1) the timer is still running or 2) the ride operator is not yet holding the emergency stop gesture, the logic flow ends and the ride vehicle does not stop.

[0042] The delay timer is a safety feature that prevents a sudden, unintentional, valid emergency stop gesture from affecting the operation of the ride vehicle. In one embodiment, the emergency stop delay time is 0.5 seconds.

[0043] Other ride operators can be controlled using logic similar to that of Figure 6. For example, the same logic can be used to unlock ride restraints, close pedestrian gates, or initiate station stops. Each of these actions is performed with various time delays based on valid gestures from a single ride operator. Table 1 below summarizes these ride actions, as well as the dispatch and emergency stop ride actions described in detail above with reference to Figures 5 and 6. JPEG2026500248000002.jpg173145 JPEG2026500248000003.jpg211146 JPEG2026500248000004.jpg77146

[0044] 6 , in some cases, different valid gestures intended to initiate different vehicle actions may be simultaneously recognized by machine learning module 308 and provided to program logic 310. In such cases, program logic 310 is configured to process each valid gesture according to known existing logic and determine whether the vehicle action associated with each valid gesture is a “legal” action. In other words, if program logic 310 determines that nothing is preventing the vehicle action from occurring, then program logic outputs a control signal to initiate that action.

[0045] In some cases, the vehicle actions associated with each valid gesture can be initiated simultaneously, in which case the program logic outputs a corresponding control signal for each action. If the program logic 310 determines that the vehicle actions cannot be initiated simultaneously, the program logic initiates the vehicle actions according to a programmed execution order. In some cases, one action is initiated first, followed by the other action. In some cases, one action is initiated and the other action is ignored.

[0046] With regard to training the CNN of the machine learning module 308, a first CNN model can be trained using known techniques to recognize the set of programmed gestures 402, 404, 406, 408, 410 based on a dataset of images of the programmed gestures captured at various locations within the ride station area 200. The images can correspond to individual frames of video captured by a video camera while a ride operator is performing the gestures. The video can be captured within the ride station area 200 using the vision system 302. Training the first CNN model can be unsupervised, or training the first CNN model can be supervised, in which images in the dataset are manually labeled with gestures and applied to the CNN. In an example of supervised training, a large sample size, e.g., 10,000 images, of images of multiple people performing various gestures is labeled. For example, a person standing with their arms crossed above their head can be labeled as "arms crossed" and used to train a CNN model output that registers "arms crossed" by feeding these images into the CNN, seeing what the CNN output is, comparing the CNN output with the corrected output, and adjusting the CNN weights using backpropagation as needed to get the accurate CNN output.

[0047] The second CNN model can be trained using known techniques to recognize and determine whether a gesture was made by a ride operator based on a labeled dataset of images of features associated with the ride operator. The features 212 can be, for example, patterns, emblems (e.g., retro-reflective emblems), symbols (e.g., bar codes, QR codes), or patches on a uniform that the ride operator would wear. The images can correspond to individual frames of video captured by a video camera while the ride operator is in the ride station area 200. The video can be captured at the ride station area 200 using the vision system 302. Training of the second CNN model can be unsupervised, or training of the second CNN can be supervised, in which images in the dataset are manually labeled with features 212 and applied to the CNN. In an example of supervised training, a large sample size of images containing the features, e.g., 10,000 images, is labeled. For example, if a person wearing a uniform with a specific feature in the shape of an emblem is labeled as an "emblem," these images can be fed into the CNN, checked to see what the CNN output is, compared the CNN output to the corrected output, and adjusted the CNN weights using backpropagation as needed to get the correct CNN output, which is then used to train the CNN model output to register "emblem."

[0048] 7 is a flowchart of a method for controlling operation of an amusement park ride having ride station areas where patrons board and disembark ride vehicles under the supervision of one or more ride operators. The method may be performed by ride control system 300 of FIGS. 2 and 3.

