SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts
This work addresses the challenge of creating a versatile navigation agent for robotics or AI systems, though it appears incremental by combining existing task types into a unified approach.
The paper tackles the problem of unifying diverse language-guided visual navigation tasks into a single framework, proposing the State-Adaptive Mixture of Experts (SAME) model, which enables an agent to handle seven navigation tasks simultaneously and outperforms or matches task-specific agents.
The academic field of learning instruction-guided visual navigation can be generally categorized into high-level category-specific search and low-level language-guided navigation, depending on the granularity of language instruction, in which the former emphasizes the exploration process, while the latter concentrates on following detailed textual commands. Despite the differing focuses of these tasks, the underlying requirements of interpreting instructions, comprehending the surroundings, and inferring action decisions remain consistent. This paper consolidates diverse navigation tasks into a unified and generic framework -- we investigate the core difficulties of sharing general knowledge and exploiting task-specific capabilities in learning navigation and propose a novel State-Adaptive Mixture of Experts (SAME) model that effectively enables an agent to infer decisions based on different-granularity language and dynamic observations. Powered by SAME, we present a versatile agent capable of addressing seven navigation tasks simultaneously that outperforms or achieves highly comparable performance to task-specific agents.