{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T12:14:48Z","timestamp":1790079288040,"version":"4.0.1"},"reference-count":21,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomimetics"],"abstract":"<jats:p>Voice interfaces to anthropomorphic robotic arms are typically evaluated without a formal safety layer, or with safety as a post hoc filter trusting the transcript, leaving transcript corruption unaddressed. This paper presents the DAS3 Neuro-Voice Controller, a voice-driven pipeline for a musculoskeletal arm model, evaluated here as a kinematic surrogate for upper-limb exoskeleton and prosthetic control, built on three commitments: on-device intent classification via a 44 M-parameter DistilBERT classifier over a bounded nine-command vocabulary; a deterministic three-layer Gatekeeper enforcing semantic validation, kinematic feasibility, and hard safety constraints independent of classifier confidence; and an upstream Phonetic Interceptor sanitising characteristic ASR mutilations of anatomical and safety terms (\u201cfour arm\u201d \u2192 \u201cforearm\u201d). Trained on a class-balanced corpus of 3591 expressions and evaluated on fourteen non-native English speakers, the classifier reached 99.95% top-1 accuracy across 1847 oracle-resolvable utterances; the Gatekeeper reduced Priority Override Failure to 0.0%, rejected 100% of out-of-domain speech, and held false-rejection at 2.02%. Against a keyword-spotter baseline the pipeline delivered a 17.4-fold improvement in end-to-end success; the acoustic front-end remains the main weakness. Upstream input repair and downstream deterministic gating emerge as first-class components of safety-critical voice interfaces for assistive systems.<\/jats:p>","DOI":"10.3390\/biomimetics11090670","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T11:09:35Z","timestamp":1790075375000},"page":"670","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hearing It Right, Doing It Safely: A Reflex-Inspired Safety Gatekeeper for Voice-Controlled Exoskeleton Arm Manipulation"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5049-7965","authenticated-orcid":false,"given":"Emanuel","family":"Muntean","sequence":"first","affiliation":[{"name":"System Control and Computer Engineering Department, University of Petrosani, 332006 Petrosani, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4083-9121","authenticated-orcid":false,"given":"Monica","family":"Leba","sequence":"additional","affiliation":[{"name":"System Control and Computer Engineering Department, University of Petrosani, 332006 Petrosani, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1988-9340","authenticated-orcid":false,"given":"Andreea","family":"Ionica","sequence":"additional","affiliation":[{"name":"Management and Industrial Engineering Department, University of Petrosani, 332006 Petrosani, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Fu, J., Choudhury, R., Hosseini, S.M., Simpson, R., and Park, J.-H. (2022). Myoelectric control systems for upper limb wearable robotic exoskeletons and exosuits\u2014A systematic review. Sensors, 22.","DOI":"10.3390\/s22218134"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"V\u00e9lez-Guerrero, M.A., Callejas-Cuervo, M., and Mazzoleni, S. (2021). Design, development, and testing of an intelligent wearable robotic exoskeleton prototype for upper limb rehabilitation. Sensors, 21.","DOI":"10.3390\/s21165411"},{"key":"ref_3","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., and Sutskever, I. (2023, January 23\u201329). Robust speech recognition via large-scale weak supervision. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Padmanabha, A., Yuan, J., Gupta, J., Karachiwalla, Z., Majidi, C., Admoni, H., and Erickson, Z. (2024). VoicePilot: Harnessing LLMs as speech interfaces for physically assistive robots. Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST \u201924), ACM.","DOI":"10.1145\/3654777.3676401"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Samarakoon, S.M.U.S., Herath, H.M.K.K.M.B., Yasakethu, S.L.P., Fernando, D., Madusanka, N., Yi, M., and Lee, B.-I. (2025). Long short-term memory-enabled electromyography-controlled adaptive wearable robotic exoskeleton for upper arm rehabilitation. Biomimetics, 10.","DOI":"10.3390\/biomimetics10020106"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shakeriaski, F., and Mohammadian, M. (2025). Enhancing upper limb exoskeletons using sensor-based deep learning torque prediction and PID control. Sensors, 25.","DOI":"10.3390\/s25113528"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fei, H., Xue, T., He, Y., Lin, S., Du, G., Guo, Y., and Wang, Z. (2025). Large language model-driven natural language interaction control framework for single-operator bimanual teleoperation. Front. Robot. AI, 12.","DOI":"10.3389\/frobt.2025.1621033"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4649","DOI":"10.1109\/LRA.2026.3667488","article-title":"Safety guardrails for LLM-enabled robots","volume":"11","author":"Ravichandran","year":"2026","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_9","unstructured":"Kim, J., Chen, W., Soleymanzadeh, D., Ding, Y., Gao, X., Tu, Z., Zhang, R., Fei, F., Veer, S., and Lyu, Y. (2026). Modular safety guardrails are necessary for foundation-model-enabled robots in the real world. arXiv."},{"key":"ref_10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_11","unstructured":"Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv."},{"key":"ref_12","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_13","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_14","first-page":"12","article-title":"Intent recognition using DistilBERT and language models","volume":"3","author":"Kavi","year":"2024","journal-title":"J. Artif. Intell. Mach. Learn."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1007\/s12559-025-10470-w","article-title":"From RNNs to transformers and beyond: A deep dive into intent detection in goal-oriented conversational agents","volume":"17","author":"Jbene","year":"2025","journal-title":"Cogn. Comput."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Sun, Q., and Kapadia, D.R. (2025). Integrating large language models into robotic autonomy: A review of motion, voice, and training pipelines. AI, 6.","DOI":"10.3390\/ai6070158"},{"key":"ref_17","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., and Hausman, K. (2022). Do as I can, not as I say: Grounding language in robotic affordances. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., and Zeng, A. (June, January 29). Code as policies: Language model programs for embodied control. Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK.","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref_19","first-page":"100131","article-title":"Large language models for human\u2013robot interaction: A review","volume":"3","author":"Zhang","year":"2023","journal-title":"Biomim. Intell. Robot."},{"key":"ref_20","unstructured":"(2011). Robots and Robotic Devices\u2014Safety Requirements for Industrial Robots\u2014Part 1: Robots (Standard No. ISO 10218-1:2011)."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"}],"container-title":["Biomimetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/9\/670\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T11:49:43Z","timestamp":1790077783000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/9\/670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":21,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["biomimetics11090670"],"URL":"https:\/\/doi.org\/10.3390\/biomimetics11090670","relation":{},"ISSN":["2313-7673"],"issn-type":[{"value":"2313-7673","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]}}}