Assisted Robot Arm with Voice Recognition for Digital Healthcare

Healthcare systems face increasing pressure from nursing shortages, growing patient-care demands, and the substantial amount of time healthcare professionals spend performing routine and repetitive bedside activities. These challenges can increase caregiver workload and reduce the time available for clinical assessment, decision-making, and direct patient interaction. Patients with limited mobility may also depend on caregivers for relatively simple activities, such as retrieving objects, obtaining drinking water, or interacting with their immediate environment, which can lead to delayed assistance when healthcare personnel are occupied with higher-priority responsibilities. Motivated by these challenges, this study investigates the use of collaborative robotics and intelligent natural-language interaction to provide supplementary assistance for predictable and repetitive patient-care tasks. An intelligent robotic patient-assistance framework is developed by integrating collaborative robotic manipulation, voice-based natural-language interaction, and non-contact physiological monitoring. The system employs a UFACTORY xArm7 collaborative manipulator to perform representative bedside assistance tasks, including cleaning a designated area, pouring water, delivering medicine, and measuring body temperature. A Python-based software architecture coordinates robot control, task execution and user interaction. To provide hands-free and intuitive control, Faster-Whisper is used for continuous speech-to-text processing, while a Large Language Model (LLM) interprets the transcribed commands and maps different natural-language expressions to predefined robotic tasks.

@article{Zhang2026,
  title     = {Assisted Robot Arm with Voice Recognition for Digital Healthcare},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {9},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Ting Zhang and Oanh Phan and Jiang Lu},
  doi       = {10.14569/IJACSA.2026.0170902},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170902}
}