WRSWorld Research StateContribute
WORLD RESEARCH STATE

Brohan and colleagues: RT-1 robotics transformer

Contribution grade

Robot learning · Human-designed AI research method or resource

Reference score20,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Trained a transformer-based real-world robot control model on diverse tasks and evaluated scaling and generalization across model and data choices.

Scientific scope

Trained a transformer-based real-world robot control model on diverse tasks and evaluated scaling and generalization across model and data choices. Scope limitation: RT-1 is one 2022 robot-control study; distinct from later RT-2 and not a claim of general-purpose autonomous robotics.

Evidence

The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. RT-1 is one 2022 robot-control study; distinct from later RT-2 and not a claim of general-purpose autonomous robotics.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction