持续性具身导航学习
Lifelong Embodied Navigation Learning
AI总结：
Uni-Walker通过分解导航知识为共享和特定组件，解决持续性具身导航学习中的灾难性遗忘问题，提升导航代理的持续学习能力。
摘要：
基于大语言模型的具身导航代理在单个任务上表现出色，但在持续获取新导航技能方面存在困难，这导致了灾难性遗忘。我们正式将这一挑战定义为持续性具身导航学习（LENL），其中代理需要适应跨越多个场景和多样化用户指令风格的一系列导航任务，同时保留之前学习的知识。为了解决这个问题，我们提出了Uni-Walker，一个持续性具身导航框架，它将导航知识分解为任务共享和任务特定的组件，采用解码器扩展LoRA（DE-LoRA）。为了学习共享知识，我们设计了一种知识继承策略和专家共激活策略，以促进在多个导航任务中的共享知识转移和细化。为了学习特定知识，我们提出了一个专家子空间正交约束以及一个导航特定的推理机制，以捕捉特定知识并增强指令风格的理解。广泛的实验表明，Uni-Walker在构建具有持续学习能力的通用导航代理方面具有优势。
英文摘要：
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. To tackle this problem, we propose Uni-Walker, a lifelong embodied navigation framework that decouples navigation knowledge into task-shared and task-specific components with Decoder Extension LoRA (DE-LoRA). To learn the shared knowledge, we design a knowledge inheritance strategy and an experts co-activation strategy to facilitate shared knowledge transfer and refinement across multiple navigation tasks. To learn the specific knowledge, we propose an expert subspace orthogonality constraint together and a navigation-specific chain-of-thought reasoning mechanism to capture specific knowledge and enhance instruction-style understanding. Extensive experiments demonstrate the superiority of Uni-Walker for building universal navigation agents with lifelong learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
