SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts

TL;DR

This paper introduces SAME, a versatile model that unifies various language-guided visual navigation tasks, enabling an agent to adaptively handle different instruction granularities and observations, achieving strong multi-task performance.

Contribution

The paper proposes a novel State-Adaptive Mixture of Experts model that effectively shares knowledge across diverse navigation tasks and adapts to task-specific requirements.

Findings

SAME outperforms task-specific agents on seven navigation tasks.

The model demonstrates strong generalization across different instruction granularities.

Unified framework simplifies multi-task learning in visual navigation.

Abstract

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.