The Embedding Report.

EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation

84d ago · Global · primary source: export.arxiv.org

Multi-source synthesis by The Embedding Report from 2 sources. Every numeric and quoted claim traces to a cited source body (see methodology).

Researchers have proposed new frameworks for Zero-Shot Object-Goal Navigation (ZS-OGN), enabling embodied agents to explore and locate target objects without prior training.

Two recent studies have introduced innovative approaches to ZS-OGN. The first, called EvolveNav[1], is a self-evolving framework that enables continuous test-time improvement. It builds an agentic rule memory by extracting actionable knowledge from past trajectories and uses a memory-guided preflection module to forecast potential outcomes before action, reducing inefficient exploration. According to the researchers, EvolveNav outperforms existing zero-shot baselines, achieving a 10.1% improvement in success rate with fewer unnecessary steps[1]. The second study introduces EffiNav[2], a framework that fuses depth and vision-language information for efficient object goal navigation. EffiNav has been evaluated on two simulation benchmarks: Habitat Matterport 3D (HM3D) and Open-Vocabulary Object goal Navigation (OVON), and has also been tested on physical robots in real-world settings. The framework has been shown to match or outperform recent baselines on two standard metrics: Success Rate (SR) and Success weighted by Path Length (SPL)[2].

research-paperapplicationtool-release

Background sources we checked (7)
  • arxiv.org ↗ Zero-Shot Object-Goal Navigation (ZS-OGN) requires embodied agents to explore and locate target objects without any prior training. To this end, recent methods leverage foundation models. But they typically rely on static priors and lack adaptation, which leads to repeated errors…
  • info.arxiv.org ↗ arXiv Labs - arXiv info | arXiv e-print repository Skip to content # arXiv Labs Attention arXiv Users: arXiv Labs is pausing new proposals ## What are arXiv Labs? arXiv Labs are a way for the community to contribute new, useful features to arXiv. These integrations are avail…
  • blog.arxiv.org ↗ arXivLabs: a space for community innovation – arXiv blog arXiv has launched a new, formalized framework enabling innovative collaborations with individuals and organizations. “Members of our community want to contribute tools that enhance the arXiv experience, and we val…
  • info.arxiv.org ↗ arXivLabs: Showcase - arXiv info | arXiv e-print repository ... # arXivLabs: Showcase ... arXiv is surrounded by a community of researchers and developers working at the cutting edge of information science and technology. ... While the arXiv team is focused on our core mission—pr…
  • en.wikipedia.org ↗ arXiv (pronounced as "archive"—the X represents the Greek letter chi ⟨χ⟩) is an open-access repository of electronic preprints and postprints (known as e-prints) approved for posting after moderation, but not peer reviewed. It consists of scientific papers in the fields of mathem…
  • en.wikipedia.org ↗ 14 (fourteen) is the natural number following 13 and preceding 15.…
  • en.wikipedia.org ↗ A large language model (LLM) is a type of machine learning model designed for natural language processing tasks such as language generation. LLMs are language models with many parameters, and are trained with self-supervised learning on a vast amount of text.…

Sources cited (2)

  1. arxiv.org ↗ E
  2. arxiv.org ↗ E
Spot something wrong? Report an issue