arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.07076cs.ROcs.AIcs.CV
收藏

无需目标识别的室内环境高层语义区域建图

Mapping High-level Semantic Regions in Indoor Environments without Object Recognition

University of Modena and Reggio Emilia(摩德纳与雷焦艾米利亚大学);Georgia Institute of Technology(佐治亚理工学院);Stanford University(斯坦福大学)

Roberto Bigazzi, Lorenzo Baraldi, Shreyas Kousik, Rita Cucchiara, Marco Pavone

AI总结:

针对现有研究较少关注大尺度语义区域建图的问题,提出结合视觉-语言模型与训练导航策略的具身导航语义建图方法,在仿真实验中显著优于多种基线。

摘要:

机器人需要对周围环境具备语义理解能力,才能在人类环境中高效且可解释地运行。现有研究大量聚焦于目标标注和穷尽式场景图生成,针对纯识别与大尺度语义区域建图任务的研究投入较少。本研究提出一种通过室内环境具身导航实现语义区域建图的方法,生成智能体知识的高层表示。为实现区域识别,该方法采用视觉-语言模型为建图提供场景信息。通过将以自我为中心的场景理解投影到全局坐标系,所提方法生成语义地图,其形式为每个位置上可能区域标签的分布。该建图流程与一个经过训练的导航策略相结合,可实现自主建图。在照片级真实感模拟器中开展的实验表明,所提方法显著优于多种基线方法,包括基于目标的系统和预训练场景分类器。

英文摘要:

Robots require a semantic understanding of their surroundings to operate in an efficient and explainable way in human environments. In the literature, there has been an extensive focus on object labeling and exhaustive scene graph generation; less effort has been focused on the task of purely identifying and mapping large semantic regions. The present work proposes a method for semantic region mapping via embodied navigation in indoor environments, generating a high-level representation of the knowledge of the agent. To enable region identification, the method uses a vision-to-language model to provide scene information for mapping. By projecting egocentric scene understanding into the global frame, the proposed method generates a semantic map as a distribution over possible region labels at each location. This mapping procedure is paired with a trained navigation policy to enable autonomous map generation. The proposed method significantly outperforms a variety of baselines, including an object-based system and a pretrained scene classifier, in experiments in a photorealistic simulator.

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。

↑