{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:26:05Z","timestamp":1789158365059,"version":"build-2803163510"},"reference-count":19,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T00:00:00Z","timestamp":1766793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"China National Magnetic Confinement Fusion Energy Development Research Program","award":["2024YFE03140003"],"award-info":[{"award-number":["2024YFE03140003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate distance perception and collision reasoning are crucial for robotic manipulation in the confined interior of tokamak vacuum vessels. Traditional mesh- or voxel-based methods suffer from discretization artifacts, discontinuities, and heavy memory requirements, making them unsuitable for continuous geometric reasoning and optimization-based planning. This paper presents an Occupancy-Aware Neural Distance Perception (ONDP) framework that serves as a compact and differentiable geometric sensor for manipulator obstacle avoidance in reactor-like environments. To address the inadequacy of conventional sampling methods in such constrained environments, we introduce a Physically-Stratified Sampling strategy. This approach moves beyond heuristic adaptation to explicitly dictate data distribution based on specific engineering constraints. By injecting weighted quotas into critical safety buffers and enforcing symmetric boundary constraints, we ensure robust gradient learning in high-risk regions. A lightweight neural network is trained directly in physical units (millimeters) using a mean absolute error loss, ensuring strict adherence to engineering tolerances. The resulting model achieves approximately 2\u20133 mm near-surface accuracy and supports high-frequency distance and normal queries for real-time perception, monitoring, and motion planning. Experiments on a tokamak vessel model demonstrate that ONDP provides continuous, sub-centimeter geometric fidelity. Crucially, benchmark results confirm that the proposed method achieves a query frequency exceeding 15 kHz for large-scale batches, representing a 5911\u00d7 speed-up over mesh-based queries. This breakthrough performance enables its seamless integration with trajectory optimization and model-predictive control frameworks for confined-space robotic manipulation.<\/jats:p>","DOI":"10.3390\/s26010194","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:50:42Z","timestamp":1766969442000},"page":"194","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Occupancy-Aware Neural Distance Perception for Manipulator Obstacle Avoidance in the Tokamak Vacuum Vessel"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0570-4544","authenticated-orcid":false,"given":"Fei","family":"Li","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering & Automation, Beihang University, Xueyuan Road 37, Beijing 100191, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1737-1030","authenticated-orcid":false,"given":"Wusheng","family":"Chou","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering & Automation, Beihang University, Xueyuan Road 37, Beijing 100191, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.fusengdes.2018.11.052","article-title":"ITER construction and manufacturing progress toward first plasma","volume":"146","author":"Bigot","year":"2019","journal-title":"Fusion Eng. Des."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"111967","DOI":"10.1016\/j.fusengdes.2020.111967","article-title":"Design of the European DEMO vacuum vessel inboard wall","volume":"160","author":"Mozzillo","year":"2020","journal-title":"Fusion Eng. Des."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1016\/j.fusengdes.2015.06.156","article-title":"Multi-purpose Deployer for ITER In-vessel Maintenance","volume":"98\u201399","author":"Choi","year":"2015","journal-title":"Fusion Eng. Des."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/S0920-3796(99)00022-8","article-title":"A Report on the First Remote Handling Operations at JET","volume":"46","author":"Rolfe","year":"1999","journal-title":"Fusion Eng. Des."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fusco, S., Sofia, A., Grazioso, S., Fontanelli, G.A., and Di Gironimo, G. (2023, January 6\u20138). Brief Overview of Long Reach Manipulators for Remote Maintenance in Fusion Reactors. Proceedings of the Third International Conference of the Italian Association of Design Methods and Tools for Industrial Engineering, Florence, Italy.","DOI":"10.1007\/978-3-031-58094-9_31"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"113121","DOI":"10.1016\/j.fusengdes.2022.113121","article-title":"EU DEMO Remote Maintenance System development during the Pre-Concept Design Phase","volume":"179","author":"Crofts","year":"2022","journal-title":"Fusion Eng. Des."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"114122","DOI":"10.1016\/j.fusengdes.2023.114122","article-title":"Concept design of automatic connector for maintenance cask of EU-DEMO and CFETR","volume":"199","author":"Li","year":"2024","journal-title":"Fusion Eng. Des."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"114334","DOI":"10.1016\/j.fusengdes.2024.114334","article-title":"An obstacle avoidance path planning algorithm to simulate hyper redundant manipulators for tokamaks maintenance","volume":"202","author":"Buonocore","year":"2024","journal-title":"Fusion Eng. Des."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/s10514-012-9321-0","article-title":"OctoMap: An efficient probabilistic 3D mapping framework based on octrees","volume":"34","author":"Hornung","year":"2013","journal-title":"Auton. Robot."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Curless, B., and Levoy, M. (1996, January 4\u20139). A volumetric method for building complex models from range images. Proceedings of the 23rd International Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA.","DOI":"10.1145\/237170.237269"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pan, J., and Manocha, D. (2012, January 14\u201318). FCL: A general purpose library for collision and proximity queries. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Saint Paul, MN, USA.","DOI":"10.1109\/ICRA.2012.6225337"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., and Lovegrove, S. (2019, January 15\u201320). DeepSDF: Learning continuous signed distance functions for shape representation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref_13","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., and Wang, W. (2021, January 6\u201314). NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Online."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Bukhari, S.T., Lawson, D., and Qureshi, A.H. (2025). Differentiable Composite Neural Signed Distance Fields for Robot Navigation in Dynamic Indoor Environments. arXiv.","DOI":"10.1109\/ICRA55743.2025.11128172"},{"key":"ref_15","unstructured":"Gil, G., Cobano, J.A., Merino, L., and Caballero, F. (2025). C-3TO: Continuous 3D Trajectory Optimization on Neural Euclidean Signed Distance Fields. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gil, G., Cobano, J.A., Caballero, F., and Merino, L. (2025, January 14\u201317). A Framework for Safe Local 3D Path Planning Based on Online Neural Euclidean Signed Distance Fields. Proceedings of the 2025 International Conference on Unmanned Aircraft Systems (ICUAS), Charlotte, NC, USA.","DOI":"10.1109\/ICUAS65942.2025.11007788"},{"key":"ref_17","unstructured":"Cai, J. (2025). Towards Intelligent Object Manipulation: Vision-Based Grasping, Pose Estimation, and Physical Property Identification. [Ph.D. Thesis, Hong Kong University of Science and Technology]."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, L., Kong, L., Liu, C., Wang, H., Wang, M., Pan, D., Tan, J., Yan, W., and Sun, Y. (2025). Efficient Path Planning for Collision Avoidance of Construction Vibration Robots Based on Euclidean Signed Distance Field and Vector Safety Flight Corridors. Sensors, 25.","DOI":"10.3390\/s25061765"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.precisioneng.2025.07.008","article-title":"Signed distance field-based collision-free trajectory planning for on-machine measurement of conical covers","volume":"96","author":"Fang","year":"2025","journal-title":"Precis. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/194\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:56:01Z","timestamp":1766969761000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/194"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,27]]},"references-count":19,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010194"],"URL":"https:\/\/doi.org\/10.3390\/s26010194","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,27]]}}}