LiLMaps: Learnable Implicit Language Maps
This work addresses the need for comprehensive scene representations to improve human-robot interaction and autonomous operation, but it appears incremental as it builds on existing implicit mapping techniques.
The paper tackles the problem of creating environment maps with language representations for robots using LLMs by enhancing incremental implicit mapping with vision-language features, resulting in solid performance improvements.
One of the current trends in robotics is to employ large language models (LLMs) to provide non-predefined command execution and natural human-robot interaction. It is useful to have an environment map together with its language representation, which can be further utilized by LLMs. Such a comprehensive scene representation enables numerous ways of interaction with the map for autonomously operating robots. In this work, we present an approach that enhances incremental implicit mapping through the integration of vision-language features. Specifically, we (i) propose a decoder optimization technique for implicit language maps which can be used when new objects appear on the scene, and (ii) address the problem of inconsistent vision-language predictions between different viewing positions. Our experiments demonstrate the effectiveness of LiLMaps and solid improvements in performance.