paper-with-me

홈 › Papers

OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation

2025-09-30 · Xinda Xue, Junjun Hu, Minghua Luo, Shichao Xie, Jintao Chen, Zixun Xie, Kuichen Quan, Wei Guo, Mu Xu, Zedong Chu arxiv

Embodied navigation presents a core challenge for intelligent robots, requiring the comprehension of visual environments, natural language instructions, and autonomous exploration. Existing models often fall short in offering a unified solution across diverse navigation paradigms, resulting in low success rates and limited generalization. We introduce OmniNav, a unified framework addressing instruct-goal, object-goal, point-goal navigation, and frontier-based exploration within a single architecture. Our approach features a lightweight, low-latency policy that accurately predicts continuous-space waypoints (coordinates and orientations). This policy surpasses action-chunk methods in precision and supports real-world deployment at control frequencies up to 5 Hz. Architecturally, OmniNav employs a fast-slow system design: a fast module generates waypoints using short-horizon visual context and subtasks, while a slow module performs deliberative planning with long-horizon observations and candidate frontiers to select subsequent subgoals and subtasks. This collaboration enhances path efficiency and maintains trajectory coherence, particularly in exploration and memory-intensive scenarios. Crucially, we identify that the primary bottleneck isn't merely navigation policy learning, but a robust understanding of general instructions and objects. To boost generalization, OmniNav integrates large-scale, general-purpose training datasets, including those for image captioning and visual recognition, into a joint multi-task regimen. This significantly improves success rates and robustness. Extensive experiments confirm OmniNav's state-of-the-art performance across various navigation benchmarks, with real-world deployment further validating its efficacy. OmniNav provides practical insights for embodied navigation, charting a scalable path towards versatile, highly generalizable robotic intelligence.

📄 PDF Abstract BibTeX arXiv:2509.25687

Code (0)

등록된 구현이 없습니다.

Tasks

Image Captioning

Similar Papers 제목 키워드 기반

Beyond Isolation: A Unified Benchmark for General-Purpose Navigation

2026-05-10 · Samson Sun, Tianyi Yang, Tengyue Wang, Yikai Xue 외 arxiv

The pursuit of general-purpose embodied agents is hindered by fragmented evaluation protocols that isolate navigation skills and fixate on specific robot morphologies, failing to reflect real-world scenarios where agents…

Prospective Learning: Learning for a Dynamic Future

2024-10-31 · Ashwin De Silva, Rahul Ramesh, Rubing Yang, Siyu Yu 외

In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably approximately correct (PAC) learning, largely…

PAC learning

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

2022-04-26 · Yang Liu, Yushen Wei, Hong Yan, Guanbin Li 외

Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emer…

BenchmarkingOut-of-Distribution GeneralizationRepresentation LearningVideo Understanding

Active Dynamical Prospection: Modeling Mental Simulation as Particle Filtering for Sensorimotor Control during Pathfinding

2021-03-14 · Jeremy Gordon, John Chuang

What do humans do when confronted with a common challenge: we know where we want to go but we are not yet sure the best way to get there, or even if we can. This is the problem posed to agents during spatial navigation a…

EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding

2026-06-23 · Yijia Lei, Jinzhao Li, Yichi Zhang, Jiacheng Hua 외 arxiv

We introduce EgoSAT, the first comprehensive benchmark for egocentric video reasoning in streaming settings, designed to evaluate the capabilities of modern vision-language models (VLMs). The benchmark targets streaming …