Energy Efficiency for Autonomous Mobile Robots and Embodied AI
Energy efficiency is a critical concern for battery-powered platforms such as autonomous and embodied AI robots. These robots rely on complex models and algorithms, including Large Language Models (LLMs), Deep Neural Networks (DNNs), and Visual Simultaneous Localization and Mapping (SLAM), to navigate and operate efficiently. However, dynamic environments make it challenging to conserve energy without sacrificing accuracy. This project aims to tackle the energy efficiency challenge by co-optimizing both software and hardware designs for these robots.
Faculty
Research Fellows
