NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
This addresses the challenge of improving navigation agents' adaptability and generalization in complex, changing environments for applications like robotics and AI assistants, representing a novel method for a known bottleneck.
The paper tackles the problem of Vision-and-Language Navigation in Continuous Environments (VLN-CE), where agents struggle with generalization and adaptation, by introducing NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making, achieving notable performance improvements on benchmarks.
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions. Current approaches often struggle with generalizing to novel environments and adapting to ongoing changes during navigation. Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks. NavMorph employs compact latent representations to model environmental dynamics, equipping agents with foresight for adaptive planning and policy refinement. By integrating a novel Contextual Evolution Memory, NavMorph leverages scene-contextual information to support effective navigation while maintaining online adaptability. Extensive experiments demonstrate that our method achieves notable performance improvements on popular VLN-CE benchmarks. Code is available at https://github.com/Feliciaxyao/NavMorph.