Athlete training system with biometric sensory input

Abstract

NOT VISIBLE DUE TO STATUS OF PATENT

Description

PATENT Dkt.0215.0005-PCT ATHLETE TRAINING SYSTEM WITH BIOMETRIC SENSORY INPUT _________________________________________________ Related Application

[0001] This application claims priority to, and the benefit of, U.S. Provisional Patent Application No. 63 / 619,20, filed January 9th, 2024, and entitled, “Athlete Training System With Biometric Sensory Input”, which is hereby incorporated by reference herein in its entirety. Field

[0002] This disclosure relates generally to training systems and, more particularly, to sensor-based intelligence systems used to train an athlete to increase athletic proficiency. Background

[0003] With conventional athlete analytic systems, one or more activities of an athlete is compared to a standard and the athlete is informed of any deviation from ideal via a static information manner, such as audible or visual indication of how the athlete should be performing. While some athletes may be able to efficiently interpret information derived from senor data, it is generally inefficient for an athlete to be able to translate data into practical actions and drills to improve performance. Hence, there is a continued goal of providing provide intelligent translation of sensor data into training instructions and drills. Summary

[0004] Various embodiments of the present disclosure are generally directed to athlete training systems, such as but not limited to corrective behavior learning.

[0005] In some embodiments, a computing device may be connected to an array of sensors positioned proximal an athlete. A feedback strategy may be generated by a feedback module of the computing device with the feedback strategy selecting at least one manner of communicating training information to the athlete from a plurality of different available manners of communicating training information. A potential module of the computing device may compute an athletic potential of the athlete in response to sensedathletic behavior of the athlete detected by array of sensors. The potential module may estimate a current skill level of the athlete in response to sensed athletic behavior of the athlete detected by the array of sensors. A training module of the computing device may determine a difference between the athletic potential of the athlete and the current skill level of the athlete before assigning a first training drill to increase a proficiency in at least one athletic task associated with the current skill level. The training module may alter the first training drill to a second training drill in response to an increase in proficiency of the at least one athletic task detected by the array of sensors.

[0006] An athletic training system, in other embodiments, may have a computing device connected to an array of sensors. The computing device may have a processor, a memory, and circuitry arranged as a feedback module, a potential module, and a training module. The feedback module may generate a feedback strategy that selects at least one manner of communicating training information to the athlete from a plurality of different available manners of communicating training information. The potential module may compute an athletic potential of the athlete in response to athletic behavior of the athlete detected by the array of sensors and estimate a current skill level of the athlete in response to athletic behavior of the athlete detected by the array of sensors. The training module may determine a difference between the athletic potential of the athlete and the current skill level before assigning a first training drill to increase a proficiency in at least one athletic task associated with the current skill level. Subsequently, the training module may alter the first training drill to a second training drill in response to an increase in proficiency of the at least one athletic task detected by the array of sensors.

[0007] These and other features which characterize various embodiments of the present disclosure can be understood in view of the following detailed discussion and the accompanying drawings. Brief Description of the Drawings

[0008] FIG. 1 is a functional block representation of an athletic environment in which various embodiments of the present disclosure can be practiced.

[0009] FIG. 2 shows a block representation of a training assembly that may be utilized in the athletic environment of FIG.1 in accordance with some embodiments.

[0010] FIG.3 shows a block of a training module that may be employed as part of an athlete training system in accordance with assorted embodiments.

[0011] FIG. 4 depicts a block representation of an example athlete training system configured and operated in accordance with various embodiments.

[0012] FIG. 5 is a flowchart depicting example operation of the athlete training system of FIG.4 in accordance with various embodiments.

[0013] FIG. 6 is a flowchart depicting example operation of the athlete training system of FIG.4 performance in accordance with some embodiments.

[0014] FIG.7 is a flowchart depicting example operations of the athlete training system of FIG.4 in accordance with assorted embodiments. Detailed Description

[0015] Various embodiments of an athlete training system are generally directed at utilizing computing capabilities, artificial intelligence, and machine learning to optimize an athlete’s improvement in a sport-specific activity. The speed, size, and intelligence capabilities of modern computing components and devices have allowed athletes engaged in a variety of different sports and athletic activities to have their motions and biometrics analyzed. However, conventional computing devices and components, previously, have been limited in how effective corrections, instructions, and information have been conveyed to an athlete. Accordingly, various embodiments are directed to an athlete training system that intelligently interprets sensed activity and biometrics into instructions and drills optimized to the specific athlete.

[0016] FIG. 1 illustrates aspects of an athletic environment 100 in which assorted embodiments of an athletic training system may be practiced. One or more athletes 110 may participate in the athletic environment 100 and conduct any number, and type, of actions in the performance of an activity, such as football, basketball, golf, tennis, pickleball, weightlifting, dancing, karate, or other sporting event. An athlete 110 may engage an athletic apparatus 120, such as a goal, hoop, net, or hole. It is contemplated that an athletic apparatus 120 may have multiple sub-components 122, such as a backboard and a hoop or a bar and weights.

[0017] An athlete 110 may be by any number, and type, of sensor that utilizes optical, acoustic, mechanical, or other detector. Such monitoring may detect and / or record numerous concurrent conditions for an athlete 110, such as movement, position, velocity, acceleration, VO2Max, and heart rate, as well as environmental conditions, such as wind speed, wind direction, temperature, humidity, and pressure. Various embodiments connect the assorted sensors in an environment 100 to a computing device 130 that may process, store, and compute signals to determine the activity, The computing device 130 may utilize a processor 132, such as a microcontroller or programmable circuitry, and memory 134, such as volatile, non-volatile, solid-state, magnetic, and tape data storage, to interpret sensed data into athletic information about the athlete 110 and / or athletic activity.

