rgarreta
I've tried several approaches to address the issue, including:
Adjusting lighting.
Tweaking latency configurations.
Enabling/disabling image processing from the mirrors.
I still haven’t been able to solve it.
My intuition is that the problem might be one of the following:
Model overfitting to the training cups. The exact list of cups used in training isn’t published. After reviewing the dataset, I see a red cup/saucer set, but I suspect its relative size is different from mine, so the model may be incorrectly estimating the right moment to release the cup.
The model might need fine-tuning with episodes recorded in my own environment using my specific cup/saucer set.
My gripper might lack the precision the original system had.
Residual jitter in the arm or gripper could also be contributing.
Other thoughts:
Depth estimation may be a bottleneck. Adding a depth camera or a secondary camera for stereo vision might help, but would likely require retraining the model from scratch.
Adding contact information could also improve performance, either via touch sensors or by borrowing ideas from ManiWAV (https://mani-wav.github.io/ ), which uses a microphone mounted on the finger.
If anyone has been more successful with this setup, I’d love to exchange notes.
Reproducing UMI with a UR5 Robot Arm and a 3D-Printed Gripper
Automatically Tag Conversations in Front Using Machine Learning
Another new major feature are our custom extractors, you can train a sequential machine learning model for text extraction. In simple words I would describe it as training a regular expression to extract data from text :)
We've been trying different sequential learning models like Conditional Random Fields and Recurrent Neural Networks.
Feedback is much appreciated!
Show HN: MonkeyLearn 3.0, custom extractors, active learning, new API and more
Monitor your Segment events through Datadog
https://monkeylearn.com/blog/how-to-create-text-classifiers-...