Scratch for Sports: Athletic Drills as a Platform for Experiencing, Understanding, and Developing AI-Driven Apps
In this episode I unpack Kumar and Worsley’s (2023) publication titled “Scratch for sports: Athletic drills as a platform for experiencing, understanding, and developing AI-driven apps,” which summarizes explorations of the intersections of computer science and physical education.
-
Quote culturally relevant and sustaining
implementations of computing education
are increasingly leveraging young
learners's passion for sports as a
platform for building interest in
different STEM Science technology
engineering and math concepts numerous
disciplines spanning physics engineering
data science and especially artificial
intelligence AI based Computing are not
only authentically used in professional
sports in today's world but can also be
productively introduced to introduce
Young Learners to these disciplines and
facilitate deep engagement with the same
in the context of sports in this work we
present a curriculum that includes a
constellation of proprietary apps and
tools that we show to student athletes
learning sports like basketball and
soccer which use AI methods like pose
detection and imu-based gesture
detection to track activity and provide
feedback we also share scratch
extensions which enable Rich access to
sports related pose object and gesture
detection algorithms that youth can then
Tinker around with and develop their own
sports drill Apple applications
represent early findings from Pilot
implementations of portions of these
tools and curricula which also Foster
discussion relating to the failings risk
and social harms associated with many of
these different AI methods noticeable in
professional sports context and relevant
to youths lives as active users of AI
Technologies as well as potential future
creators of the same end quote that is
the abstract for the paper which is
titled scratch for sports colon
authentic drills as a platform for
experiencing understanding and
developing AI driven apps this was
written by vishesh Kumar and Marcela
warsley apologies if I mispronounce any
names but how to summarize this paper
into a single sentence that say that
this paper summarizes explorations of
the intersections of computer science
and physical education which is not
discussed enough and which is why I
wanted to bring this up in this
unpacking scholarship episode there are
nearly 200 more episodes that are like
this as well as some interviews and some
professional development discussions you
can find that at jaredoleery.com in the
introduction of this paper the authors
talk about how interdisciplinary areas
can be very motivating for students
because they're able to combine some
interest in multiple subject areas in a
way that is individually meaningful for
them for example many students are
really interested in sports or physical
education as well as in Computing if you
can combine the two in a meaningful way
this might be very motivating for
students in addition there's been some
scholarship that has explored a concept
known as embodied cognition or as paper
might describe it body sentinicity which
is like learning kinesthetically and
learning through movement motion Etc
students are able to explore and embody
different Computing and physical
education Concepts through Sport and the
exploration of sport through technology
and Computing that is assisted by
artificial intelligence if you're
interested in learning more about the
intersections of computing and AI
education or the intersections of AI
education in sports There's a summary on
that on page sixteen thousand and twelve
so check it out if you're interested in
that and the authors mentioned that
there are many ways that you can explore
these intersections of computing and
Sports in contexts like PE and Library
classes or programming at the park
sessions community centers pop-ups
through like summer camps or in like a
computer science class so throw
throughout the paper the authors
mentioned here's where you might be able
to explore this type of project or this
type of idea in different contexts which
is important to consider especially when
you are doing some kind of a physical
activity that requires larger space or
like larger ceilings Etc which you'll
find out why in a moment on page 16 2013
the authors talk about a video sensing
app called home court and scratch so the
first section that I talk about is on
video sensing so this is like on home
court in scratch which is a project that
allows students to kind of explore
through the iPad how you might be able
to use like body tracking movement in AI
to kind of explore different drills for
like moving a basketball or like even
kicking a soccer ball Etc to be able to
figure out how to practice your
dribbling or practice your shots Etc
through the use of like AI assisted
technology to be able to look at your
patterns and figure out areas that you
might be able to improve these types of
apps are frequently used by individuals
in their Leisure or for professional
sports or entire teams and are becoming
increasingly more popular like think of
like the rocky scenario where we have
like Rocky who's training old school