[0018] A sensor may be positioned in a variety of positions in an athletic environment 100. For instance, mounted sensors 142 may be secured with a stand, mount, or other physical structure anywhere around a room, field, course, or court. In some embodiments, an array of sensors 150 is positioned proximal an athlete 110. As shown, a sensor array 150 may be specifically configured to attach a sensor 152 to a designated portion of an athlete 110, such as a head 112, torso 114, arm 116, or leg 118. By providing one or more sensors 152 on a wearable band, strap, harness, or other wearable garment, various aspects of athlete 110 activity and position may be accurately and efficiently sensed.

[0019] Despite the incorporation of computer processing and memory with one or more computing devices 130, the translation of collected information from sensors 142 / 152 into identified tendencies, behaviors, and deviations from ideal performance may be inefficient. FIG. 2 conveys a block representation of portions of a training assembly 200 that may be utilized in the athletic environment 100 of FIG. 1 in some embodiments. The training assembly 200 may be arranged and operated to provide feedback to an athlete 110 before, during, and after an athlete 110 engages in physical activity. The training assembly 200 may include any number of computing devices 130 that employ one or more processors 132 to translate raw data from one or more sensors 142 / 152 into an understanding of what, and where, the athlete 110, is doing and how to train one or more athletic actions with practical feedback.

[0020] In the non-limiting examples in FIG. 2, a computing device 130 may compile sensor data into representations of one or more movements, actions, or behaviors of an athlete 110. The processor 132 may convey such compiled sensor data to an athlete 110 via a graphical plotting of activity (solid line 222) compared to one or more plots (segmented line 224) corresponding with ideal activity for maximum performance. That is, information derived from sensed athlete activity can be presented to the athlete 110 in graphical form, once compiled by the processor 132, compared to ideal athletic activity. Such graphical comparison of actual behavior to ideal behavior may efficiently convey a relatively large amount of information. However, an athlete 110 may not efficiently translate the graphical comparison into practical changes, drills, or positions that will improve performance over time.

[0021] Other embodiments may utilize the computing processor 132 to provide audible and / or visual checklist of ideal behavior element list 232 compared to the sensed behavior and activity of an athlete 110. In other words, the processor 132 may identify goals, elements, and other aspects of an ideal behavior, such as moving a ball, performing a jump shot, lifting a weight, racing a vehicle, or hitting a ball. The identified aspects of an ideal behavior may be displayed, or spoken, to an athlete 110 as tasks that have been met (check mark), been missed (x mark), or yet to be achieved (question mark), as shown in list 232. Through the identification of ideal behavior aspects to be conducted by an athlete 110, overall behaviors, movements, and actions can be efficiently conveyed. However, an athlete 110 may not efficiently, or accurately, understand how to achieve certain identified ideal elements, which can correspond with inefficient growth, learning, or improvement through practice.

[0022] Embodiments of the computing device 130 utilize a processor 132 to capture aspects of an athlete’s behavior and identify deviations from a predetermined standard stored in memory 134 accessible by the processor 132. Such identification of how behavior is different than a standard position, motion, or application of force can be characterized as visual feedback 242 that augments a picture, video, or series of pictures with text, arrows, circles, or other identifying marks to indicate where the athlete is not performing according to a standard.

[0023] Although the computer 132 may efficiently analyze an athlete’s behavior and incorporate one or more identifiers to visual direct an athlete 110 to what aspects are different than ideal, such visual feedback 242 may be inefficient at conveying how to change to correct the identified issue. For instance, visual feedback 242 may convey where they are deficient, such as posture, arm movement, or timing of the application of force, but may be inefficient at indicating what an athlete 110 can do to improve performance. In other words, visual feedback 242 may identify what is wrong without indicating how the athlete 110 can reach the ideal performance. Indeed, some athletes 110 may understand visual feedback 242 well, but others may misunderstand, or not comprehend, what is needed to conduct ideal behavior for maximum performance.

[0024] In some embodiments, the computing device 130 may generate multiple different types of feedback for an athlete 110. As an example, the computing processor 132 may generate visual feedback 242 and graphical analytics 222 / 224 that may be selected by an athlete 110 or shown concurrently to the athlete 110. However, the diversity of feedback may be insufficient and / or inefficient at improving the performance of an athlete 110. It is contemplated that conventional feedback, such as graphical analytics, visual feedback 242, and checklist elements 232, may lack progressive actions or activities to gradually correct an athlete’s behavior. Instead, feedback may simply show the differences in an athlete’s behavior compared to an ideal standard, which may be challenging to correctly implement into some behaviors, particularly complex behaviors commonly utilized in sports activities like golf, basketball, baseball, weight lifting, racing, and soccer.

[0025] The use of a single standard for ideal behavior for an athlete 110 may add challenges to accurate implementation, despite efficient visual representation of an athlete’s deviation from ideal behavior. That is, ideal performance may be different for different athletes 110 and may correspond with different postures, positions, motions, and movements to reach maximum possible performance of athletic capabilities. For instance, a single ideal standard for athletic behavior may not factor an athlete’s capabilities due to body type, previous injury, current skill level, or environment. As such, the computing processor 132 can lack analysis and / or instruction to efficiently improve an athlete’s performance and / or reaching an athlete’s performance potential.

[0026] Accordingly, embodiments of computing device 130 utilize intelligence, machine learning, and / or other circuitry to identify at least one type of feedback to communicate efficiently and accurately with an athlete 110, identify maximum athletic potential for an athlete 110 based on current skill, capabilities, and / or body abilities, and generate practical actions and / or progressions for an athlete 110 to conduct to improve athletic behavior to reach more of an athlete’s performance potential.

