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

• URL: http://arxiv.org/abs/2508.09444v1
• Date: Wed, 13 Aug 2025 02:51:43 GMT
• Title: DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
• Authors: Haoxiang Shi, Xiang Deng, Zaijing Li, Gongwei Chen, Yaowei Wang, Liqiang Nie,
• Abstract summary: Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces.<n>Existing VLN-CE approaches typically use a two-stage waypoint planning framework.<n>We propose DAgger Diffusion Navigation (DifNav) as an end-to-end optimized VLN-CE policy.
• Score: 73.80968452950854
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ReasonNavi: Human-Inspired Global Map Reasoning for Zero-Shot Embodied Navigation [53.95797153529148]
  Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations.<n>We introduce ReasonNavi, a human-inspired framework that operationalizes this reason-then-act paradigm by coupling Multimodal Large Language Models (MLLMs) with deterministic planners.
  arXiv  Detail & Related papers  (2026-01-26T19:09:20Z)
• VLD: Visual Language Goal Distance for Reinforcement Learning Navigation [5.225089020389076]
  We introduce Vision-Language Distance (VLD) learning, a framework for goal-conditioned navigation.<n>We first train a self-supervised distance-to-goal predictor on internet-scale video data.<n>This predictor generalizes across both image- and text-based goals, providing a distance signal that can be minimized by a reinforcement learning policy.
  arXiv  Detail & Related papers  (2025-12-08T19:05:51Z)
• Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation [67.68165784193556]
  Nav-$R2$ is a framework that explicitly models two types of relationships, target-environment modeling and environment-action planning.<n>Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives.<n>Nav-R2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline.
  arXiv  Detail & Related papers  (2025-12-02T04:21:02Z)
• SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation [12.152477445938759]
  Vision-and-Language Navigation (VLN) in continuous environments requires agents to interpret natural language instructions while navigating unconstrained 3D spaces.<n>Existing VLN-CE frameworks rely on a two-stage approach: a waypoint predictor to generate waypoints and a navigator to execute movements.<n>We propose a zero-shot VLN-CE framework integrating an enhanced waypoint predictor with a Multi-modal Large Language Model (MLLM)-based navigator.
  arXiv  Detail & Related papers  (2025-03-13T05:32:57Z)
• PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation [30.710806048991923]
  Vision and language navigation is a task that requires an agent to navigate according to a natural language instruction. Recent methods predict sub-goals on constructed topology map at each step to enable long-term action planning. We propose an alternative method that facilitates navigation planning by considering the alignment between instructions and directed fidelity trajectories.
  arXiv  Detail & Related papers  (2024-07-16T08:22:18Z)
• Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation [64.84996994779443]
  We propose a novel Affordances-Oriented Planner for continuous vision-language navigation (VLN) task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making. Experiments on the challenging R2R-CE and RxR-CE datasets show that AO-Planner achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-07-08T12:52:46Z)
• Versatile Navigation under Partial Observability via Value-guided Diffusion Policy [14.967107015417943]
  We propose a versatile diffusion-based approach for both 2D and 3D route planning under partial observability. Specifically, our value-guided diffusion policy first generates plans to predict actions across various timesteps. We then employ a differentiable planner with state estimations to derive a value function, directing the agent's exploration and goal-seeking behaviors.
  arXiv  Detail & Related papers  (2024-04-01T19:52:08Z)
• NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning [97.88246428240872]
  Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions.<n>Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability.<n>This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision.
  arXiv  Detail & Related papers  (2024-03-12T07:27:02Z)
• NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration [57.15811390835294]
  This paper describes how we can train a single unified diffusion policy to handle both goal-directed navigation and goal-agnostic exploration. We show that this unified policy results in better overall performance when navigating to visually indicated goals in novel environments. Our experiments, conducted on a real-world mobile robot platform, show effective navigation in unseen environments in comparison with five alternative methods.
  arXiv  Detail & Related papers  (2023-10-11T21:07:14Z)
• ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments [56.194988818341976]
  Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. We propose ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments. ETPNav yields more than 10% and 20% improvements over prior state-of-the-art on R2R-CE and RxR-CE datasets.
  arXiv  Detail & Related papers  (2023-04-06T13:07:17Z)
• Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation [41.334731014665316]
  Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments. We propose a predictor to generate a set of candidate waypoints during navigation. We show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions.
  arXiv  Detail & Related papers  (2022-03-05T14:56:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.