method in the cold just running doing
pull-ups push-ups Etc and then we have
the fighter who's got the scientist all
around him who's hooked up the machines
and checking heart rate Etc that's where
we're increasingly heading with sports
education and whatnot and sports
training for especially the professional
area not just like Leisure and whatnot
but trying to find that one percent
incremental advantage over somebody else
over an extended period of time really
can add up so AI assisted tools that are
able to analyze your motion and find
more efficient ways of moving or better
patterns for dribbling Etc can help you
get that one percent Edge over other
people so students will explore this
kind of an app like on their iPad and
then engage in a discussion on how it
might help them or talking about like
the motivation that can come with local
and Global leaderboards in apps like
this and then the students explore a
like a watered-down version of how you
might be able to create something
similar in scratch using some extensions
that they developed which this is
fascinating to see that like this is
where we are headed with scratch
thinking about where scratch was even I
don't know five years ago I can't wait
to see what kind of tools and whatnot
are going to be implemented in scratch
way but the authors mentioned that
students are not only exploring like the
applications of an app but they're also
then learning how might you create
something similar Brandon it's going to
be a watered down version of this but
allows you to explore and kind of
simulate the thought processes and
design thinking that is involved in
creating something similar which I think
is very helpful for students here's a
quote from page 16
in discussing the ability of video based
AI systems in helping Sports practice
which often also opens the door to
discussing the usage of similar systems
in their surroundings seen on face
identifying systems on smartphones and
home security systems and the underlying
ethics of regarding data access and
surveillance enabled these systems end
quote which is a really important thing
to consider now the next set of projects
that the authors kind of describe in
here is on wearables so this is on smart
watches and microbes so in this space
the authors recommend having some kind
of an open space like a track or like a
gym or whatever so they have the
students take like a lap around the
space and then kind of guess how many
steps did that take for you to get
around that lap and then that leads to a
discussion on like how would you be able
to get a more precise answer with that
very quickly so that can lead to
discussions about like wearables like
smart watches Etc which will kind of
like keep track of how many steps you're
taking and then the authors recommend
like okay you could have a discussion
where you compare what was your estimate
versus what actually happened and then
have students create their own step
counters using something like a micro
bit and then you can have a discussion
about the three different approaches how
did the micro bit compare from the
Smartwatch compare from my initial
estimate without technology what about a
discussion around the false positives
that can come with micro bits because
they're not going to be as accurate as a
device that is like a few hundred
dollars for context micro bits are very
affordable relatively speaking very
cheap especially for the amount of like
features you get out of it I highly
recommend them so in this discussion the
authors are also recommending students
to try and main trick basically like to
be able to get your steps in like I can
sit here and like move my arms around
and the steps counter is going up but
I'm just still sitting in my chair not
actually stepping same thing with the
micro bit you can kind of trick the
system to have some false positives the
authors then kind of unpack a little
activity that you can do with like
pattern detection algorithms being able
to detect different like patterns with
movements so like for example if you're
boxing those different types of punches
that you can do whether you're gonna do
like a jab a cross a hook etc those are
all very different types of movements a
pair you might get registered as a punch
even though it's just a Parry so if
you're interested in learning more about
that pattern detection algorithms check
out page 1614 but the last section that
the authors talk about is ball sensors
so this is on play impossible in siq and
the micro bits so play impossible is
like a game and so like one of the games
that it talks about is like how high can
you throw a ball or like how fast can
you shake a ball in a given amount of
time and kind of like talks about these
in some different contests that you can
do with different groups or classes Etc
now obviously if you're gonna throw a
ball that really high or as high as
possible you want to make sure you're in
a space where you don't have a ceiling
because students might surprise you at
how high they can throw a ball even if
you're in a like a large gym or whatever
it might hit the ceiling or get stuck in
a light or whatever just look up next
time you're in the gym and you just