[0027] FIG. 3 is a block representation of portions of an athlete training system 300 configured and operated in accordance with various embodiments. The training system 300 may employ any number and type of computing device 130 to provide intelligent collection, analysis, and feedback to an athlete 110 participating in an athletic environment 100. The computing device 130 may employ one or more processors 132 to translate assorted input information into a variety of determinations, strategies, and milestones that can be used to efficiently communicate with an athlete 110 and convey training activities optimized to improve the athlete’s performance.

[0028] While not limiting or required, various embodiments input at least data from sensors 120, biographical data about the subject athlete 110, environmental data, and model data to compute the athletic performance potential of the athlete 110. The assorted input data and data generated by the local, or remote 302, processors 132 may be temporarily, or permanently, stored in memory 134, which may make computations, analysis, and intelligent generation of feedback more efficient than if a memory 134 was not utilized for data storage. The ability to utilize multiple processors 132, either local or remotely located, provides robust computing capabilities that feed various operational modules. It is noted, however, that some embodiments utilize separate processors 132 for the respective operational modules of the computing device 130.

[0029] The assorted operational modules 310 / 320 / 330 shown in FIG.3 are respectively illustrated in block form for simplicity, but may include one or more circuits physically present in a local, or remote, computing device 130, such as a tablet, smartphone, laptop, or desktop computer, that operate to translate input signals into at least one decision, determination, or conclusion. Hence, each module 310 / 320 / 330 may include numerous separate signal pathways, integrated circuits, chips, system on chips (SoC), or otherprogrammable circuitry that provides selection of an answer or determination with regard to at least what type of feedback is optimal for an athlete, what the athletic potential of an athlete is, what drills can be conducted by an athlete to improve towards their potential, and if a training milestone has been achieved.

[0030] Although the processor(s) 132 / 302 of the computing device 130 may operate alone to translate input data into assorted training determinations, such as athletic potential and drills, various embodiments structurally configure the computing device 130 with separate circuitry directed to carrying out specific tasks alone, or with the aid of the available processors 132 / 302. Such task specific circuitry can be characterized as a module, but in no way limits the possible circuit configurations and operational components of the computing device 130 that may intelligently translate input data into athlete training aspects. In other words, circuitry of the computing device 130 can operate alone, or in combination with other circuitry, to carry out data analysis, computations, determinations, and content generation.

[0031] The computing device 130 may have a feedback module 310 directed at determining the optimal manner in which training information is conveyed to an athlete 110. In some embodiments, the feedback module 310 generates a feedback strategy that includes multiple different manners of conveying information in response to thresholds, triggers, or detected actions prescribed by the feedback module 310. For example, the feedback module 310 may translate various biographical and / or sensed data about an athlete 110 into a strategy that conveys training feedback as audio signals while the athlete 110 is moving and as a combination of audio and graphical visual elements when the athlete 110 enters a predetermined geofence area, moves to face a predetermined direction, or disengages a piece of athletic equipment.

[0032] Embodiments of the feedback strategy prescribe different visual, audio, and / or haptic feedback manners of communication based on how effective the respective manners are at communicating. As an example, the feedback strategy may define a progression of feedback manners of communicating, such as audio only, augmented reality visual representation of an ideal way of performing an athletic task, haptic taps, or a combination thereof, which may be sequentially activated by the computing device 130 manually inresponse to input or automatically from athletic performance, such as an incorrect alignment, mistiming, or motion. Through the electronic determination of the feedback strategy, the feedback module 310 provides intelligent and efficient communication with an athlete 110 that can result in optimized training time and athletic performance improvement over time.

[0033] It is contemplated that the feedback module 310 refines a feedback strategy over time as greater volumes of sensed data aid in identifying what is effective for a particular athlete 110. Hence, the feedback strategy may be customized to a particular athlete 110 and, perhaps, evolve over time as the feedback module 310 builds a more accurate athlete profile with sensed activity. The presence of an athlete profile stored in the memory 212 may provide an array of characteristics that aid in the generation, and communication, of training commands, drills, tasks, and information. Some embodiments of the athlete profile may include various athlete biographical information. Such information may be input by the athlete 110, derived from sensed data, and / or derived from the athlete’s athletic performance over time.

[0034] It is noted that the presence of an accurate athlete profile may be helpful in effectively determining the athletic potential of an athlete 110 with a potential module 320 of the computing device 130. An athlete profile is not limited to a particular set of information, but may have physiological information about an athlete 110 as well as existing skill levels for various athletic tasks. In the absence of an existing athlete profile, the potential module 320 may construct a new profile, temporarily substitute a different athlete’s profile, and / or make assumptions about assorted aspects of an athlete’s skill, physical capabilities, and injuries until an accurate athletic performance potential can be determined from sensor input in response to athletic actions of the athlete 110.

[0035] While a determination about an athlete’s skill or physical potential is not required for the computing device 130 to translate various sensed aspects of an athlete 110 into drills that may improve one or more athletic tasks, the availability of an accurate current skill level and / or athletic potential for an athlete 110 may allow for greater precision and faster training progression compared to the training module 330 assigning training drills solely in response to sensed aspects. The separation of the potential module 320 andthe training module 330 may allow for analysis and conclusions about an athlete to efficiently create athletic tasks that have a high chance of improving the athlete’s performance of a sport or athletic activity in the future.

[0036] It is noted that training tasks can be characterized as drills, which may, or may not, correspond with actual positions, movements, or equipment employed to participate in a sport or athletic activity. For instance, yoga poses, or movements, may be assigned by the training module 330 to improve balance, range of motion, and / or coordination improvement drills that are not directly conducted in the execution of a sport or athletic activity being trained and improved. Other instances of training drills created by the training module 330 direct an athlete 110 to conduct exact poses, movements, or partial movements that are used to play a sport or athletic activity in an effort to improve positions, consistency, and / or stamina of the athlete 110.

