用视觉识别控制假肢手，无需用户校准，实现实时抓取。
Vision Controlled Orthotic Hand Exoskeleton
- 基于定制MobileNet_V2模型，通过摄像头实时识别物体并判断距离。
- 推理速度仅51毫秒，电池续航8小时，支持自主抓放操作。
- 适合康复训练与日常辅助，尤其关注免校准与便携性需求者。
本文提出一种基于AI视觉的矫形手部外骨骼设计与实现，旨在提升手部运动功能障碍患者的康复与辅助能力。系统采用Google Coral Dev Board Micro搭配边缘TPU，运行在六类物体数据集上训练的定制MobileNet_V2模型，实现物体实时检测、距离估算及气动执行器的自动启停，完成抓取与释放任务，避免了传统肌电（EMG）系统所需的用户个性化校准。设备设计紧凑，内置1300 mAh电池，续航达8小时。实验显示推理速度为51毫秒，较以往显著提升；但光照变化和物体姿态差异仍影响模型鲁棒性。尽管最新YOLOv11模型在测试中达到15.4 FPS，量化问题限制其部署。原型验证了视觉控制外骨骼在真实辅助场景中的可行性，兼顾便携性、能效与实时响应，同时指明未来需优化模型性能与硬件小型化方向。
原文摘要 · Abstract (English)
This paper presents the design and implementation of an AI vision-controlled orthotic hand exoskeleton to enhance rehabilitation and assistive functionality for individuals with hand mobility impairments. The system leverages a Google Coral Dev Board Micro with an Edge TPU to enable real-time object detection using a customized MobileNet\_V2 model trained on a six-class dataset. The exoskeleton autonomously detects objects, estimates proximity, and triggers pneumatic actuation for grasp-and-release tasks, eliminating the need for user-specific calibration needed in traditional EMG-based systems. The design prioritizes compactness, featuring an internal battery. It achieves an 8-hour runtime with a 1300 mAh battery. Experimental results demonstrate a 51ms inference speed, a significant improvement over prior iterations, though challenges persist in model robustness under varying lighting conditions and object orientations. While the most recent YOLO model (YOLOv11) showed potential with 15.4 FPS performance, quantization issues hindered deployment. The prototype underscores the viability of vision-controlled exoskeletons for real-world assistive applications, balancing portability, efficiency, and real-time responsiveness, while highlighting future directions for model optimization and hardware miniaturization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。