DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation

TL;DR

This paper introduces DAgger Diffusion Navigation (DifNav), an end-to-end diffusion-based policy for vision-language navigation that outperforms traditional two-stage waypoint methods by modeling multi-modal actions directly in continuous space.

Contribution

The paper proposes a unified diffusion policy for VLN-CE that eliminates the need for waypoint prediction and incorporates DAgger training for robustness and error recovery.

Findings

Outperforms previous state-of-the-art models on benchmark datasets.

Eliminates reliance on waypoint predictors, simplifying the navigation pipeline.

Enhances robustness and long-horizon spatial reasoning in navigation tasks.

Abstract

Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a high-level waypoint predictor generates the navigable waypoints, and then a navigation planner suggests the intermediate goals in the high-level action space. However, this two-stage decomposition framework suffers from: (1) global sub-optimization due to the proxy objective in each stage, and (2) a performance bottleneck caused by the strong reliance on the quality of the first-stage predicted waypoints. To address these limitations, we propose DAgger Diffusion Navigation (DifNav), an end-to-end optimized VLN-CE policy that unifies the traditional two stages, i.e. waypoint generation and planning, into a single diffusion policy. Notably, DifNav employs a conditional diffusion policy to directly model multi-modal action distributions over future actions in continuous navigation space, eliminating the need for a waypoint predictor while enabling the agent to capture multiple possible instruction-following behaviors. To address the issues of compounding error in imitation learning and enhance spatial reasoning in long-horizon navigation tasks, we employ DAgger for online policy training and expert trajectory augmentation, and use the aggregated data to further fine-tune the policy. This approach significantly improves the policy's robustness and its ability to recover from error states. Extensive experiments on benchmark datasets demonstrate that, even without a waypoint predictor, the proposed method substantially outperforms previous state-of-the-art two-stage waypoint-based models in terms of navigation performance. Our code is available at: https://github.com/Tokishx/DifNav.