arXiv 2603.039532026-07-14cs.ROcs.AIcs.CV

RVN-Bench: 一种用于反应式视觉导航的基准测试

RVN-Bench: A Benchmark for Reactive Visual Navigation

Department of Electrical and Computer Engineering, Seoul National University (SNU) and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc.（电气与计算机工程系，首尔国立大学（SNU）和自动化与系统研究所（ASRI）以及Sequor机器人公司）；Department of Electrical and Computer Engineering, Seoul National University (SNU) and Automation and Systems Research Institute (ASRI)（电气与计算机工程系，首尔国立大学（SNU）和自动化与系统研究所（ASRI））；Interdisciplinary Program in Artificial Intelligence, Seoul National University (SNU) and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc.（人工智能跨学科项目，首尔国立大学（SNU）和自动化与系统研究所（ASRI）以及Sequor机器人公司）；Sequor Robotics Inc.（Sequor机器人公司）

Jaewon Lee, Jaeseok Heo, Gunmin Lee, Howoong Jun, Jeongwoo Oh, Songhwai Oh

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

RVN-Bench是一种针对室内移动机器人安全视觉导航的碰撞感知基准测试，通过高保真度场景和标准化工具，支持在线和离线学习，提升导航任务的泛化能力。

摘要：

安全的视觉导航对于在拥挤环境中操作的室内移动机器人至关重要。然而，现有的基准测试往往忽视碰撞或设计用于户外场景，使其不适合用于室内视觉导航。为了解决这一限制，我们引入了反应式视觉导航基准（RVN-Bench），一种针对室内移动机器人的碰撞感知基准。在RVN-Bench中，代理必须在以前未见过的环境中，仅使用视觉观测和没有先验地图的情况下，依次到达目标位置，同时避免碰撞。基于Habitat 2.0模拟器，并利用高保真度的HM3D场景，RVN-Bench提供了大规模、多样的室内环境，定义了碰撞感知的导航任务和评估指标，并提供了标准化训练和基准测试的工具。RVN-Bench通过提供一个用于在线强化学习的环境、轨迹图像数据集生成器以及用于生成捕捉碰撞事件的负轨迹图像数据集的工具，支持在线和离线学习。实验表明，在RVN-Bench上训练的策略能够有效泛化到未见过的环境，证明了其作为标准化基准测试在安全和稳健视觉导航中的价值。代码和附加材料可在：https://rvn-bench.github.io/上获得。

英文摘要：

Safe visual navigation is critical for indoor mobile robots operating in cluttered environments. Existing benchmarks, however, often neglect collisions or are designed for outdoor scenarios, making them unsuitable for indoor visual navigation. To address this limitation, we introduce the reactive visual navigation benchmark (RVN-Bench), a collision-aware benchmark for indoor mobile robots. In RVN-Bench, an agent must reach sequential goal positions in previously unseen environments using only visual observations and no prior map, while avoiding collisions. Built on the Habitat 2.0 simulator and leveraging high-fidelity HM3D scenes, RVN-Bench provides large-scale, diverse indoor environments, defines a collision-aware navigation task and evaluation metrics, and offers tools for standardized training and benchmarking. RVN-Bench supports both online and offline learning by offering an environment for online reinforcement learning, a trajectory image dataset generator, and tools for producing negative trajectory image datasets that capture collision events. Evaluations demonstrate that policies trained on RVN-Bench generalize effectively across unseen simulated environments. Furthermore, initial physical experiments using a Jackal UGV indicate promising sim-to-real transfer. Code and additional materials are available at: https://sequor-robotics-research.github.io/projects/RVN-Bench/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。