Current end-to-end robotic policies, specifically Vision-Language-Action (VLA) models, typically operate on a single observation or a very short history. This 'lack of memory' makes ...
collecting some new ideas for slam (Semantic, 3DGS, BEV, Nav, LLM, Multi-session) and will update this repo weekly, for both engineering and academic usings. - runjtu/awesome-and-novel-works-in-slam ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results