[NO-AI]

Being a weightlifter for 20+ years now, I'm working on a barbell speed and path tracking sensor based on newer IMU hardware technologies, which makes it both more precise and cheaper than camera- or actuator-based systems. Ultimately it helps you lift and train safer and better.

It's an intersection of industrial design, hardware, firmware, and software (and some sport science, of course). This intersection is not yet dominated by LLMs so it's a breath of fresh air.

In an early prototype stage as in "strap a Raspberry Pi to a bar", but it looks promising and I'm happy to move forward, also using connections from my previous 12+ years in China.

▲

utopiah 22 minutes ago | parent | next [-]

How about strapping the phone to the bar and opening a Web page with https://developer.mozilla.org/en-US/docs/Web/API/Acceleromet... ?

Seems it would have a much higher reach.

▲

era86 12 hours ago | parent | prev | next [-]

Wannabe powerlifter here of about 20 years as well. This sounds like an awesome project! Is bar-path the main metric for safety and "better" lifting? A project I had in mind, once upon a time, was an automatic "Form Check Friday" for myself using a Pi + Webcam.

▲

cleaning 7 hours ago | parent | next [-]

As someone who has been very deep down this rabbit hole and hacked together multiple path and velocity trackers over the years (specifically for olympic weightlifting), there is no extra information that tracking bar path will give you that simply looking at the video won't, and often just adds more clutter. You don't need to graph bar path to see that the bar is looping too far forward after hip contact in the snatch.

Velocity on the other hand is a great metric to track and is used as a proxy for RPE. Mike Tuchscherer was the first one to systematize it for powerlifting a while back, if you've been lifting for 20 years you're probably aware of the name.

▲

mstaoru 10 hours ago | parent | prev | next [-]

Thanks! I think for "canonical" lifts (squat, deadlift, row, to some extent military press) the vertical bar path is mathematically optimal, and for all kinds of lateral or sagittal movements you do more work with weak stabilizing muscles and load joints laterally too. Is it productive work that strengthens your core? Possibly, but it's hard to quantify. It it something that can lead to injury? Absolutely yes.

For more complicated lifts like bench press (J-shaped) or snatch (S-shaped), for example, I would rather set a "golden sample" path with a coach and compare to that.

It's unlikely to be the sole metric, especially given the inverse kinematics of different body types (long/short femur, etc), but together with bar speed, over time, it can provide a lot of good feedback.

	▲	cleaning 7 hours ago \| parent [-]
		It is not "absolutely" something that can lead to injury. Injury itself is difficult to define, and often the reason one experiences pain sensation is multifactorial. Within lifting contexts, generally the factor which has the strongest evidence for injury prediction is how sharply an athlete increases intensity compared to what they have previously adapted to. No offense, but this post does come across as you only having a surface level understanding of the field. Especially surrounding injury/pain perception, I would be more careful of what you assume is true, there's far more nuance.

▲

notesinthefield 11 hours ago | parent | prev [-]

Not OP but velocity is typically what these devices are used for. Its a great measure of between-set intensity.

▲

grepfru_it 8 hours ago | parent | prev | next [-]

Side note: My LG Watch Sport smartwatch was able to determine what weight training workout I was performing and somehow figured the weight with astonishing accuracy.

▲

a-dub 10 hours ago | parent | prev | next [-]

i'm curious about how effective path tracking can be in comparison with computer vision based inverse kinematics of the body itself. do all forms of bad form have detectable imu signatures?

i wonder if it would make sense to consider it as a data problem, capture a bunch of high fidelity inverse kinematics data for various forms of bad form/dangerous lifting along with the imu data and then work from there. there could be some interesting and unexpected features that are easier to detect than straying from straight line paths with some tolerance.

	▲	mstaoru an hour ago \| parent [-]
		For me it's a bit of an inverse problem. I go to a public gym (hard to sustain motivation at home) and I absolutely don't want to film myself there.

▲

sberens 7 hours ago | parent | prev | next [-]

Have you seen https://fort.cx?

▲

frankdenbow 12 hours ago | parent | prev | next [-]

this sounds awesome. have any videos of it?

	▲	mstaoru 10 hours ago \| parent [-]
		Thanks! Working on it, for now it's literally a taped breadboard. :D

▲

wrer 7 hours ago | parent | prev [-]

[dead]