{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:19:18Z","timestamp":1761005958109,"version":"build-2065373602"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T00:00:00Z","timestamp":1760918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PRE2022-105119","PLEC2023-010353","MCIN\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["PRE2022-105119","PLEC2023-010353","MCIN\/AEI\/10.13039\/501100011033"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Mobile robots require knowledge of the environment, especially of humans located in its vicinity. While the most common approaches for detecting humans involve computer vision, an often overlooked hardware feature of robots for people detection are their 2D range finders. These were originally intended for obstacle avoidance and mapping\/SLAM tasks. In most robots, they are conveniently located at a height approximately between the ankle and the knee, so they can be used for detecting people too, and with a larger field of view and depth resolution compared to cameras. In this paper, we present a new dataset for people detection using knee-high 2D range finders called FROG. This dataset has greater laser resolution, scanning frequency, and more complete annotation data compared to existing datasets such as DROW (Beyer et al., 2018). Particularly, the FROG dataset contains annotations for 100% of its laser scans (unlike DROW which only annotates 5%), 17x more annotated scans, 100x more people annotations, and over twice the distance traveled by the robot. We propose a benchmark based on the FROG dataset, and analyze a collection of state-of-the-art people detectors based on 2D range finder data. We also propose and evaluate a new end-to-end deep learning approach for people detection. Our solution works with the raw sensor data directly (not needing hand-crafted input data features), thus avoiding CPU preprocessing and releasing the developer of understanding specific domain heuristics. Experimental results show how the proposed people detector attains results comparable to the state of the art, while an optimized implementation for ROS can operate at more than 500 Hz.<\/jats:p>","DOI":"10.3389\/frobt.2025.1671673","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T07:27:40Z","timestamp":1760945260000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FROG: a new people detection dataset for knee-high 2D range finders"],"prefix":"10.3389","volume":"12","author":[{"given":"Fernando","family":"Amodeo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"No\u00e9","family":"P\u00e9rez-Higueras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Merino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"Caballero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,20]]},"reference":[{"key":"B1","first-page":"3402","volume-title":"Using boosted features for the detection of people in 2D range data","author":"Arras","year":"2007"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.5281\/ZENODO.14936068","article-title":"Sixth sense: indoor human spatial awareness dataset","author":"Arreghini","year":"2025"},{"key":"B3","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1109\/lra.2016.2645131","article-title":"DROW: real-time deep learning based wheelchair detection in 2D range data","volume":"2","author":"Beyer","year":"2017","journal-title":"IEEE Robotics Automation Lett. (RA-L)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2726","DOI":"10.1109\/lra.2018.2835510","article-title":"Deep person detection in two-dimensional range data","volume":"3","author":"Beyer","year":"2018","journal-title":"IEEE Robotics Automation Lett. (RA-L)"},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01164","article-title":"nuScenes: a multimodal dataset for autonomous driving","author":"Caesar","year":"2020"},{"key":"B6","first-page":"5030","article-title":"WILDTRACK: a multi-camera HD dataset for dense unscripted pedestrian detection","author":"Chavdarova","year":"2018"},{"key":"B7","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"B8","first-page":"19576","article-title":"STCrowd: a multimodal dataset for pedestrian perception in crowded scenes","author":"Cong","year":"2022"},{"key":"B9","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"B10","first-page":"100","article-title":"The development and real-world deployment of FROG, the fun robotic outdoor guide","author":"Evers","year":"2014"},{"key":"B12","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/978-3-031-26354-5_4","article-title":"On the optimal combination of cross-entropy and soft dice losses for lesion segmentation with out-of-distribution robustness","volume-title":"Diabetic foot ulcers grand challenge","author":"Galdran","year":"2023"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: the KITTI dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robotics Res. (IJRR)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3389\/fnbot.2018.00085","article-title":"Tracking people in a Mobile robot from 2D LIDAR scans using full convolutional neural networks for security in cluttered environments","volume":"12","author":"Guerrero-Higueras","year":"2019","journal-title":"Front. Neurorobotics"},{"key":"B15","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B16","article-title":"MobileNets: efficient convolutional neural networks for Mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv Prepr. arXiv:1704.04861"},{"key":"B17","first-page":"10270","article-title":"DR-SPAAM: a spatial-attention and auto-regressive model for person detection in 2D range data","author":"Jia","year":"2020"},{"key":"B18","first-page":"13301","article-title":"Self-supervised person detection in 2D range data using a calibrated camera","author":"Jia","year":"2021"},{"key":"B19","doi-asserted-by":"publisher","first-page":"11807","DOI":"10.1109\/LRA.2022.3184025","article-title":"Socially CompliAnt navigation dataset (SCAND): a large-scale dataset of demonstrations for social navigation","volume":"7","author":"Karnan","year":"2022","journal-title":"IEEE Robotics Automation Lett. (RA-L)"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1940","DOI":"10.1109\/LRA.2019.2896705","article-title":"PedX: benchmark dataset for metric 3-D pose estimation of pedestrians in complex urban intersections","volume":"4","author":"Kim","year":"2019","journal-title":"IEEE Robotics Automation Lett. (RA-L)"},{"key":"B21","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"B22","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"B23","doi-asserted-by":"publisher","first-page":"6748","DOI":"10.1109\/tpami.2021.3070543","article-title":"JRDB: a dataset and benchmark of egocentric robot visual perception of humans in built environments","volume":"45","author":"Mart\u00edn-Mart\u00edn","year":"2023","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B24","unstructured":"ROS leg detector package\n          \n          \n            \n              Pantofaru\n              C.\n            \n          \n          \n          2010"},{"key":"B25","article-title":"Navigating among people in crowded environment: datasets for localization and human robot interaction Workshop on robots in clutter: perception and interaction in clutter","author":"Ram\u00f3n-Vigo","year":"2014"},{"key":"B26","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"B27","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume-title":"Advances in neural information processing systems","author":"Ren","year":"2015"},{"key":"B28","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention (MICCAI)","author":"Ronneberger","year":"2015"},{"key":"B29","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1109\/lra.2020.2965416","article-title":"TH\u00d6R: human-robot navigation data collection and accurate motion trajectories dataset","volume":"5","author":"Rudenko","year":"2020","journal-title":"IEEE Robotics Automation Lett. (RA-L)"},{"key":"B30","article-title":"The magni human motion dataset: Accurate, complex, multi-modal, natural, semantically-rich and contextualized","author":"Schreiter","year":"2022"},{"key":"B31","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","article-title":"Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations","volume-title":"Deep learning in medical image analysis and multimodal learning for clinical decision support","author":"Sudre","year":"2017"},{"key":"B34","article-title":"\u201cHierarchical Data Format, version 5\u201d","year":"2024"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.5281\/ZENODO.13730199","article-title":"Semantic2D: a semantic dataset for 2D lidar semantic segmentation","author":"Xie","year":"2024","journal-title":"Dataset"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3420353","article-title":"Li2Former: omni-dimension aggregation transformer for person detection in 2-D range data","volume":"73","author":"Yang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1671673\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T07:27:43Z","timestamp":1760945263000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1671673\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,20]]},"references-count":33,"alternative-id":["10.3389\/frobt.2025.1671673"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2025.1671673","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,20]]},"article-number":"1671673"}}