[0049] 2 and 3, one or more images of one or more ride operators 208a, 208b, 208c are captured at one or more locations within ride station area 200 by vision system 302. Ride system 302 includes multiple video cameras 210a, 210b, 201c, 210d positioned to provide a field of view that includes ride station area 200. Video cameras 210a, 210b, 201c, 210d provide real-time video feeds of ride operators 208a, 208b, 208c.

[0050] 3 and 4, at block 704, one or more valid gestures are recognized in one or more images. To this end, one or more images captured by the vision system 302 are applied to a machine learning module 308 having a first model trained to identify gestures 402, 404, 406, 408, 410 that correspond to gestures in a set of programmed gestures. The set of programmed gestures can include any number of different gestures. Examples of sets of programmed gestures are shown in FIGS. 4A-4E.

[0051] Proceeding to block 704, the images of the one or more people captured by the vision system 302 are also applied to a second model of the machine learning module 308 that is trained to determine when the gestures 402, 404, 406, 408, 410 identified by the first model are made by one of the one or more vehicle operators. To this end, the second model is trained to recognize features 212 associated with the vehicle operators. The features 212 may be, for example, a pattern, an emblem (e.g., a retro-reflective emblem), a symbol (e.g., a barcode, a QR code), or a patch on a uniform that the vehicle operators would wear.

[0052] At block 706, and with further reference to Figures 3, 5, and 6, valid gestures recognized in one or more images are processed by program logic 310 to enable vehicle operation.

[0053] 5, in some embodiments, processing a valid gesture in the image to enable a vehicle action includes enabling a vehicle action from a first set of vehicle actions if the image includes the same valid gesture from at least two of the ride operators. The first set of vehicle actions may include, for example, vehicle dispatch. In some embodiments, in addition to requiring the same valid gesture from at least two of the ride operators, processing by program logic 310 requires that the same valid gesture be continuously present in the image for a threshold duration. The threshold duration is programmable and may be, for example, two seconds. In some embodiments, in addition to requiring the same valid gesture for a specified duration from at least two of the ride operators, processing by program logic 310 requires receiving a corresponding action signal from the operator control console.

[0054] 6 , in some embodiments, processing a valid gesture in the image to enable a vehicle action includes enabling a vehicle action from a second set of vehicle actions if the image includes a valid gesture from at least one of the vehicle operators. The second set of vehicle actions may include, for example, an emergency stop, a station stop, an unlock restraint, a close pedestrian gate, etc. In some embodiments, in addition to requiring a valid gesture from one of the vehicle operators, processing by the program logic 310 requires that the valid gesture be present in the image for a threshold duration. The threshold duration is programmable and may be, for example, 0.5 seconds or 2 seconds.

[0055] Referring to FIG. 3 , as disclosed herein, operation of an amusement park ride can be controlled utilizing a ride control processor 304. The ride control processor 304 can be any device employing a processor, such as an application-specific processor. The ride control processor 304 can also include a memory 306 that stores instructions executable by a machine learning module 308 and program logic 310 to perform the described methods and ride control operations. The machine learning module 308 and program logic 310 can include one or more processing devices, and the memory 306 can include one or more tangible, non-transitory machine-readable media. By way of example, such machine-readable media can include RAM, ROM, EPROM, EEPROM, optical disk storage, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of machine-executable instructions or data structures and that can be accessed by the machine learning module 308 and program logic 310 or any general-purpose or special-purpose computer or other machine having a processor.

[0056] Accordingly, disclosed herein is a ride control system 300 for controlling operation of an amusement park ride under the supervision of one or more ride operators. The ride control system 300 includes a vision system 302 and a ride control processor 304 coupled to receive images from the vision system 302. The vision system 302 is configured to capture images of the one or more ride operators at one or more locations within a ride station area. The ride control processor 304 includes a machine learning module 308 configured to recognize one or more valid gestures within the one or more images. The ride control processor 304 also includes program logic 310 configured to process the one or more valid gestures within the one or more images to enable ride operation.

[0057] The vehicle control system 300 disclosed herein is advantageous over current systems in that it allows for control of vehicle operation from a single operator control console without requiring all vehicle operators to be within line of sight of the vehicle operator at the operator control console.

