KiCad Version 10.0.5 Released
The KiCad project is proud to announce the latest version 10 bug fix release. See the blog post on the KiCad website for more information about this release.
https://t.co/WFK6YIzrU1
Sharpa Robotics @SharpaRobotics observed that teleoperating a dual hand robot offering a combined 63 DoF is a nightmare, even for an experienced operator.
They offer a two fold solution:
- a VLA that handles "in hand rotation" (like the apple in video below), that the operator can trigger using a foot pedal.
- a Mixture-of-Dexterous-Experts that fuses tactile sensing data.
Interestingly enough, the first model handles the apple peeling end-to-end, tactile data does not help here.
However, it greatly enhances the insertion and grasping of the apple.
This research makes use of the SharpaWave 22-DoF dexterous hand, with force and tactile feedback on all ten fingertips.
I find it interesting that is now possible to delegate complex low-level finger coordination tasks to RL-trained atomic skills.
Optimizing such steps that are difficult to reproduce in teleoperation significantly helps overcoming the data acquisition bottleneck.
The encoder module is open source too.
One module packs a 15-bit magnetic encoder, bearing, hardware limit, and driver together.
Design frames to match your robot's joints and you've got a leader arm for it. Bearings are already inside, so all you need is the frames.
We are excited to announce the release of a new OpenArm teleoperation device: KER (Kinematic Equivalent Replica). This is a lightweight leader device that shares the exact same joint structure as OpenArm 2.0.
KER uses only encoders for each joint, no motors, allowing for smooth and easy operation with zero resistance. Every joint maps 1:1 to OpenArm 2.0, so no coordinate transforms are needed.
This release marks the completion of the OpenArm 2.0 ecosystem. KER, OpenArm, and the Cell are all open source and are ready to be used in state-of-the-art reproducible research! 🦾
#OpenArm #OpenSource #Robotics
Keeping human at the center is what allows us to cut through the noise.
Unlike many previous works, UME is designed for humans — not the robot.
Over the past few days, I’ve received a lot of great feedback on our hardware design. Truly appreciate all of it! I wanted to clarify a core philosophy behind our choices:
Our hardware design is human-centered, the only goal is to maximize human comfort and recover the full range of motion of the human arm.
Why? Because data quality and efficiency matters. When a user struggles to hold an awkward end-effector or faces joint limits, his time is wasted for nothing, and the data goes into trash.
This is exactly the reason we committed to our hardware software combination of Coaxial Configuration and Universal Retargeting.
Inspired by @StanfordHAI@Stanford