[0037] The presence of an accurate determination of an athlete’s potential and / or current skill level may allow the training module 330 to prescribe more effective drills than if sensor readings were utilized alone. For example, the type, intensity, progression, and timing of drills can be intelligently selected sooner and more accurately by the training module 330 in response to an established skill level and / or athletic potential for an athlete 110. More specifically, a drill assigned based on a known skill level may have a relatively fine resolution that engrains precise positions and / or motion while a drill assigned without knowledge of an athlete’s skill level may have a relatively coarse resolution that trains general positions and / or motion.

[0038] Operation of the circuitry of the training module 330, in some embodiments, creates a series of drills that is intelligently sequenced to engrain assorted positions, movements, and actions that correspond with improved athletic performance. Embodiments of the training module 330 may further assign a progression of training drills to determine, or verify, an athlete’s proficiency in an athletic task or physical capability, which may serve to improve the assignment of training drills to the athlete in the future. Along with generating drills to improve athletic performance, the training module 330 may generate milestones that indicate where an athlete 110 is in relation to being able to perform with maximum athletic potential. Milestones may additionally provide triggering events in anathlete’s training to a different, or schedule of drills, which may increase the likelihood of muscle confusion and tangible performance results from training tasks.

[0039] FIG.4 illustrates a block representation of portions of an athlete training system 400 utilizing a computing device 130 in accordance with various embodiments. The system 400 employs a number of separate sensors 120 that can be stationary 122 or dynamic 124 to provide data and signals to the assorted circuitry of the computing device 130. Through the analysis of the sensed aspects of an athlete’s activities, the computing device 130, and specifically the potential module 320, may determine a current skill level of an athlete 110 and an athletic potential in step 402.

[0040] The potential of an athlete 110 in step 402 may include numerous different athletic potentials to conduct assorted actions and movements associated with performing a sport or athletic activity. For instance, the potential in step 402 may include different athletic potentials for strength, jumping height, reaction time, and range of motion that collectively are utilized to perform a golf swing, jump shot, tackle, pass, or lift weights. Some embodiments of step 402 base the athletic potential and / or skill level determinations on past logged athlete behaviors and / or determinations about skill and potential. It is contemplated that step 402 verifies previous potential and / or skill determinations with, or without, alterations to the previous conclusions.

[0041] As discussed above, the conclusion of an athlete’s skill level and physical potential in step 402 is not required as the computing device 130, and specifically the feedback module 310, may make a decision, or strategy, in step 404 that dictates how training information is conveyed to an athlete. That is, the feedback module 320 may determine that a single communication manner is to be employed, such as audible, tactile, or visual instructions, a combination of communication types is to be utilized, such as augmented reality visual display and audible cues, or all the available manners are to be used to convey how the athlete is performing and / or instructions for conducting one or more drills.

[0042] The feedback decision from step 404 may include a predetermined progression of communication manners that are triggered by established thresholds, such as reaching athletic performance thresholds, timed activity limits, proper drill execution, or transition toa new drill. It is noted that the computing 130, and specifically the training module 330, may generate one or more drills in step 406 to perform by an athlete 110 and performance milestones in step 408 that may, or may not, be communicated to the athlete 110 upon satisfaction. That is, the computing device 130 may generate a single training drill, or a prescribed series of drills, in step 406 along with a single performance milestone, or plurality of different milestones, in step 408 with, or without, the determination of an athlete’s performance potential in step 402 and / or manner of feedback in step 404.

[0043] With the generation and determination of the various training aspects in steps 402-408, the computing device an provide intelligent training tasks that progress an athlete 110 in proficiency of at least one aspect of an athletic activity. By basing prescribed drills on a relatively accurate understanding of the skill level and / or athletic performance potential of an athlete 110, the computing device 130 may increase the abilities of the athlete 110 faster, and potentially more accurately, than if a standard schedule of drills is prescribed without regard for the particular athlete 110. The combination of drills customized to the abilities of the athlete 110 and training feedback, along with training instructions, conveyed to the athlete 110 in manner(s) intelligently selected based on the athlete’s traits allows for optimized speed, accuracy, and effectiveness of training time.

[0044] Through the various capabilities and intelligence provided by the circuitry of the computing device 130, training programs may be more efficient and effective due to increased automation over time. That is, the modules and processing circuitry of the computing device 130 may generate a schedule of drills and / or feedback manners that may be automatically activated and delivered to an athlete in response to predetermined triggers, such as time, drill proficiency threshold reached, or body language of the athlete 110. The ability to initially prescribe a schedule of training drills and / or feedback manners does not exclude the computing device 130 from changing or removing previously prescribed drills, or feedback manner, in real-time in response to one or more sensed aspects of the athlete 110, such as drill task failure, inconsistent posture, or relatively quick proficiency in an assigned athletic task.

[0045] The ability to customize training drills as well as how the drills are conveyed to an athlete 110 allows for automated or reactionary adaptations that maintain a high degreeof training efficiency and effectiveness changes in training conditions over time. For instance, the proactive prescription of customized training content, and delivery manner, may be complemented by reactive customizations as a result of injury, training progression, fatigue, sickness, muscle growth, or skeletal changes. In practice, the intelligence and / or learning provided by the circuitry of the computing device 130 may consistently identify more accurate, current conditions associated with a training subject (athlete 110) by factoring in recent sensor data, which ensures the prescribed training drills, as well as the manner feedback is conveyed, are optimized to provide the highest chance of success in the quickest timeframe possible.

