Research spanning time-series pattern discovery, grounded language acquisition, and learning from unlabelled sensor data - the problem of turning raw robot experience into reusable structure.
That thread runs directly into current robotics practice: perception models trained on teleoperation logs, and language interfaces that map an instruction onto a physical action.
This page is preserved because it is still referenced from academic and directory sources. Publication records from the group remain in the Coral Labs archive.
This page preserves a historic coral-lab.org address. The original files are held offline; if you need them for citation or attribution, contact Coral Labs.