In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale. But most of these systems are: (a) isolated (perception, speech, or language only); (b) trained on static datasets. On the other hand, in the field of robotics, large-scale learning has always been difficult. Supervision is hard to gather and real world physical interactions are expensive. In this work we introduce and open-source droidlet, a modular, heterogeneous agent architecture and platform. It allows us to exploit both large-scale static datasets in perception and language and sophisticated heuristics often used in robotics; and provides tools for interactive annotation. Furthermore, it brings together perception, language and action onto one platform, providing a path towards agents that learn from the richness of real world interactions.
@article{arxiv.2101.10384,
title = {droidlet: modular, heterogenous, multi-modal agents},
author = {Anurag Pratik and Soumith Chintala and Kavya Srinet and Dhiraj Gandhi and Rebecca Qian and Yuxuan Sun and Ryan Drew and Sara Elkafrawy and Anoushka Tiwari and Tucker Hart and Mary Williamson and Abhinav Gupta and Arthur Szlam},
journal= {arXiv preprint arXiv:2101.10384},
year = {2021}
}