Data Scaling for Navigation in Unknown Environments

• URL: http://arxiv.org/abs/2601.09444v1
• Date: Wed, 14 Jan 2026 12:44:39 GMT
• Title: Data Scaling for Navigation in Unknown Environments
• Abstract summary: Generalization of imitation-learned navigation policies to environments unseen in training remains a major challenge.<n>We conduct the first large-scale study of how data quantity and data diversity affect real-world generalization in end-to-end, map-free visual navigation.
• Score: 5.877363757610773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalization of imitation-learned navigation policies to environments unseen in training remains a major challenge. We address this by conducting the first large-scale study of how data quantity and data diversity affect real-world generalization in end-to-end, map-free visual navigation. Using a curated 4,565-hour crowd-sourced dataset collected across 161 locations in 35 countries, we train policies for point goal navigation and evaluate their closed-loop control performance on sidewalk robots operating in four countries, covering 125 km of autonomous driving. Our results show that large-scale training data enables zero-shot navigation in unknown environments, approaching the performance of policies trained with environment-specific demonstrations. Critically, we find that data diversity is far more important than data quantity. Doubling the number of geographical locations in a training set decreases navigation errors by ~15%, while performance benefit from adding data from existing locations saturates with very little data. We also observe that, with noisy crowd-sourced data, simple regression-based models outperform generative and sequence-based architectures. We release our policies, evaluation setup and example videos on the project page.

Related papers

• NavOL: Navigation Policy with Online Imitation Learning [10.836499380430254]
  NavOL is an online imitation learning paradigm that interacts with a simulator and updates itself using expert demonstrations online.<n> NavOL trains in a rollout update loop: during rollout, the policy acts in the simulator and queries a global planner which has privileged access to the global environment.<n>This online imitation loop removes the need for reward design, improves learning efficiency, and mitigates distribution shift by training on the policy own explored rollouts.
  arXiv  Detail & Related papers  (2026-05-12T08:33:38Z)
• 120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL [11.190261147281186]
  We show that we can collect a dataset, train an in-domain policy, and deploy it to the real world.<n>Our method, MINav, formulates image-goal navigation as an offline goal-conditioned reinforcement learning problem.
  arXiv  Detail & Related papers  (2026-03-27T14:09:33Z)
• OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value [74.80873109856563]
  OpenDataArena (ODA) is a holistic and open platform designed to benchmark the intrinsic value of post-training data.<n>ODA establishes a comprehensive ecosystem comprising four key pillars: (i) a unified training-evaluation pipeline that ensures fair, open comparisons across diverse models; (ii) a multi-dimensional scoring framework that profiles data quality along tens of distinct axes; and (iii) an interactive data lineage explorer to visualize dataset genealogy and dissect component sources.
  arXiv  Detail & Related papers  (2025-12-16T03:33:24Z)
• LookOut: Real-World Humanoid Egocentric Navigation [61.14016011125957]
  We introduce the challenging problem of predicting a sequence of future 6D head poses from an egocentric video.<n>To solve this task, we propose a framework that reasons over temporally aggregated 3D latent features.<n>Motivated by the lack of training data in this space, we present a dataset collected through this approach.
  arXiv  Detail & Related papers  (2025-08-20T06:43:36Z)
• Learning to Drive Anywhere with Model-Based Reannotation [49.80796496905606]
  We develop a framework for generalizable visual navigation policies for robots.<n>We leverage passively collected data, including crowd-sourced teleoperation data and unlabeled YouTube videos.<n>This relabeled data is then distilled into LogoNav, a long-horizon navigation policy conditioned on visual goals or GPS waypoints.
  arXiv  Detail & Related papers  (2025-05-08T18:43:39Z)
• CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos [11.912608309403359]
  We propose a scalable, data-driven approach for human-like urban navigation.<n>We train agents on thousands of hours of in-the-wild city walking and driving videos sourced from the web.<n>Our model learns sophisticated navigation policies to handle diverse challenges and critical scenarios.
  arXiv  Detail & Related papers  (2024-11-26T19:02:20Z)
• Scaling Data Generation in Vision-and-Language Navigation [116.95534559103788]
  We propose an effective paradigm for generating large-scale data for learning. We apply 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning.
  arXiv  Detail & Related papers  (2023-07-28T16:03:28Z)
• LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting [65.71129509623587]
  Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning. However, the promising results achieved on current public datasets may not be applicable to practical scenarios. We introduce the LargeST benchmark dataset, which includes a total of 8,600 sensors in California with a 5-year time coverage.
  arXiv  Detail & Related papers  (2023-06-14T05:48:36Z)
• Large Scale Real-World Multi-Person Tracking [68.27438015329807]
  This paper presents a new large scale multi-person tracking dataset -- textttPersonPath22. It is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20.
  arXiv  Detail & Related papers  (2022-11-03T23:03:13Z)

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.