[0046] Indeed, the adaptive capabilities of the circuitry of the computing device 130 allows for real-time alterations to training instructions and / or drills to provide constructive training activities, and time, that have a high chance of progressing the proficiency of the athlete 110 being trained despite intentional and inadvertent changes in training conditions. As a non-limiting example, the computing device 130 may discard previously assigned training instructions, add training instructions to existing drills, add training feedback in relation to generated milestones, or alter drill tasks in response to one or more sensed athletic conditions, such as inconsistent drill effectiveness, large latency in understanding feedback, or frustration in the athlete 110.

[0047] FIG.5 is a flowchart of an example feedback routine 500 that may be performed by an athlete training system, such as the systems 300 / 400 of FIGS. 3 & 4. The feedback routine 500 may begin with a computing device 130 compiling a biographical athlete profile in step 502. Such a profile is not limited to a particular number, type, or recency of biographical metrics, but, in some embodiments, includes assorted sensor data associated with an athlete 110. It is contemplated that the profile compiled in step 502 consists of physiological information measured by a sensor, such as height, weight, or wingspan, as well as derived information from sensed information, such as flexibility, range of motion, strength, or coordination.

[0048] While a profile for an athlete being trained is not required for the computing device 130 to intelligently translate sensed information into drills, training tasks, and feedback, the presence of a profile allows for efficient use of training time, particularly atthe outset of a training session when little sensor data has been accumulated. As step 502 compiles biographical athlete information from one or more sensors, decision 504 can evaluate if an existing profile accurately describes the athlete engaged in training. For instance, the computing device 130, in decision 504, may use facial recognition or other unique physical feature, such as a fingerprint, retina scan, voice passcode, or gesture, to identify an athlete and a corresponding profile. It is contemplated that decision 504 may correlate a profile of a different athlete to the athlete being trained due to detected similarities, such as height, weight, or posture during an activity.

[0049] In the event decision 504 locates a known profile, or a close enough profile to more accurately describe the athlete being trained than a template profile, step 506 proceeds to populate the profile with the most current sensed information. It is noted that populating a profile in step 506 may result in adding, changing, or removing existing aspects of a profile, which ensures the profile has the most up-to-date information to describe the athlete being trained. It is further noted that populating an athlete profile may involve entering raw data, such as consistency, timing, applied force, and weight transfer metrics, entering derived data, such as balance, coordination, and skill level, or entering speculative data not directly based on sensed information, such as physical potential.

[0050] The population of profile information may result in greater volumes of changes in step 508 when a template profile is utilized in place of a particular identified athlete or a profile that closely resembles the athlete being trained. That is, if decision 504 does not find an acceptable existing profile, step 508 utilizes a template, or default, profile with the expectation that a majority of the profile aspects will be modified early and often in a training session as sensed data is collected, logged, and analyzed. The use of a template profile can increase efficiency of computing device 130 by providing reasonable assumptions, which contrasts a one size fits all schedule of drills, selected task to improve during training, and resolution of feedback, volume of feedback, manner of feedback.

[0051] It is noted that the population of accurate biographical information in one or more steps 502 / 506 / 508 may include metrics pertaining to the physiological aspects of an athlete. For instance, a profile, or template, may be populated with information taken directly from sensors, such as hand size or body mass index, along with derivedinformation, such as balance or without the athlete engaging in athletic activities. However, biographical information may, alternatively, be sensed during the preparation and / or execution of an athletic activity, such as throwing a ball, hitting a ball, or running. The ability to provide a reasonably accurate profile with or without engaging in athletic activities provides system flexibility and allows training sessions to be as efficient as possible due to training drills and feedback being generated and chosen intelligently with respect to the athlete’s profile.

[0052] With a profile populated with biographical information about an athlete to be trained, one or more athletic activities may be sensed by at least one sensor in step 510 before being analyzed by a system computing device. The sensing of athletic activity in step 510 may occur continuously, or sporadically, in response to prescribed actions, or spontaneous actions elected by the athlete. Compared to the biographical information detected, or derived, in steps 506 or 508, the sensed athletic activities in step 510 may be directed to measuring static and dynamic aspects of performing predetermined athletic tasks associated with a trained sport. As such, various embodiments of step 510 concurrently, or sequentially, employ multiple different sensors, such as stationary 122 and dynamic 124 sensors, to collect data involving a selected athletic task.

[0053] As a non-limiting example of step 510 compared to collecting biographical information, instead of a single sensor collecting information about a single biographical aspect, such as weight or height, multiple sensors can simultaneously detect different characteristics in step 510 about the posture of an athlete followed immediately by different characteristics of the athlete’s movement as a ball is hit, thrown, shot, or caught. The assorted sensed characteristics during an athletic activity in step 510 is applied to the athlete’s profile in step 512 to continually provide the most accurate, and current, representation of the athlete. It is noted that the application of sensed data to an athlete’s profile in step 512 may involve processing, combining, or derivation from the raw measurements of one or more sensors.

[0054] With a profile populated with both biographical and athletic activity data, step 514 may generate at least one feedback manner for training information based on the profile. That is, a computing device of an athlete training system may intelligently translateinformation from an athlete’s profile into or more manners of communicating with optimal efficiency and effectiveness. For instance, an athlete’s weight and derived difference from an ideal athletic motion for one or more athletic tasks may prompt a computing device to prescribe a certain feedback manner, such as audible prompts, while other profile information may prompt the computing device to prescribe a combination of manners, such as visual, augmented reality, and haptic prompts, to indicate how the athlete is performing and what actions are being requested.

