{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:41:38Z","timestamp":1772300498176,"version":"3.50.1"},"reference-count":83,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Navigation in forest environments is a challenging and open problem in the area of field robotics. Rovers in forest environments are required to infer the traversability of <jats:italic>a priori<\/jats:italic> unknown terrains, comprising a number of different types of compliant and rigid obstacles, under varying lighting and weather conditions. The challenges are further compounded for inexpensive small-sized (portable) rovers. While such rovers may be useful for collaboratively monitoring large tracts of forests as a swarm, with low environmental impact, their small-size affords them only a low viewpoint of their proximal terrain. Moreover, their limited view may frequently be partially occluded by compliant obstacles in close proximity such as shrubs and tall grass. Perhaps, consequently, most studies on off-road navigation typically use large-sized rovers equipped with expensive exteroceptive navigation sensors. We design a low-cost navigation system tailored for small-sized forest rovers. For navigation, a light-weight convolution neural network is used to predict depth images from RGB input images from a low-viewpoint monocular camera. Subsequently, a simple coarse-grained navigation algorithm aggregates the predicted depth information to steer our mobile platform towards open traversable areas in the forest while avoiding obstacles. In this study, the steering commands output from our navigation algorithm direct an operator pushing the mobile platform. Our navigation algorithm has been extensively tested in high-fidelity forest simulations and in field trials. Using no more than a 16 \u00d7 16 pixel depth prediction image from a 32 \u00d7 32 pixel RGB image, our algorithm running on a Raspberry Pi was able to successfully navigate a total of over 750 m of real-world forest terrain comprising shrubs, dense bushes, tall grass, fallen branches, fallen tree trunks, small ditches and mounds, and standing trees, under five different weather conditions and four different times of day. Furthermore, our algorithm exhibits robustness to changes in the mobile platform\u2019s camera pitch angle, motion blur, low lighting at dusk, and high-contrast lighting conditions.<\/jats:p>","DOI":"10.3389\/frobt.2023.1086798","type":"journal-article","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T12:10:12Z","timestamp":1687954212000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["An embarrassingly simple approach for visual navigation of forest environments"],"prefix":"10.3389","volume":"10","author":[{"given":"Chaoyue","family":"Niu","sequence":"first","affiliation":[]},{"given":"Callum","family":"Newlands","sequence":"additional","affiliation":[]},{"given":"Klaus-Peter","family":"Zauner","sequence":"additional","affiliation":[]},{"given":"Danesh","family":"Tarapore","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"key":"B1","volume-title":"TensorFlow: Large-Scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"B2","first-page":"9439","article-title":"Deep visual navigation under partial observability","author":"Ai","year":"2022"},{"key":"B3","volume-title":"High quality monocular depth estimation via transfer learning","author":"Alhashim","year":"2018"},{"key":"B4","first-page":"55","article-title":"Real-time monocular human depth estimation and segmentation on embedded systems","author":"An","year":"2021"},{"key":"B5","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MRA.2010.936946","article-title":"Learning for autonomous navigation","volume":"17","author":"Bagnell","year":"2010","journal-title":"IEEE Robotics Automation Mag."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1628","DOI":"10.55417\/fr.2022050","article-title":"Kilometer-scale autonomous navigation in subarctic forests: Challenges and lessons learned","volume":"2","author":"Baril","year":"2022","journal-title":"Field Robot."},{"key":"B7","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1111\/j.1475-2743.2009.00236.x","article-title":"Soil compaction and soil management \u2013 A review","volume":"25","author":"Batey","year":"2009","journal-title":"Soil Use Manag."},{"key":"B8","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1109\/TITS.2017.2769218","article-title":"Learning traversability from point clouds in challenging scenarios","volume":"19","author":"Bellone","year":"2017","journal-title":"IEEE Trans. Intelligent Transp. Syst."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1002\/rob.21795","article-title":"Weaver: Hexapod robot for autonomous navigation on unstructured terrain","volume":"35","author":"Bjelonic","year":"2018","journal-title":"J. Field Robotics"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1567","DOI":"10.55417\/fr.2022049","article-title":"A survey on terrain traversability analysis for autonomous ground vehicles: Methods, sensors, and challenges","volume":"2","author":"Borges","year":"2022","journal-title":"Field Robot."