Robot Language Learning, Generation, and Comprehension
This addresses the challenge of enabling robots to understand and generate language for navigation tasks, representing an incremental advance in robotics and natural language processing.
The paper tackles the problem of grounding natural-language semantics in robotic driving by presenting a unified framework for learning, generating, and comprehending language, achieving 94.6% correctness and 85.6% completeness in human evaluations.
We present a unified framework which supports grounding natural-language semantics in robotic driving. This framework supports acquisition (learning grounded meanings of nouns and prepositions from human annotation of robotic driving paths), generation (using such acquired meanings to generate sentential description of new robotic driving paths), and comprehension (using such acquired meanings to support automated driving to accomplish navigational goals specified in natural language). We evaluate the performance of these three tasks by having independent human judges rate the semantic fidelity of the sentences associated with paths, achieving overall average correctness of 94.6% and overall average completeness of 85.6%.