[0058] Within this disclosure, the term "exemplary" is used to mean "serving as an example, instance, or illustration." Any embodiment or aspect described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects of the disclosure. Likewise, the term "aspect" does not require that all aspects of the disclosure include the discussed feature, advantage, or mode of operation. As used herein, the term "coupled" refers to a direct or indirect coupling between two objects. For example, a first object can be coupled to a second object without the first object being in direct physical contact with the second object.

[0059] One or more of the components, steps, features, and / or functions illustrated in Figures 1-7 may be rearranged and / or combined into a single component, step, feature, or function, or embodied in multiple components, steps, or functions. Additional elements, components, steps, and / or functions may also be added without departing from the novel features disclosed herein. The apparatus, devices, and / or components illustrated in Figures 1-7 may be configured to perform one or more of the methods, features, or steps described herein. Additionally, the novel algorithms described herein may be efficiently implemented in software and / or hardware.

[0060] It is understood that the specific order or hierarchy of steps in the methods disclosed is an example of a sample process. Based on design preferences, it is understood that the specific order or hierarchy of steps in the methods can be rearranged. The appended claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy presented, unless specifically stated therein.

[0061] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Accordingly, the claims are not intended to be limited to the aspects set forth herein, but are to be accorded the full scope consistent with the language of the claims, wherein reference to an element in the singular is not intended to mean "only one," unless specifically so stated, but rather "one or more." Unless otherwise specified, the term "some" refers to one or more. Phrases referring to "at least one" of a list of items refer to any combination of those items, including single members. As an example, "at least one of a, b, or c" is intended to cover a; b; c; a and b; a and c; b and c; and a, b, and c. All structural and functional equivalents to the elements of the various embodiments described throughout this disclosure that are known or later become known to those skilled in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Furthermore, nothing disclosed herein is intended to be made available to the public, regardless of whether such disclosure is expressly recited in the claims. Any claim element shall be construed under the provisions of 35 U.S.C. § 112(f) unless the element is expressly recited using the phrase "means for," or, in the case of a claim, unless the element is recited using the phrase "step for." [Explanation of symbols]

[0062] 302 Vision System 206 Operator Control Console 304 Vehicle Control Processor 308 Machine Learning Module (Gesture Recognition) 310 Program Logic 306 memory

Claims

1. 1. A ride control system for controlling operation of an amusement park ride having a ride station area under the supervision of one or more ride operators, comprising: a vision system configured to capture one or more images of the one or more ride operators at one or more locations within the ride station area; a vehicle control processor coupled to receive one or more images from the vision system, a machine learning module configured to recognize one or more valid gestures in the one or more images, wherein a valid gesture corresponds to a gesture from at least one of the one or more vehicle operators; and program logic configured to process the one or more valid gestures in the image to enable a vehicle operation; a vehicle control processor including: A vehicle control system comprising:

2. The machine learning module: identifying gestures in the one or more images that correspond to gestures in a set of programmed gestures; determining that the identified gesture was made by at least one of the one or more vehicle operators; 10. The vehicle control system of claim 1, wherein the vehicle control system is configured to recognize one or more valid gestures in the one or more images by being trained to recognize one or more valid gestures in the one or more images.

3. 3. The ride control system of claim 2, wherein the machine learning module is trained to identify gestures in the one or more images that correspond to gestures in the set of programmed gestures based on a labeled dataset of images of programmed gestures captured at one or more locations within the ride station area.

4. The vehicle control system of claim 3 , wherein images of programmed gestures in the labeled data set are captured by the vision system.

5. 3. The ride control system of claim 2, wherein the machine learning module is trained to determine that the identified gesture was made by at least one of the one or more ride operators based on a labeled dataset of images of features associated with the one or more ride operators.