},{"key":"B11","first-page":"4387","article-title":"Topological large-scale off-road navigation and exploration RAVON at the European land robot trial 2008","author":"Braun","year":"2009"},{"key":"B12","first-page":"457","article-title":"3D traversability analysis in forest environments based on mechanical effort","author":"Carvalho","year":"2022"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-022-03283-z","article-title":"Rspmp: Real-time semantic perception and motion planning for autonomous navigation of unmanned ground vehicle in off-road environments","author":"Chen","year":"2022","journal-title":"Appl. Intell."},{"key":"B14","first-page":"2085","article-title":"Dealing with shadows: Capturing intrinsic scene appearance for image-based outdoor localisation","author":"Corke","year":"2013"},{"key":"B15","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3390\/computation9120127","article-title":"Unimodal and multimodal perception for forest management: Review and dataset","volume":"9","author":"da Silva","year":"2021","journal-title":"Computation"},{"key":"B16","volume-title":"The global forest goals report 2021","author":"Desa","year":"2021"},{"key":"B17","first-page":"139","article-title":"A deep learning approach towards autonomous flight in forest environments","author":"Dionisio-Ortega","year":"2018"},{"key":"B18","first-page":"10242","article-title":"Local obstacle-skirting path planning for a fast Bi-steerable rover using b\u00e9zier curves","author":"Fnadi","year":"2020"},{"key":"B19","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."},{"key":"B20","doi-asserted-by":"publisher","first-page":"rob.21981","DOI":"10.1002\/rob.21981","article-title":"Efficient autonomous navigation for planetary rovers with limited resources","volume":"37","author":"Gerdes","year":"2020","journal-title":"J. Field Robotics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/LRA.2015.2509024","article-title":"A machine learning approach to visual perception of forest trails for mobile robots","volume":"1","author":"Giusti","year":"2015","journal-title":"IEEE Robotics Automation Lett."},{"key":"B22","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1080\/01691864.2013.791742","article-title":"Control of off-road mobile robots using visual odometry and slip compensation","volume":"27","author":"Gonzalez","year":"2013","journal-title":"Adv. Robot."},{"key":"B23","doi-asserted-by":"publisher","first-page":"153","DOI":"10.13031\/2013.26324","article-title":"Navigation techniques for mobile robots in greenhouses","volume":"25","author":"Gonz\u00e1lez","year":"2009","journal-title":"Appl. Eng. Agric."},{"key":"B24","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1038\/s42256-021-00436-6","article-title":"Environmental robotics for a sustainable future in circular economies","volume":"4","author":"Grau Ruiz","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"B25","doi-asserted-by":"publisher","first-page":"8972","DOI":"10.1109\/LRA.2022.3188900","article-title":"Autonomous service robots for urban waste management-multiagent route planning and cooperative operation","volume":"7","author":"Gupta","year":"2022","journal-title":"IEEE Robotics Automation Lett."},{"key":"B26","first-page":"7521","article-title":"Explore bravely: Wheeled-legged robots traverse in unknown rough environment","author":"Haddeler","year":"2020"},{"key":"B27","doi-asserted-by":"publisher","first-page":"887910","DOI":"10.3389\/frobt.2022.887910","article-title":"Traversability analysis with vision and terrain probing for safe legged robot navigation","volume":"9","author":"Haddeler","year":"2022","journal-title":"Front. Robotics AI"},{"key":"B28","first-page":"2827","article-title":"A near-to-far non-parametric learning approach for estimating traversability in deformable terrain","author":"Ho","year":""},{"key":"B29","first-page":"3475","article-title":"Traversability estimation for a planetary rover via experimental kernel learning in a Gaussian process framework","author":"Ho","year":""},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.4324\/9781351332323","volume-title":"Aviation law and drones: Unmanned aircraft and the future of aviation","author":"Hodgkinson","year":"2018"},{"key":"B31","first-page":"1","article-title":"Collective motion pattern scaling for improved open-loop off-road navigation","author":"Hoeller","year":"2013"},{"key":"B32","volume-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"B33","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1002\/rob.20244","article-title":"State space sampling of feasible motions for high-performance mobile robot navigation in complex environments","volume":"25","author":"Howard","year":"2008","journal-title":"J. Field Robotics"},{"key":"B34","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-642-13408-1_7","article-title":"Receding horizon model-predictive control for mobile robot navigation of intricate paths","volume":"69","author":"Howard","year":"2010","journal-title":"Field Serv. Robotics Results 7th Int. Conf. Springer Berlin