SBIR Phase I: A Novel Human Machine Interface for Assistive Robots

小型企业创新研究(SBIR)第一阶段项目的更广泛影响/商业潜力将使全球3000万中风、脊髓损伤和创伤性脑损伤的残疾幸存者受益。让辅助机器人变得更实惠、更容易使用对这个市场很重要，预计到2024年，这个市场将增长到12亿美元。拟议的可穿戴技术将实现机器人的有效通信和控制，旨在帮助患者进行日常生活活动，这将帮助患者提高生活质量，降低长期护理成本，并通过增加活动来保持身心健康。这些数据可能被用来监测康复和病情恶化的进程，这可能会鼓励患者更频繁地锻炼，并实现更个性化的治疗。这个小型企业创新研究(SBIR)第一阶段项目将探索将一种轻巧紧凑的光学传感器频段商业化的可行性，以检测残疾用户的命令并控制辅助机器人。由于患者病情的多样化和不断演变，大多数商业上可用的人-机器人接口选项对于慢性偏瘫患者来说不实用或不可靠。研究目标包括设计光学传感器阵列来捕捉肌肉活动，以及开发一种基于自适应肌肉协同的分类算法来将光学数据转换为用户命令。该项目将优化近红外发射器和光电晶体管的配置，以有效地监测前臂的肌肉活动。先进的信号处理和机器学习技术将用于过滤从多模式传感器输入收集的数据，以确保无论用户条件如何都具有稳健的性能。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will benefit the 30 million disabled survivors of stroke, spinal cord injury, and traumatic brain injury around the globe. Making assistive robots more affordable and easy to use is important for this market, projected to grow to $1.2 billion in 2024. The proposed wearable technology will enable effective communication and control of robots designed to assist patients with activities of daily living, which will help patients improve quality of life, lower costs for long-term care, and preserve physical and mental health with increased activities. The data may be used to monitor rehabilitation and deterioration progress, which could encourage patients to exercise more frequently and enable more personalized treatment.This Small Business Innovation Research (SBIR) Phase I project will explore the feasibility of commercializing a lightweight and compact optical sensor band for detecting commands from disabled users and controlling assistive robots. Most commercially available human-robot interface options are not practical or reliable for chronic hemiparetic patients due to the diverse and evolving patient conditions. The research objective involves designing an optical sensor array to capture muscle activities and developing an adaptive muscle synergy-based classification algorithm to convert optical data to user command. The project will optimize the configuration for near-infrared emitters and phototransistors to efficiently monitor muscle activities on the forearm. Advanced signal processing and machine learning techniques will be used to filter the data collected from multimodal sensor inputs to ensure robust performance regardless of user conditions.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.