AI RESEARCH
Lifelong Embodied Navigation Learning
arXiv CS.AI
•
ArXi:2603.06073v1 Announce Type: cross Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge as lifelong embodied navigation learning (LENL), where an agent is required to adapt to a sequence of navigation tasks spanning multiple scenes and diverse user instruction styles, while retaining previously learned knowledge.