Heidelberg"},{"key":"B35","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"B36","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1002\/rob.20280","article-title":"Editorial","volume":"26","author":"Huang","year":"","journal-title":"J. Field Robotics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/rob.20275","article-title":"Editorial: Editorial","volume":"26","author":"Huang","year":"","journal-title":"J. Field Robotics"},{"key":"B38","first-page":"576","article-title":"Virtual-to-real-world transfer learning for robots on wilderness trails","author":"Iuzzolino","year":"2018"},{"key":"B39","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1002\/rob.20161","article-title":"The DARPA LAGR program: Goals, challenges, methodology, and phase I results","volume":"23","author":"Jackel","year":"2006","journal-title":"J. Field robotics"},{"key":"B40","first-page":"157","article-title":"Autonomous mobile robot for apple plant disease detection based on cnn and multi-spectral vision system","author":"Karpyshev","year":"2021"},{"key":"B41","volume-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"B42","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1002\/rob.21866","article-title":"Multimodal obstacle detection in unstructured environments with conditional random fields","volume":"37","author":"Kragh","year":"2020","journal-title":"J. Field Robotics"},{"key":"B43","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1002\/rob.20332","article-title":"Adaptive rover behavior based on online empirical evaluation: Rover\u2013terrain interaction and near-to-far learning","volume":"27","author":"Krebs","year":"2010","journal-title":"J. Field Robotics"},{"key":"B44","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"B45","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10514-006-9000-0","article-title":"The DARPA perceptor evaluation experiments","volume":"22","author":"Krotkov","year":"2007","journal-title":"Aut. Robots"},{"key":"B46","first-page":"3389","article-title":"A self-training approach-based traversability analysis for mobile robots in urban environments","author":"Lee","year":"2021"},{"key":"B47","doi-asserted-by":"publisher","first-page":"107250","DOI":"10.1109\/ACCESS.2022.3212768","article-title":"ODS-Bot: Mobile robot navigation for outdoor delivery services","volume":"10","author":"Lee","year":"2022","journal-title":"IEEE Access"},{"key":"B48","doi-asserted-by":"publisher","first-page":"43482","DOI":"10.1109\/ACCESS.2020.2977889","article-title":"Slip-aware motion estimation for off-road mobile robots via multi-innovation unscented kalman filter","volume":"8","author":"Liu","year":"","journal-title":"IEEE Access"},{"key":"B49","first-page":"5671","article-title":"Robot navigation in crowded environments using deep reinforcement learning","author":"Liu","year":""},{"key":"B50","doi-asserted-by":"publisher","first-page":"6","DOI":"10.13140\/RG.2.2.30400.89606","article-title":"Towards deep learning using TensorFlow lite on RISC-V","volume":"1","author":"Louis","year":"2019","journal-title":"Third Workshop Comput. Archit. Res. RISC-V (CARRV)"},{"key":"B51","article-title":"3D local planning for a forestry UGV based on terrain gradient and mechanical effort","author":"Louren\u00e7o","year":"2020"},{"key":"B52","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1109\/LRA.2018.2800083","article-title":"J-mod2: Joint monocular obstacle detection and depth estimation","volume":"3","author":"Mancini","year":"2018","journal-title":"IEEE Robotics Automation Lett."},{"key":"B54","first-page":"14054","article-title":"A self-supervised near-to-far approach for terrain-adaptive off-road autonomous driving","author":"Mayuku","year":"2021"},{"key":"B55","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1002\/rob.21512","article-title":"A self-learning framework for statistical ground classification using radar and monocular vision","volume":"32","author":"Milella","year":"2015","journal-title":"J. Field Robotics"},{"key":"B56","doi-asserted-by":"publisher","first-page":"e0178448","DOI":"10.1371\/journal.pone.0178448","article-title":"Unmanned aircraft systems as a new source of disturbance for wildlife: A systematic review","volume":"12","author":"Mulero-P\u00e1zm\u00e1ny","year":"2017","journal-title":"PloS one"},{"key":"B57","first-page":"4689","article-title":"Creating and using probabilistic costmaps from vehicle experience","author":"Murphy","year":"2012"},{"key":"B58","first-page":"746","article-title":"Indoor segmentation and support inference from RGB-D images","author":"Nathan Silberman","year":"2012"},{"key":"B59","volume-title":"Procedural generation and rendering of realistic, navigable forest environments: An open-source tool","author":"Newlands","year":"2022"},{"key":"B60","first-page":"8035","article-title":"Low-viewpoint forest depth dataset for sparse rover swarms","author":"Niu","year":"2020"},{"key":"B61","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1177\/0278364916645661","article-title":"Robust Constrained Learning-based NMPC enabling reliable mobile robot path tracking","volume":"35","author":"Ostafew","year":"2016","journal-title":"Int. J. Robotics Res."