Nur Muhammad “Mahi” Shafiullah

Deploying robots at scale demands robustness to the long tail of everyday situations.

Recent advances in robot learning have generated significant interest in capable platforms that may eventually approach human-level competence.

Language-conditioned robot learning has emerged as the dominant paradigm for creating general-purpose robot policies.

Significant progress has been made in open-vocabulary mobile manipulation, where the goal is for a robot to perform tasks in any environment given a natural language description.

Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities.

Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision making.

Remarkable progress has been made in recent years in the fields of vision, language, and robotics.

Throughout history, we have successfully integrated various machines into our homes.

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging.

We propose CLIP-Fields, an implicit scene model that can be trained with no direct human supervision.