Abstract: We present a novel neural scene reconstruction method for RGB-D sequences that employs a multi-level feature grid to enhance the quality and improve the efficiency of surface reconstruction.
Abstract: Recent robot task planners utilize large language models (LLMs) or vision-language models (VLMs) as a failure detector. These methods perform well by leveraging their semantic reasoning ...
Even in communities with tight lot lines, working in private spaces is still possible. Designing for privacy in residential neighborhoods often means creating distance between homes, but that’s not ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results