Semantic Goal
Semantic goal research focuses on enabling artificial agents, particularly robots, to understand and achieve goals expressed in terms of meaningful concepts rather than just coordinates. Current work emphasizes hierarchical frameworks that decompose complex tasks into interpretable sub-goals, often leveraging graph neural networks and symbolic planning to reason about spatial relationships and object properties. This research is crucial for advancing embodied AI, improving human-robot interaction, and creating more robust and adaptable robotic systems capable of navigating and manipulating objects in unstructured environments.
Papers
January 6, 2023
October 17, 2022
October 16, 2022
October 10, 2022
June 21, 2022
May 14, 2022