ARISE: AI-Powered At-Home Exercise for Older Adults

ARISE, An AI-powered Real-time Interactive Support for Exercise in Elderly Communities, was ADAL’s SCARP 2025 project.

ARISE is an AI-powered at-home exercise system for older adults. It combines lightweight pose estimation with voice interaction (offline automatic speech recognition, a local large language model and text-to-speech) to give real-time feedback and coaching during exercise sessions. The system is designed to run on low-power single-board computers such as the Raspberry Pi 5 with a Hailo-8 NPU and the NVIDIA Jetson Nano. All processing happens locally, so no data is sent to the cloud.

Team

  • Aaron Frist and Alexander Roop, student researchers
  • Dr. Peilong Li, faculty mentor
Avatar
ADAL
Department of Computer Science

The Agentic and Dependable AI Lab (ADAL) is an undergraduate research lab at Elizabethtown College working on AI for cybersecurity, edge AI, large language models and privacy-preserving machine learning.

Related