Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale

• URL: http://arxiv.org/abs/2509.24910v1
• Date: Mon, 29 Sep 2025 15:15:54 GMT
• Title: Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale
• Authors: Songze Li, Zun Wang, Gengze Zhou, Jialu Li, Xiangyu Zeng, Limin Wang, Yu Qiao, Qi Wu, Mohit Bansal, Yi Wang,
• Abstract summary: We present SID, a goal-oriented language-guided navigation learning approach with Self-Improving Demonstrations.<n>Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories.<n>We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations can be transferred across a variety of language-guided navigation tasks.
• Score: 90.91312440221306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Goal-oriented language-guided navigation requires robust exploration capabilities for agents to navigate to specified goals in unknown environments without step-by-step instructions. Existing methods tend to exclusively utilize shortest-path trajectories, lacking effective exploration priors for training navigation agents. To address the above challenges, we present SID, a goal-oriented language-guided navigation learning approach with Self-Improving Demonstrations. Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories. The novel rollouts provide demonstrations with stronger exploration strategies to train a better agent, which in turn produces higher-quality agent demonstrations for the next round of training. We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations can be transferred across a variety of language-guided navigation tasks, elevating the performance ceiling in diverse goal-oriented navigation tasks. Extensive experiments demonstrate that SID significantly boosts the exploration capabilities and generalization of navigation agents. The resulting agent achieves new state-of-the-art performance on goal-oriented language-guided navigation tasks, including REVERIE, SOON, notably achieving a 50.9% success rate on the unseen validation splits of SOON, surpassing the prior leading approaches by a margin of 13.9%.

Related papers

• ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation [57.399685080574756]
  Existing MLLM-based VLN methods rely on imitation learning (IL) and often use DAgger for post-training.<n>We propose ActiveVLN, a VLN framework that explicitly enables active exploration through multi-turn RL.<n>Experiments show that ActiveVLN achieves the largest performance gains over IL baselines compared to both DAgger-based and prior RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-09-16T03:31:46Z)
• Efficient Strategy Learning by Decoupling Searching and Pathfinding for Object Navigation [11.816377162334401]
  Two-Stage Reward Mechanism (TSRM) for object navigation decouples the searching and pathfinding behaviours in an episode.<n>Also, we propose a pretraining method Depth Enhanced Masked Autoencoders (DE-MAE) that enables agent to determine explored and unexplored areas.<n>In addition, we propose a new metric of Searching Success weighted by Searching Path Length (SSSPL) that assesses agent's searching ability and exploring efficiency.
  arXiv  Detail & Related papers  (2024-06-20T08:35:10Z)
• TINA: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation [11.591176410027224]
  This paper presents a Vision-Language Navigation (VLN) agent based on Large Language Models (LLMs) We propose the Thinking, Interacting, and Action framework to compensate for the shortcomings of LLMs in environmental perception. Our approach also outperformed some supervised learning-based methods, highlighting its efficacy in zero-shot navigation.
  arXiv  Detail & Related papers  (2024-03-13T05:22:39Z)
• Towards Learning a Generalist Model for Embodied Navigation [24.816490551945435]
  We propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. We conduct extensive experiments to evaluate the performance and generalizability of our model.
  arXiv  Detail & Related papers  (2023-12-04T16:32:51Z)
• Masked Path Modeling for Vision-and-Language Navigation [41.7517631477082]
  Vision-and-language navigation (VLN) agents are trained to navigate in real-world environments by following natural language instructions. Previous approaches have attempted to address this issue by introducing additional supervision during training. We introduce a masked path modeling (MPM) objective, which pretrains an agent using self-collected data for downstream navigation tasks.
  arXiv  Detail & Related papers  (2023-05-23T17:20:20Z)
• Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration [83.96729205383501]
  We introduce prompt-based learning to achieve fast adaptation for language embeddings. Our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE.
  arXiv  Detail & Related papers  (2022-03-08T11:01:24Z)
• Waypoint Models for Instruction-guided Navigation in Continuous Environments [68.2912740006109]
  We develop a class of language-conditioned waypoint prediction networks to examine this question. We measure task performance and estimated execution time on a profiled LoCoBot robot. Our models outperform prior work in VLN-CE and set a new state-of-the-art on the public leaderboard.
  arXiv  Detail & Related papers  (2021-10-05T17:55:49Z)
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning [66.9937776799536]
  The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments. We propose a cross-modal grounding module to equip the agent with a better ability to track the correspondence between the textual and visual modalities.
  arXiv  Detail & Related papers  (2020-11-22T09:13:46Z)
• Active Visual Information Gathering for Vision-Language Navigation [115.40768457718325]
  Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct a robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. This work draws inspiration from human navigation behavior and endows an agent with an active information gathering ability for a more intelligent VLN policy.
  arXiv  Detail & Related papers  (2020-07-15T23:54:20Z)

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.