[0055] A feedback manner prescribed in step 514 may communicate any volume and type of information to an athlete via one or more devices, such as a monitor, screen, speaker, or haptic component, that are stationary away from an athlete or worn by an athlete. By basing the decision on how training information is to be communicated to an athlete on information in the athlete’s profile, which is relatively specific to the athlete, the feedback manner has a greater chance of optimizing training time by efficiently identifying how an athlete is performing and what training actions are being requested. Hence, the computing system in step 514 provides an intelligently selected feedback manner in an effort to minimize confusion and delay of understanding and implementing training feedback information.

[0056] Some embodiments of step 514 generates a schedule of different feedback manners, or combinations of different manners, along with triggering events. For example, step 514 may prescribe a first type of visual feedback for a set time or until the athlete reaches a milestone or performance consistency that triggers the transition, or addition, of audible feedback. The ability to prescribe a feedback schedule and triggering events allows the computing device of an athlete training system to provide robust communication customized to an athlete without expending superfluous processing time and energy.

[0057] It is contemplated that routine 500 may cyclically perform steps 510-514 to sense athletic activity and prescribe feedback manners directed to efficient and effective communication with the athlete based on an understanding of the athlete derived from the athlete’s compiled profile. However, various embodiments may selectively test the effectiveness of a feedback manner in step 516. While not limited to a particular manner of testing the effectiveness or efficiency of a manner of training, various embodiments test amanner of feedback by measuring, with or more sensors, any number of athlete behaviors, such as facial expressions, reaction time, and / or change in task performance.

[0058] Decision 518 evaluates the results of the assorted feedback manner tests of step 516 to determine if a current, or future, change in feedback manners. If so, the intelligent selection of a feedback manner, or schedule of different manners, in step 514 is revisited. A determination that the presently prescribed feedback manner(s) provide efficient and effective communication to the athlete being trained prompts step 520 to incorporate the results of the feedback manner tests from step 516 into the athlete’s profile to provide a more robust and comprehensive indication of the athlete.

[0059] FIG.6 is a flowchart of an example potential routine 600 that may be performed by portions of an athlete training system to provide intelligent training tasks directed at optimal improvement of athletic skills in a given training time. In much a similar procedure as routine 500, the potential routine 600 may establish a reasonably accurate athlete profile through the evaluation of existing athlete profiles in steps 602, 604 and 606 or begin populating a template profile in step 608.

[0060] Any number, and type, of attributes may be sensed individually, or collectively, as an athlete performs static activities, such as a yoga pose or stretch, and / or dynamic activities, such as running or jumping. It is contemplated that a warm-up procedure is prescribed to the athlete by an athlete training system in response to the presence, or absence, of an athlete profile specific to the athlete being training. That is, an athlete may be directed to perform minimal warm-up activities before training begins if an existing profile is deemed accurate in step 606 while populating a template or inaccurate profile in step 608 may correspond with greater numbers, and different types, of warm-up activities to allow the various system sensors to efficiently populate, or verify, a profile.

[0061] Although not required, a currently accurate athlete profile allows a computing device of the athlete training system to derive, with a potential module in step 610, the skill level of the athlete. It is noted that the skill level of an athlete may correspond with proficiency in one or more athletic tasks. For instance, profile attributes, such as height, experience performing an athletic task, and intelligence, may contribute to an efficient, and accurate, determination of an athlete’s skill level for performing multiple athletic tasks,such as jumping, shooting a ball, hitting a or catching a ball. A skill level is not limited to a particular description of an athlete, but may be characterized as an ability to perform certain tasks individually and / or collectively to engage in an athletic activity. For example, a skill level generated in step 610 may describe an athlete’s consistency of posture, consistency of timing, relative alignment, stamina, decision latency, response latency, applied force vector, and arm angle.

[0062] The derivation of one or more skill levels in step 610 may correspond with the training system sensing how an athlete participates in one or more athletic tasks that may, or may not, be directly involved in performing a sport. In some embodiments, an athlete’s profile provides information describing an athlete that increases the accuracy of skill level derivation for performing one or more athletic tasks in step 610. Other embodiments determine an athlete’s skill level in step 610 without utilizing information of an athlete’s profile, which may expedite warm-up activities and generation of training drills.

[0063] Regardless of whether profile information is employed to generate an athlete’s skill level in step 610, the intelligent determination of an athlete’s skill level may increase the accuracy and speed of calculating an athlete’s athletic potential in step 612. The athletic potential determined in step 612 may correspond with the maximum performance possible with an athlete. Such maximum performance may correlate to a sport, such as shooting accuracy percentage, driving distance, throwing speed, ball spin rate, or lap times. It is noted that athletic potential from step 612 may also correlate to maximum performance in certain tasks, such as jumping height, acceleration, posture consistency, or applied force.

[0064] Hence, the determination of athletic potential in step 612 may differ from the skill level derived in step 610 by current proficiency compared to possible future proficiency in performing one or more athletic tasks. The combined determination of current athletic proficiency (skill level) and future, possible proficiency (potential) allows a computing device, and specifically a potential module, to generate training drills and exercises that have the best chance of increasing the skill level of an athlete as quickly and permanently as possible. As a non-limiting example, a training drill directed to increasing posture consistency may be ignored or altered by a computing device in response to a determination in steps 610 and 612 that an athlete is close to a posture consistencymaximum potential, which allows the system to prescribe training drills directed at athletic tasks that are farther from an athlete’s maximum potential.

[0065] The determination of an athlete’s skill level and potential in routine 600 may be conducted once before a training session or continually over time by cycling through steps 606, 610, and 612. However, it is contemplated that routine 600 tests one or more determinations about an athlete at any time. Decision 614 evaluates if a skill level or athletic potential is to be tested. A determination in decision 614 that a skill level generated from step 610 and / or an athletic potential generated in step 612 is to be verified prompts step 616 to generate one or more activities that allow the training system sensors to detect characteristics that confirm, or negate, a skill level or athletic potential in step 618.

