metadata

license: mit

RDT-1B

RDT-1B is a 1B-parameter (largest to date) imitation learning Diffusion Transformer pre-trained on 1M+ (largest to date) multi-robot episodes. Given a language instruction and 3-view RGB image observations, RDT can predict the next 64 robot actions. RDT is inherently compatible with almost all kinds of modern mobile manipulators, from single-arm to dual-arm, joint to EEF, pos. to vel., and even with a mobile chassis.

Model Sources

Repository: [More Information Needed]
Paper : [More Information Needed]
Project Page: https://rdt-robotics.github.io/rdt-robotics/

Uses

RDT-1B supports finetuning on custom dataset, deploying and inferencing on real-robots, and pre-training with large scale datasets.

Please refer to our repository for all the above guides.

Citation

BibTeX:

[More Information Needed]