might see a ball that is stuck in the
roof these types of games can also be
replicated or reproduced using a micro
bit whether you're doing like scratch or
doing something like make code or
whatever so the authors talk about how
you can use these different gesture
types of detections to create some
different projects and whatnot in your
classes in the discussion of future work
the authors talk about how this is kind
of like the beginning of some potential
applications and explorations of the
intersections of computing and physical
education or Sports if you have ideas on
how you've explored these intersections
in your classes please feel free to
share them in the comments on YouTube or
on any of the social media platforms
that I'm on which you can quickly just
find on jaredelary.com under the socials
tab but as always with these unpacking
scholarship episodes I want to share
some of my lingering questions or
thoughts so one of them is how do we
incorporate physical Computing in an
individualized or rhizomatic way there's
a big difference between general
interest and individual interests among
kids so kids might generally be
interested in video games and generally
interested in anime or sports but not
every student is going to be interested
in video games anime and sports and like
even within those different categories
there's going to be some students who
are interested in some areas and not
others I love some animes and don't
really have an interest in others I love
some video games and not interested
others same thing with sports I'll do a
Muay Thai any day but I'm not gonna go
join a football team so there's a
tendency that some curriculum developers
have when they're creating some lessons
where they essentialize that because
generally speaking kids are interested
in things then all kids will be
interested in this very specific thing
within that category and that is just
simply not true so we as Educators need
to think about not just the general
areas that students are interested in
but how they might explore the specifics
within that general area in an
individualized way we talk about that in
some of the rhizomatic learning episodes
which I will link to in the show notes
so you can explore more about that
concept so I won't rant about that here
and the next question I have is when do
you use physical Computing in your
classroom whether it's like an unplugged
or like using a device like a micro bit
to be able to create some kind of like a
sports game or whatever when do you use
it do you use it to introduce a concept
to reinforce a concept or is this like a
separate unit or activity or do you not
engage with it at all if you do engage
with physical Computing how do you
prevent the novelty from wearing off I
often see kids who get very interested
in some kind of a physical device and if
it does not have like a low floors High
ceilings and wide walls like a micro bit
might have then students eventually get
bored with it with some kind of even if
students are like super excited about
this like robot or whatever you give it
a week or two of them using it and
they'll be like yeah this isn't as
interesting as being able to like code
something in scratch which has low
floors High ceilings wide walls which
means that there's a low barrier of
Entry there's a high ceiling for
complexity that can be explored and
there's a wide range of projects or
activities or whatever that can be
created through that particular platform
or device Etc to reiterate this I have
speaking with some like heads of
computer science in districts across the
country and many of them have said yeah
we bought this particular robot or
device or tool for physical Computing it
was interesting students may have used
it for a week maybe for a month and then
it just sits on the shelf and collects
dust for the rest of the year if you
think those experiences are so valuable
that it's worth that initial investment
costs which generally speaking is very
high you'll get classroom sets or
District sets Etc and you think that's
worthwhile great but if you are not
aware of that phenomenon and you have
not experienced buying devices only to
see it being put on the Shelf after a
month maybe experiment with a small
subset of devices and see how that goes
instead of buying a bunch of different
devices or one approach that you could
do is like if this is really interesting
for like two weeks get like a school set
that can be used by a classroom educator
and then rotate over to another school
like for the remaining weeks and just
keep doing that throughout the year so
then eventually it'll come back and
it'll be novel again because students
aren't working on it every single day
but those are just my experiences and
opinions you enjoyed this episode or any
of the nearly 200 episodes that are
available on my website at
jaredeliry.com please consider sharing
with somebody else stay tuned for an
episode next week until then I hope
you're all staying safe and are having a
wonderful week
Article
Kumar, V., & Worsley, M. (2023). Scratch for Sports: Athletic Drills as a Platform for Experiencing, Understanding, and Developing AI-Driven Apps. In Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16011-16016.
