\textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation

TL;DR

NaVIDA introduces inverse dynamics supervision and hierarchical action chunking to improve vision-language navigation, resulting in more stable, generalizable, and efficient agent behaviors in complex environments.

Contribution

The paper proposes a novel VLN framework that embeds action-grounded visual dynamics through inverse dynamics supervision and hierarchical action chunking, enhancing navigation stability and planning.

Findings

NaVIDA outperforms state-of-the-art methods with fewer parameters.

It demonstrates improved stability and generalization in navigation tasks.

Real-world robot tests confirm practical effectiveness.

Abstract

Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly action-grounded visual dynamics modeling. Lacking awareness of how actions transform subsequent visual observations, agents cannot plan actions rationally, leading to unstable behaviors, weak generalization, and cumulative error along trajectory. To address these issues, we introduce \textsc{NaVIDA} (\textbf{Nav}igation with \textbf{I}nverse \textbf{D}ynamics \textbf{A}ugmentation), a lightweight VLN framework that incorporates inverse dynamics supervision (IDS) as an explicit objective to embed action-grounded visual dynamics into policy learning. By jointly optimizing this visual dynamics with instruction-conditioned action prediction in a shared representation and action space, \textsc{NaVIDA} provides additional structured supervision that regularizes learning and leads to more stable and consistent navigation. To structure this supervision and extend the effective planning range, \textsc{NaVIDA} employs hierarchical probabilistic action chunking (HPAC), which organizes trajectories into multi-step chunks and provides discriminative, longer-range visual-change cues. Extensive experiments show that \textsc{NaVIDA} achieves superior navigation performance compared to state-of-the-art methods with fewer parameters (3B vs. 8B). Real-world robot evaluations further validate the practical feasibility and effectiveness of our approach.