[0066] As a result of decision 614, an athlete training system may identify physiological deviations from one or more models. The correlation of an athlete’s profile to a model athletic activity may customize the comparison of an athlete’s performance, behavior, and / or potential to the athlete’s body, injury history, stamina, or intelligence. A determination from decision 614 that no testing or verification of the determinations of steps 610 or 612 allows routine 600 to proceed to utilize the computed skill level and / or athletic potential in generating a training strategy in step 620.

[0067] Through the intelligent determination of an athlete’s current skill level and maximum athletic potential in routine 600, greater training efficiency may be experienced as training dills and milestones that trigger changes in a training session may be optimally selected with respect to the actual athlete being trained. In contrast, a training session that does not consider an athlete’s current capabilities and possible maximum athletic potential may result in training drills, and progression of drills, that are inefficient and / or ineffective at creating permanent improvement in athletic performance. Yet, embodiments of an athlete training system may intelligently choose, and adapt, training drills without a verified athlete potential or skill level.

[0068] FIG.7 is a flowchart of an example drill routine 700 that may be performed by a computing device, and particularly a training module, in accordance with assorted embodiments to provide intelligent, efficient, and effective training of athletic activities. Initially, the routine 700 can evaluate, in decision 702, whether the athlete being trained hasa known profile. It is contemplated 702 may evaluate, alternatively or additionally, if the athlete being trained has a known skill level. In the event the athlete being trained has a known profile and / or skill level, decision 704 evaluates if the attributes are to be verified.

[0069] If verification is called for, the athlete training system may proceed to step 706 where circuitry of the athlete training system, such as the training module 330, generates one or more training tasks to test aspects of the stored profile and / or skill level. As a result of detecting assorted aspects of an athlete preparing, conducting, and completing one or more assigned tasks, such as stretching, moving, or hitting a ball, the athlete training system may determine that a temporary, or permanent, change to an existing athlete profile or skill level is needed to accurately describe the athlete’s current athletic capabilities. For instance, a series of running, jumping, and movement exercises can be assigned in step 706 to determine if an injury, or other temporary physical impairment, is present that could degrade an athlete’s physical capabilities, which may aid in prescribing optimal training drills to provide effective and efficient improvements in one or more athletic activities.

[0070] If no verification is called for in decision 704, or at the conclusion of the testing of an athlete in step 706, step 708 populates a current physical profile for the athlete being trained. Such population in step 708 may involve copying, replacing, and / or updating aspects of an existing profile, or template, to accurately represent the athlete and allow a training module to prescribe drills and exercises that have the best chance to result in improvement of an athlete towards model athletic behavior.

[0071] Returning to decision 702, a determination that a profile is not present may prompt step 710 to assign a warm-up schedule of athletic activities that are monitored to provide a computing device with ample data to populate a template profile in step 712. The use of sensed athlete behaviors to modify a template profile in step 712 provides specificity about an athlete’s physical capabilities, which allows for a more accurate determination, in step 714, of an athlete’s difference from one or more ideal athletic models. Indeed, the use of a known profile and / or skill level from step 708 also allows for an intelligent determination of how much improvement is needed to reach ideal model behaviors or the maximum physical capabilities of the athlete.

[0072] As a non-limiting example of electronic activity conducted by one or more circuits of a computing device connected to athlete sensors in step 712, an athlete’s computed athletic potential and physical capabilities are compared to a current proficiency in conducting physical tasks, which can be characterized as skill level. Another non- limiting example of step 712 may compare an existing athlete profile attribute, such as hand position while engaging a club, bat, or ball, with an ideal model while other athlete behaviors, such as reaction time, strength, or posture, are compared to a computed athlete physical potential to determine how much physical change is needed for the athlete to perform ideally or to the athlete’s maximum potential.

[0073] The intelligent computation of an athlete’s room to improve in step 712 provides information that indicates what training drills, tasks, and exercises have the best chance of improving an athlete’s athletic performance in regard to consistency, accuracy, speed, and strength. Step 716 takes the information pertaining to an athlete’s performance separation from ideal athletic behavior, and / or an athlete’s maximum capabilities, to assign one or more athletic tasks, drills, exercises, and actions to reduce the computed difference from the ideal, or maximum potential. More specifically, a computing device of an athlete training system, in step 716 selects from a preexisting list, and / or generates a new, activity that is directed at bringing the athlete’s athletic behavior closer to the ideal model and the maximum athletic potential of the athlete.

[0074] Next, decision 718 evaluates if multiple athletic drills are to be conducted sequentially or if the performance of a single assigned drill is to be sensed and used to assign the next drill of a training session. That is, decision 718 may be conducted by a training module, or other circuitry of a computing device, to determine if a series of drills provide efficient training of the athlete or if drills are to be assigned in response to how an athlete performs in a single assigned drill. If a progression is to be assigned from decision 718, the routine 700 returns to step 716 at least once to generate, or select, additional athletic drills directed to advance an athlete’s performance.

[0075] Once decision 718 concludes that no additional drills are to be assigned, step 720 issues the assigned drill(s) to the athlete in an intelligent manner dictated by a feedback module of the system computing device. In other words, whatever drill, exercise, action, ortask that is prescribed from step 716 is to the athlete in a feedback manner that is intelligently selected to efficiently convey the training information, such as what drill to perform, how to perform a drill, ideal drill execution timing, or the physical status of the athlete during activity.

