1 5 112

Jack Vial PRO

jackvial

AI & ML interests

Embodied AI, Robotics, Reinforcement Learning

Recent Activity

commented on an article 21 days ago

You could have designed state of the art positional encoding

reacted to branikita's post with 🚀 about 1 month ago

With https://huggingface.co/Robonine team we recently verified the rotational speed of the Feetech STS3250 servo motor (12 V, 50 kg·cm torque, magnetic encoder) to compare measured performance with the official specification. According to the datasheet: - Rated speed: 0.133 s per 60° Calculation: - 0.133 s × 6 = 0.798 s per full rotation - 1 / 0.798 = 1.253 revolutions per second - 1.253 × 60 = 75.2 RPM This confirms the official specification of approximately 75 RPM at 12 V under no load. Our measurement: - Encoder output: 5,300 values per second - Encoder resolution: 4,096 counts per revolution Calculation: - Revolutions per second = 5,300 ÷ 4,096 = 1.294 rev/s - RPM = 1.294 × 60 = 77.6 RPM Result: The measured value differs by only about 2–3% from the datasheet specification, confirming that the STS3250 performs very close to its rated no-load speed. This close agreement validates both the servo’s performance and our measurement approach. Video: https://youtube.com/shorts/_O_mVZvYQlQ?feature=share #servo #robotics #automation #motioncontrol #mechatronics #Feetech #STS3250 #engineering #datasheet #precision #hardwaretesting #roboticsengineering

liked a dataset about 1 month ago

lerobot/droid_1.0.1

View all activity

Organizations

None yet

commented on You could have designed state of the art positional encoding 21 days ago

Fantastic post!

An important bit of context for those not familiar with signal processing/Fourier analysis concepts is that Euler's formula relates the complex exponential to sine and cosine: e^ix = cos(x) + i sin(x), and e^ix allows you to think about rotations in 2d dimensions on the complex plane.

The Taylor expansion of the complex exponential explains e^ix = cos(x) + i sin(x) and the alternating odd sine and even cosine in a bit more depth. Steven Brunton has an excellent walkthrough of the derivation here
https://www.youtube.com/watch?v=Rp-smPZLESc&list=PLMrJAkhIeNNQBRslPb7I0yTnES981R8Cg

reacted to branikita's post with 🚀 about 1 month ago

Post

2886

With

Robonine team we recently verified the rotational speed of the Feetech STS3250 servo motor (12 V, 50 kg·cm torque, magnetic encoder) to compare measured performance with the official specification.

According to the datasheet:
- Rated speed: 0.133 s per 60°

Calculation:
- 0.133 s × 6 = 0.798 s per full rotation
- 1 / 0.798 = 1.253 revolutions per second
- 1.253 × 60 = 75.2 RPM

This confirms the official specification of approximately 75 RPM at 12 V under no load.

Our measurement:
- Encoder output: 5,300 values per second
- Encoder resolution: 4,096 counts per revolution

Calculation:
- Revolutions per second = 5,300 ÷ 4,096 = 1.294 rev/s
- RPM = 1.294 × 60 = 77.6 RPM

Result:
The measured value differs by only about 2–3% from the datasheet specification, confirming that the STS3250 performs very close to its rated no-load speed. This close agreement validates both the servo’s performance and our measurement approach.

Video: https://youtube.com/shorts/_O_mVZvYQlQ?feature=share

#servo #robotics #automation #motioncontrol #mechatronics #Feetech #STS3250 #engineering #datasheet #precision #hardwaretesting #roboticsengineering