18365966. USING LANGUAGE MODELS IN AUTONOMOUS AND SEMI-AUTONOMOUS SYSTEMS AND APPLICATIONS (NVIDIA Corporation)
Contents
USING LANGUAGE MODELS IN AUTONOMOUS AND SEMI-AUTONOMOUS SYSTEMS AND APPLICATIONS
Organization Name
Inventor(s)
Denis Laprise of Palo Alto CA (US)
Mark Wheeler of Saratoga CA (US)
James Wu of Foster City CA (US)
USING LANGUAGE MODELS IN AUTONOMOUS AND SEMI-AUTONOMOUS SYSTEMS AND APPLICATIONS
This abstract first appeared for US patent application 18365966 titled 'USING LANGUAGE MODELS IN AUTONOMOUS AND SEMI-AUTONOMOUS SYSTEMS AND APPLICATIONS
Original Abstract Submitted
Approaches presented herein provide for the generation of a text-based representation of an environment. In particular, a large language model (LLM) can be used to generate a tokenized text string representation of an environment using information such as the semantics, topology, and geometry of the environment. A language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. Such representations can be used to generate reconstructions of existing environments, correct or augment previously-constructed representations, or generate representations of new but realistic environments that comply with real-world rules. A text-based representation can comprise a one-dimensional string of tokens, which can encapsulate the important spatial information and semantics of an environment.