},{"key":"B62","first-page":"10014","article-title":"Domain adaptation for outdoor robot traversability estimation from RGB data with safety-preserving loss","author":"Palazzo","year":"2020"},{"key":"B63","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1016\/j.engappai.2013.01.006","article-title":"Terrain traversability analysis methods for unmanned ground vehicles: A survey","volume":"26","author":"Papadakis","year":"2013","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B64","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1002\/rob.21536","article-title":"Learned stochastic mobility prediction for planning with control uncertainty on unstructured terrain","volume":"31","author":"Peynot","year":"2014","journal-title":"J. Field Robotics"},{"key":"B65","first-page":"5848","article-title":"Towards real-time unsupervised monocular depth estimation on CPU","author":"Poggi","year":"2018"},{"key":"B66","first-page":"4510","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"B67","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1002\/rob.21521","article-title":"Terrain classification in complex three-dimensional outdoor environments","volume":"32","author":"Santamaria-Navarro","year":"2015","journal-title":"J. Field Robotics"},{"key":"B68","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s11721-010-0051-7","article-title":"Swarm cognition on off-road autonomous robots","volume":"5","author":"Santana","year":"2011","journal-title":"Swarm Intell."},{"key":"B69","first-page":"2678","article-title":"Geometric and visual terrain classification for autonomous mobile navigation","author":"Schilling","year":"2017"},{"key":"B70","first-page":"2899","article-title":"Neural network based heterogeneous sensor fusion for robot motion planning","author":"Sebastian","year":"2019"},{"key":"B71","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1177\/0278364910369715","article-title":"Learning from demonstration for autonomous navigation in complex unstructured terrain","volume":"29","author":"Silver","year":"2010","journal-title":"Int. J. Robotics Res."},{"key":"B72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.comcom.2019.10.007","article-title":"Unmanned aerial vehicle (uav) based forest fire detection and monitoring for reducing false alarms in forest-fires","volume":"149","author":"Sudhakar","year":"2020","journal-title":"Comput. Commun."},{"key":"B73","first-page":"4885","article-title":"An autonomous exploration algorithm using environment-robot interacted traversability analysis","author":"Tang","year":"2019"},{"key":"B74","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3389\/frobt.2020.00083","article-title":"Sparse robot swarms: Moving swarms to real-world applications","volume":"7","author":"Tarapore","year":"2020","journal-title":"Front. Robotics AI"},{"key":"B75","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1002\/rob.22054","article-title":"On the role of feature and signal selection for terrain learning in planetary exploration robots","volume":"39","author":"Ugenti","year":"2022","journal-title":"J. Field Robotics"},{"key":"B76","first-page":"6914","article-title":"Rough terrain navigation for legged robots using reachability planning and template learning","author":"Wellhausen","year":"2021"},{"key":"B77","first-page":"719","article-title":"Local behavior-based navigation in rough off-road scenarios based on vehicle kinematics","author":"Wolf","year":"2018"},{"key":"B78","doi-asserted-by":"publisher","first-page":"eaar7650","DOI":"10.1126\/scirobotics.aar7650","article-title":"The grand challenges of Science Robotics","volume":"3","author":"Yang","year":"2018","journal-title":"Sci. Robotics"},{"key":"B79","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TITS.2019.2955598","article-title":"Fast depth prediction and obstacle avoidance on a monocular drone using probabilistic convolutional neural network","volume":"22","author":"Yang","year":"2021","journal-title":"IEEE Trans. Intelligent Transp. Syst."},{"key":"B80","volume-title":"Mbldp-r: A multiple biomolecules based rapid life detection protocol embedded in a rover scientific subsystem for soil sample analysis","author":"Zaman","year":"2022"},{"key":"B81","first-page":"6848","article-title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"key":"B82","doi-asserted-by":"publisher","first-page":"eabm5954","DOI":"10.1126\/scirobotics.abm5954","article-title":"Swarm of micro flying robots in the wild","volume":"7","author":"Zhou","year":"2022","journal-title":"Sci. Robotics"},{"key":"B83","first-page":"8697","article-title":"Learning transferable architectures for scalable image recognition","author":"Zoph","year":"2018"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2023.1086798\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T12:10:24Z","timestamp":1687954224000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2023.1086798\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":83,"alternative-id":["10.3389\/frobt.2023.1086798"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2023.1086798","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,28]]},"article-number":"1086798"}}