[0076] As the assigned drill(s) are performed by an athlete, step 722 senses the athlete’s behavior and provides data to a system computing device that allows decision 724 to determine if a training milestone has been reached. That is, one or more system sensors may collect information as an athlete perform one or more assigned drills to allow for the determination whether the athlete has reached a training milestone corresponding with the athlete’s profile, computed physical capabilities, and / or derived skill level. The achievement of a milestone, either explicitly or computationally with sensed behavioral results, may trigger a computing system, in step 726, to advance to a different training focus, objective, training speed, or feedback manner.

[0077] For instance, step 726 may involve reacting to hitting a ball a predetermined distance, reaching a predetermined accuracy consistency for a given timeframe, or properly altering an incorrect body position a predetermined number of times by updating the athlete’s profile and skill level before advancing to a different athletic skill, a faster training pace, or greater precision of required athlete movements. As such, the identification, or speculation, that an athlete has reached a milestone can optimize training efficiency by progressing how skills, tasks, and positions are taught and reinforced as the athlete develops. The use of sensed athlete behaviors and activity to determine if a milestone is reached, along with basing assigned milestones on the athlete’s computed athletic potential, further ensures that training drills are optimized to the athlete and has the best chance of increasing proficiency towards maximum athletic potential and / or an ideal athletic model behaviors.

[0078] Through the assorted embodiments of an athlete training system, an athlete’s activity may be interpreted in real-time into a training program intelligently directed to improving one or more static positions and / or dynamic actions with feedback optimized to provide efficient understanding and replication. As a result, an athlete may conductactivities at will and receive instructions improvement in at least one medium that provides easy implementation and accurate replication.

[0079] It is to be understood that even though numerous characteristics and advantages of various embodiments of the present disclosure have been set forth in the foregoing description, this description is illustrative only, and changes may be made in detail, especially in matters of structure and arrangements of parts within the principles of the present disclosure to the full extent indicated by the broad general meaning of the terms wherein the appended claims are expressed.

Claims

What is claimed is:

1. A method comprising: connecting a computing device to an array of sensors, the array of sensors positioned proximal an athlete; generating a feedback strategy with a feedback module of the computing device, the feedback strategy selecting at least one manner of communicating training information to the athlete from a plurality of different available manners of communicating training information; computing an athletic potential of the athlete with a potential module of the computing device in response to sensed athletic behavior of the athlete detected by the array of sensors; estimating, with the potential module, a current skill level of the athlete in response to sensed athletic behavior of the athlete detected by the array of sensors; determining, with a training module of the computing device, a difference between the athletic potential of the athlete and the current skill level; assigning a first training drill with the training module, the first training drill selected by the training module to increase a proficiency in at least one athletic task associated with the current skill level; and altering the first training drill to a second training drill in response to an increase in proficiency of the at least one athletic task detected by the array of sensors.

2. The method of claim 1, wherein the array of sensors is worn by the athlete.

3. The method of claim 1, wherein the array of sensors comprises at least one stationary sensor and at least one sensor positioned on the athlete.

4. The method of claim 1, wherein the plurality of different available manners of communicating training information comprises audible, visual, and haptic cues.

5. The method of claim 4, wherein the feedback module selects multiple manners of concurrently communicating training information to the athlete.

6. The method of claim 5, the multiple manners of communicating training information differently convey training information selected by the training module.

7. The method of claim 1, wherein the athletic potential corresponds with a maximum physical capability of the athlete estimated from input from the array of sensors.

8. The method of claim 7, wherein the maximum physical capability of the athlete corresponds with an ability to repetitively perform athletic behaviors with a predetermined operational characteristics.

9. The method of claim 8, wherein the maximum physical capability of the athlete corresponds with an ability to repetitively perform athletic behaviors within a range of physical positions defined by the computing device.

10. The method of claim 7, wherein the maximum physical capability of the athlete is unique to the athlete and corresponds with at least one unique physical trait detected by the array of sensors.

11. The method of claim 1, wherein the increase in proficiency of the at least one athletic task corresponds with the athlete performing athletic behavior corresponding with a milestone generated by the training module.

12. The method of claim 1, wherein the first training drill is selected to decrease the difference between the athletic potential of the athlete and the current skill level of the athlete.

13. The method of claim 1, wherein the first training drill is altered in response to a change in current skill level of the athlete computed by the computing device.

14. The method of claim 1, wherein the second training drill is assigned by the training module in response to a determination by the computing device that the first training drill is not increasing proficiency in the at least one athletic task.

15. The method of claim 1, the at least one athletic task is shooting a basketball.

16. An athlete training system comprising: a computing device; an array of sensors connected to the computing device; wherein the computing device comprises a processor and memory; wherein the computing device has circuitry structurally configured as a feedback module, a potential module, and a training module; wherein the feedback module is operable to generate a feedback strategy that selects at least one manner of communicating training information to the athlete from a plurality of different available manners of communicating training information; wherein the potential module is operable to compute an athletic potential of the athlete in response to athletic behavior of the athlete detected by the array of sensors; wherein the potential module is operable to estimate a current skill level of the athlete in response to athletic behavior of the athlete detected by the array of sensors; wherein the training module is operable to determine a difference between the athletic potential of the athlete and the current skill level; wherein the training module is operable to assign a first training drill to increase a proficiency in at least one athletic task associated with the current skill level; and wherein the training module is operable to alter the first training drill to a second training drill in response to an increase in proficiency of the at least one athletic task detected by the array of sensors.

17. The athlete training system of claim 16, wherein each sensor of the array of sensors is worn by the athlete.

18. The athlete training system claim 16, wherein at least one sensor of the array of sensors is physically separated from the athlete.

19. The athlete training system of claim 16, wherein the computing device is worn by the athlete.

20. The athlete training system of claim 16, wherein the computing device is connected to the array of sensors via at least one wireless signal pathway.