6. The program logic comprises: the one or more valid gestures in the one or more images include a plurality of the same valid gestures from at least two of the one or more vehicle operators; 10. The vehicle control system of claim 1, configured to enable vehicle operation when

7. The program logic comprises: the one or more valid gestures in the one or more images include a plurality of the same valid gestures from at least two of the one or more vehicle operators; each of the plurality of identical valid gestures is present in the one or more images for a threshold duration; 10. The vehicle control system of claim 1, configured to enable vehicle operation when

8. The vehicle control processor is coupled to an operator control console, and the program logic comprises: the one or more valid gestures in the one or more images include a plurality of the same valid gestures from at least two of the one or more vehicle operators; each of the plurality of the same valid gestures is present in the one or more images for a threshold duration; a corresponding operating signal is received from said operator control console; 10. The vehicle control system of claim 1, configured to enable vehicle operation when

9. The program logic comprises: the one or more valid gestures in the one or more images include a single valid gesture from at least one of the one or more vehicle operators; 10. The vehicle control system of claim 1, configured to enable vehicle operation when

10. The program logic comprises: the one or more valid gestures in the image include a single valid gesture from at least one of the one or more vehicle operators; the single valid gesture is present in the image for a threshold duration; 10. The vehicle control system of claim 1, configured to enable vehicle operation when

11. 1. A method of controlling operation of an amusement park ride having ride station areas under the supervision of one or more ride operators, comprising: capturing one or more images of one or more of the one or more ride operators at one or more locations within the ride station area; Recognizing one or more valid gestures in the one or more images, wherein the valid gestures correspond to gestures from at least one of the one or more vehicle operators; processing the one or more valid gestures in the one or more images to enable vehicle operation; A method comprising:

12. Recognizing one or more valid gestures in the one or more images applying the one or more images to a machine learning module trained to identify gestures that correspond to gestures in a set of programmed gestures; applying the one or more images to a machine learning module trained to determine that the identified gesture was made by one of the one or more vehicle operators; The method of claim 11 , comprising:

13. Processing the one or more valid gestures in the one or more images to enable vehicle operation includes: the one or more valid gestures in the one or more images include a plurality of the same valid gestures from at least two of the one or more vehicle operators; 12. The method of claim 11, comprising enabling the vehicle operation if

14. Processing the one or more valid gestures in the one or more images to enable a vehicle operation includes: the one or more valid gestures in the one or more images include a plurality of the same valid gestures from at least two of the one or more vehicle operators; each of the plurality of the same valid gestures is present in the one or more images for a threshold duration; 12. The method of claim 11, comprising enabling the vehicle operation if

15. Processing the one or more valid gestures in the one or more images to enable vehicle operation includes: the one or more valid gestures in the one or more images include a plurality of the same valid gestures from at least two of the one or more vehicle operators; each of the plurality of the same valid gestures is present in the image for a threshold duration; A corresponding operating signal is received from an operator control console; 12. The method of claim 11, comprising enabling the vehicle operation if

16. Processing the one or more valid gestures in the one or more images to enable vehicle operation includes: the one or more valid gestures in the one or more images include a single valid gesture from at least one of the one or more vehicle operators; 12. The method of claim 11, comprising enabling the vehicle operation if

17. Processing the one or more valid gestures in the one or more images to enable vehicle operation includes: the one or more valid gestures in the image include a single valid gesture from at least one of the one or more vehicle operators; the single valid gesture is present in the one or more images for a threshold duration; 12. The method of claim 11, further comprising enabling the vehicle operation if

18. a machine learning module configured to recognize one or more valid gestures within one or more images, the valid gestures corresponding to gestures from at least one of one or more ride operators within a ride station area, the machine learning module comprising: a first model trained to identify gestures in images that correspond to gestures in a set of programmed gestures; a second model trained to determine that the gesture was made by at least one of the one or more vehicle operators; a machine learning module, and program logic configured to process the one or more valid gestures in the one or more images to enable a vehicle operation. Vehicle Control Processor.

19. 20. The ride control processor of claim 18, wherein the first model includes a convolutional neural network trained to identify gestures corresponding to gestures in the set of programmed gestures based on a labeled dataset of images of programmed gestures captured at one or more locations within the ride station area.

20. 19. The vehicle control processor of claim 18, wherein the second model comprises a convolutional neural network trained to determine that the gesture was made by at least one of the one or more vehicle operators based on a labeled dataset of images of features associated with the one or more vehicle operators.

Images