Abstract
“Culturally relevant and sustaining implementations of computing education are increasingly leveraging young learners' passion for sports as a platform for building interest in different STEM (Science, Technology, Engineering, and Math) concepts. Numerous disciplines spanning physics, engineering, data science, and especially Artificial Intelligence (AI) based computing are not only authentically used in professional sports in today's world but can also be productively introduced to introduce young learners to these disciplines and facilitate deep engagement with the same in the context of sports. In this work, we present a curriculum that includes a constellation of proprietary apps and tools that we show to student athletes learning sports like basketball and soccer which use AI methods like pose detection and IMU-based gesture detection to track activity and provide feedback. We also share Scratch extensions which enable rich access to sports related pose, object, and gesture detection algorithms that youth can then tinker around with and develop their own sports drill applications. We present early findings from pilot implementations of portions of these tools and curricula, which also fostered discussion relating to the failings, risks, and social harms associated with many of these different AI methods – noticeable in professional sports contexts, and relevant to youths' lives as active users of AI technologies as well as potential future creators of the same.”
Author Keywords
Sports, Physical Computing, Gesture Detection, K-12 Education, Object Detection, Scratch, Soccer, Basketball
My One Sentence Summary
This paper summarizes explorations of the intersections of computer science and physical education.
Some Of My Lingering Questions/Thoughts
How do we incorporate physical computing in an individualized or rhizomatic way?
When do you use physical computing in your classroom?
If you use engage with physical computing, how do you prevent the novelty from wearing off?
Resources/Links Relevant to This Episode
Other podcast episodes that were mentioned or are relevant to this episode
Fostering Intersectional Identities through Rhizomatic Learning
In this episode, Jon Stapleton and I read our (2022) publication titled “Fostering intersectional identities through rhizomatic learning,” which uses mapping as a metaphor for individualized learning.
How to Get Started with Computer Science Education
In this episode I provide a framework for how districts and educators can get started with computer science education for free.
micro:bit, Rhizomatic Learning, and CS for Healing with Katie Henry
In this interview with Katie Henry, we discuss the micro:bit and the do your :bit challenge, rhizomatic learning, the potential for CS for healing, and much more.
Performing Algorithms: Weaving as Promising Context for Computational Learning
In this episode I unpack Keune’s (2022) publication titled “Performing algorithms: Weaving as promising context for computational learning,” which explores weaving as a potential practice for exploring computer science concepts.
Project moveSMART: When Physical Education Meets Computational Thinking in Elementary Classrooms
In this episode I unpack Fritz et al.’s (2021) publication titled “Project moveSMART: When physical education meets computational thinking in elementary classrooms,” which summarizes pilot study findings and activities that integrate CS/CT with physical education through a micro:bit.
Rhizomatic Learning with Catherine Bornhorst, Jon Stapleton, and Katie Henry
In this panel discussion with Catherine Bornhorst, Jon Stapleton, and Katie Henry, we discuss what rhizomatic learning is and looks like in formalized educational spaces, affordances and constraints of rhizomatic learning, how to support individual students within a group setting, standards and rhizomatic learning, why few people know and use rhizomatic learning approaches, how to advocate for and learn more about rhizomatic learning, and much more.
Robotics and Physical Computing with Brenda Bass
In this interview with Brenda Bass, we discuss advice for educators interested in getting started with robotics or physical computing, considering equity and access with robots and physical computing devices, how to learn more about robotics and CS without a background in either area, and much more.
The Centrality of Curriculum and the Function of Standards: The Curriculum is a Mind-altering Device
In this episode I unpack Eisner’s (2002) publication titled “The centrality of curriculum and the function of standards: The curriculum is a mind-altering device,” which problematizes curricula and standards by discussing how both can deprofessionalize the field of education.
In this episode I unpack Bresler’s (1995) publication titled “The subservient, co-equal, affective, and social integration styles and their implications for the arts,” which “examines the different manifestations of arts integration in the operational, day-to-day curriculum in ordinary schools, focusing on the how, the what, and the toward what” (p. 33).
Find other CS educators and resources by using the #CSK8 hashtag on Twitter
Free CS Resources I Have Created
More Content
