mlsanityData to 14 Oct 2026

RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models

arXiv 2506.02354 ↗First posted 3 Jun 2025cs.CVcited by 4

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in semantic map construction and target direction prediction in current research, redundant exploration and exploration failures remain inevitable. A critical but underexplored direction is the timely termination of exploration to overcome these challenges. We observe a diminishing marginal effect between exploration steps and exploration rates and analyze the cost-benefit relationship of exploration. Inspired by this, we propose RATE-Nav, a Region-Aware Termination-Enhanced method. It includes a geometric predictive region segmentation algorithm and region-Based exploration estimation algorithm for exploration rate calculation. By leveraging the visual question answering capabilities of visual language models (VLMs) and exploration rates enables efficient termination.RATE-Nav achieves a success rate of 67.8% and an SPL of 31.3% on the HM3D dataset. And on the more challenging MP3D dataset, RATE-Nav shows approximately 10% improvement over previous zero-shot methods.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 34 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

25 of 34 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination13 Oct
  2. 2024OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models16 Feb
  3. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation6 Dec

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  7. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  8. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 244
  9. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  10. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  11. 2022ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddingscited by 178
  12. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
10 more
  1. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 127
  2. 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 120
  3. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 109
  4. 2023PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNavcited by 93
  5. 2023Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skillcited by 77
  6. 2023How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontierscited by 54
  7. 20223D-Aware Object Goal Navigation via Simultaneous Exploration and Identificationcited by 46
  8. 2024TriHelper: Zero-Shot Object Navigation with Dynamic Assistancecited by 25
  9. 2020Exploiting Scene-specific Features for Object Goal Navigationcited by 20
  10. 2022Search for or Navigate to? Dual Adaptive Thinking for Object Navigationcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigationcited by 13
  2. 2026CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Controlcited by 3
  3. 2026From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA modelscited by 3
  4. 2026MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning
  2. 2024End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering
  3. 2026MarvisNav: Making Memory Visible on Route Choices for Zero-Shot Object Navigation ↗
  4. 2024Balancing Performance and Efficiency in Zero-shot Robotic Navigation
  5. 2024Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs
  6. 2026C2Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation
  7. 2026SparseNav: Instruction-conditioned Sparse Semantic Perception for Training-Free Vision-Language Navigation
  8. 2025MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding ↗