An international collaboration between New Jersey Institute of Technology (NJIT) and Ben-Gurion University of the Negev (BGU) is using AI and edge computing to revolutionize how robotic dogs interact with their owners. The project, according to Htworld.co.uk, is sponsored by the Institute for Future Technologies (IFT) and aims to make robotic dogs more responsive to their masters by adapting wearable-based sensing devices that detect physiological and emotional stimuli inherent to the owner’s personality and traits.
As Science Daily reports, the researchers, led by Assistant Professor Kasthuri Jayarajah of NJIT’s Ying Wu College of Computing, are designing a socially assistive model of the Unitree Go2 robotic dog. The invention could significantly impact home and healthcare settings, helping combat loneliness in the elderly population and aiding in therapy and rehabilitation.
“Robots like the Unitree Go2 are not yet up for big AI tasks,” Jayarajah explains. “They have limited processing power compared to big GPU clusters, not a lot of memory, and limited battery life.” Despite these challenges, the long-term goal is to make the robotic dog come “alive” by detecting the owner’s unique physiological and emotional stimuli, enabling a more dynamic and responsive interaction between the robotic dog and its human companion.
Progress So Far
The Unitree Go2 robotic dog, which is the focus of this project, can already understand and respond to gestural cues from its partners. Jayarajah’s initial work on this aspect will be presented at the International Conference on Intelligent Robots and Systems (IROS) later this year.
Shelly Levy-Tzedek, Associate Professor at BGU’s Department of Physical Therapy, focuses her research on rehabilitation robotics. “We are excited to collaborate on this project that could significantly impact the lives of elderly individuals and those undergoing therapy or rehabilitation,” Levy-Tzedek stated, emphasizing the potential benefits of this innovative approach.
Image credit: NJIT
