OctoNav: Towards Generalist Embodied Navigation

• URL: http://arxiv.org/abs/2506.09839v1
• Date: Wed, 11 Jun 2025 15:15:17 GMT
• Title: OctoNav: Towards Generalist Embodied Navigation
• Abstract summary: Embodied navigation stands as a foundation pillar within the broader pursuit of embodied AI.<n>In this work, we take steps toward generalist navigation agents, which can follow free-form instructions.<n>We propose a large-scale benchmark and corresponding method, termed OctoNav-Bench and OctoNav-R1.
• Score: 36.062963913289316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied navigation stands as a foundation pillar within the broader pursuit of embodied AI. However, previous navigation research is divided into different tasks/capabilities, e.g., ObjNav, ImgNav and VLN, where they differ in task objectives and modalities, making datasets and methods are designed individually. In this work, we take steps toward generalist navigation agents, which can follow free-form instructions that include arbitrary compounds of multi-modal and multi-capability. To achieve this, we propose a large-scale benchmark and corresponding method, termed OctoNav-Bench and OctoNav-R1. Specifically, OctoNav-Bench features continuous environments and is constructed via a designed annotation pipeline. We thoroughly craft instruction-trajectory pairs, where instructions are diverse in free-form with arbitrary modality and capability. Also, we construct a Think-Before-Action (TBA-CoT) dataset within OctoNav-Bench to provide the thinking process behind actions. For OctoNav-R1, we build it upon MLLMs and adapt it to a VLA-type model, which can produce low-level actions solely based on 2D visual observations. Moreover, we design a Hybrid Training Paradigm (HTP) that consists of three stages, i.e., Action-/TBA-SFT, Nav-GPRO, and Online RL stages. Each stage contains specifically designed learning policies and rewards. Importantly, for TBA-SFT and Nav-GRPO designs, we are inspired by the OpenAI-o1 and DeepSeek-R1, which show impressive reasoning ability via thinking-before-answer. Thus, we aim to investigate how to achieve thinking-before-action in the embodied navigation field, to improve model's reasoning ability toward generalists. Specifically, we propose TBA-SFT to utilize the TBA-CoT dataset to fine-tune the model as a cold-start phrase and then leverage Nav-GPRO to improve its thinking ability. Finally, OctoNav-R1 shows superior performance compared with previous methods.

Related papers

• LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation [52.91080323083409]
  Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments.<n>Here we present LightNav-0, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads.
  arXiv  Detail & Related papers  (2026-08-31T15:08:53Z)
• Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System [96.69286664036143]
  We present Qwen-RobotNav, a scalable navigation model built on Qwen-RobotNav.<n>We train Qwen-RobotNav on 15.6M samples; co-training with vision-language data prevents the collapse into reactive action-sequence mappers.<n>Qwen-RobotNav sets new state-of-the-art results across major navigation benchmarks.
  arXiv  Detail & Related papers  (2026-06-16T16:17:44Z)
• FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation [20.13280678867453]
  FineCog-Nav organizes navigation into fine-grained modules for language processing, perception, attention, memory, imagination, reasoning, and decision-making.<n>FineCog-Nav consistently outperforms zero-shot baselines in instruction adherence, long-horizon planning, and generalization to unseen environments.
  arXiv  Detail & Related papers  (2026-04-17T17:59:48Z)
• 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)
• FeudalNav: A Simple Framework for Visual Navigation [7.136542835931238]
  We develop a hierarchical framework that decomposes the navigation decision-making process into multiple levels.<n>Our method learns to select subgoals through a simple, transferable waypoint selection network.<n>We show competitive results with a suite of SOTA methods in Habitat AI environments without using any odometry in training or inference.
  arXiv  Detail & Related papers  (2026-01-15T22:10:29Z)
• EvolveNav: Self-Improving Embodied Reasoning for LLM-Based Vision-Language Navigation [111.0993686148283]
  We propose a novel sElf-improving embodied reasoning framework for boosting Vision-Language Navigation, dubbed EvolveNav.<n>Our EvolveNav consists of two stages: (1) Formalized CoT Supervised Fine-Tuning, where we train the model with formalized CoT labels to activate the model's navigational reasoning capabilities and increase the reasoning speed; (2) Self-Reflective Post-Training, where the model is iteratively trained with its own reasoning outputs as self-enriched CoT labels to enhance the supervision diversity.
  arXiv  Detail & Related papers  (2025-06-02T11:28:32Z)
• Navigation World Models [68.58459393846461]
  We introduce a controllable video generation model that predicts future visual observations based on past observations and navigation actions.<n>In familiar environments, NWM can plan navigation trajectories by simulating them and evaluating whether they achieve the desired goal.<n>Experiments demonstrate its effectiveness in planning trajectories from scratch or by ranking trajectories sampled from an external policy.
  arXiv  Detail & Related papers  (2024-12-04T18:59:45Z)
• InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment [5.43847693345519]
  In this work, we propose InstructNav, a generic instruction navigation system. InstructNav makes the first endeavor to handle various instruction navigation tasks without any navigation training or pre-built maps. With InstructNav, we complete the R2R-CE task in a zero-shot way for the first time and outperform many task-training methods.
  arXiv  Detail & Related papers  (2024-06-07T12:26:34Z)
• 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)
• $A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models [89.64729024399634]
  We study the task of zero-shot vision-and-language navigation (ZS-VLN), a practical yet challenging problem in which an agent learns to navigate following a path described by language instructions. Normally, the instructions have complex grammatical structures and often contain various action descriptions. How to correctly understand and execute these action demands is a critical problem, and the absence of annotated data makes it even more challenging.
  arXiv  Detail & Related papers  (2023-08-15T19:01:19Z)
• NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models [17.495162643127003]
  We introduce the NavGPT to reveal the reasoning capability of GPT models in complex embodied scenes. NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status. We show that NavGPT is capable of generating high-quality navigational instructions from observations and actions along a path.
  arXiv  Detail & Related papers  (2023-05-26T14:41:06Z)
• 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)

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.