DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Vision-Language NavigationSpatial ReasoningSimilar Papers 제목 키워드 기반
Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning
A common failure mode for policies trained with imitation is compounding execution errors at test time. When the learned policy encounters states that are not present in the expert demonstrations, the policy fails, leadi…
Imitation LearningFlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the …
Reinforcement LearningWNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly t…
Vision-Language NavigationEfficient Active Imitation Learning with Random Network Distillation
Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to p…
Imitation LearningImitation Learning for Neural Network Autopilot in Fixed-Wing Unmanned Aerial Systems
This research identifies the feasibility of training an artificial neural network (ANN) autopilot, using supervised learning techniques, including an imitation learning framework known as the data aggregation set (DAgger…
Imitation Learning