paper-with-me

홈 › Papers

Lifelong Topological Visual Navigation

2021-10-16 · Rey Reza Wiyatno, Anqi Xu, Liam Paull

Commonly, learning-based topological navigation approaches produce a local policy while preserving some loose connectivity of the space through a topological map. Nevertheless, spurious or missing edges in the topological graph often lead to navigation failure. In this work, we propose a sampling-based graph building method, which results in sparser graphs yet with higher navigation performance compared to baseline methods. We also propose graph maintenance strategies that eliminate spurious edges and expand the graph as needed, which improves lifelong navigation performance. Unlike controllers that learn from fixed training environments, we show that our model can be fine-tuned using only a small number of collected trajectory images from a real-world environment where the agent is deployed. We demonstrate successful navigation after fine-tuning on real-world environments, and notably show significant navigation improvements over time by applying our lifelong graph maintenance strategies.

📄 PDF Abstract BibTeX arXiv:2110.08488

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Navigation

Similar Papers 제목 키워드 기반

Topological Motion Planning Diffusion: Generative Tangle-Free Path Planning for Tethered Robots in Obstacle-Rich Environments

2026-03-16 · Yifu Tian, Xinhang Xu, Thien-Minh Nguyen, Muqing Cao arxiv

In extreme environments such as underwater exploration and post-disaster rescue, tethered robots require continuous navigation while avoiding cable entanglement. Traditional planners struggle in these lifelong planning s…

Computational EfficiencyMotion Planning

AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning

2026-06-09 · Hang Yin, Yinan Liang, Jiazhao Zhang, Jiahang Liu 외 arxiv

Lifelong embodied navigation in dynamic environments requires robots to form persistent scene understanding from fragmentary observations, which remains difficult for existing methods that rely on explicit maps or scene …

Reinforcement LearningScene Understanding

TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation

2026-05-03 · Yiyao Wang, Sixian Zhang, Keming Zhang, Xinhang Song 외 arxiv

Existing zero-shot Object Goal Navigation (ObjectNav) methods often exploit commonsense knowledge from large language or vision-language models to guide navigation. However, such knowledge arises from internet-scale text…

SSMG-Nav: Enhancing Lifelong Object Navigation with Semantic Skeleton Memory Graph

2026-03-02 · Haochen Niu, Lantao Zhang, Xingwu Ji, Rendong Ying 외 arxiv

Navigating to out-of-sight targets from human instructions in unfamiliar environments is a core capability for service robots. Despite substantial progress, most approaches underutilize reusable, persistent memory, const…

GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation

2024-04-09 · CVPR 2024 1 · Mukul Khanna, Ram Ramrakhya, Gunjan Chhablani, Sriram Yenamandra 외

The Embodied AI community has made significant strides in visual navigation tasks, exploring targets from 3D coordinates, objects, language descriptions, and images. However, these navigation models often handle only a s…

Go to AnyThingNavigateUniversal NavigationVisual Navigation