Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Miniscope Zero, the first fully wireless Miniscope, is on bioRxiv! Wireless power + data enable neural recordings in enclosed mazes, 3D environments & from two animals at once! Dr. Marcel Brosch Miniscope Team Paper: Wiki:

23,293 Aufrufe • vor 14 Tagen •via X (Twitter)

6 Kommentare

Profilbild von Takuya SASATANI
Takuya SASATANIvor 14 Tagen

Team: T. Sasatani & M. Brosch @BroschMarcel (co-first) Z. Dong, J. Saunders @json_dirs, P. Zhao @PingpingION, M. Sehgal @MeghaSehgal_, L. Oesch, F.S. Jimka, H. Semwal, A. Guha, H. Chorsi, K. Keus @karina_keus, B. Madruga @BlakeMadruga, A. Silva, A.K. Churchland @anne_churchland, P. Golshani @pgolshani & D. Aharoni. @MiniscopeTeam

Profilbild von Isamu Amir
Isamu Amirvor 14 Tagen

@biorxivpreprint @BroschMarcel @MiniscopeTeam おめでとうございます!素晴らしい!

Profilbild von Takuya SASATANI
Takuya SASATANIvor 14 Tagen

@biorxivpreprint @BroschMarcel @MiniscopeTeam ありがとうございます!

Profilbild von Burak Gençay
Burak Gençayvor 14 Tagen

@biorxivpreprint @BroschMarcel @MiniscopeTeam Dear Takuya, I would love to work with you and your team.

Profilbild von eat organic, don't oil panic
eat organic, don't oil panicvor 14 Tagen

@biorxivpreprint @BroschMarcel @MiniscopeTeam Poor things.

Profilbild von Heikki Kallio
Heikki Kalliovor 14 Tagen

@biorxivpreprint @BroschMarcel @MiniscopeTeam @grok what kind of data could we gather from here that could be animated as easily understandable images, and/or writing?

Ähnliche Videos

Domain Randomization (DR) is a key component of the data augmentation pipeline at Axis Robotics. By applying DR, we are able to scale verified, high-quality human trajectories by 10x to 100x. During training, we systematically introduce variances in environmental parameters. This prevents the model from relying on spurious visual correlations. The objective is to ensure the policy learns rather than overfitting. To demonstrate the necessity and effectiveness of this approach, we evaluated both DR and No-DR models on Task 74 (pour_water_into_mug). The empirical results show a definitive impact on real-world deployment reliability: integrating DR into the pipeline increased the success rate from 0% to 90% (Fig. 1). This divergence stems from how the respective policies process visual observations (Fig. 2). The baseline (No DR) model overfits to the static visual background. It essentially memorizes the poses from the training dataset but fails to generalize when subjected to the inevitable variances of real-world deployment. Consequently, it cannot execute the correct manipulation on the target object. Conversely, the DR-trained model learns to extract essential geometric features and physical constraints, filtering out superficial visual noise. This leads to significantly higher robustness in dynamic environments. The structural difference in execution is clearly reflected in the end-effector trajectory data: These real-world deployment recordings further illustrate this difference (Videos 1 and 2). Scaling Physical AI requires turning raw trajectory data into robust policies, and a rigorously engineered DR infrastructure is an essential bridge to close the Sim2Real gap.

Axis Robotics

27,125 Aufrufe • vor 5 Monaten