Improved Navigation for Social Robots Through OS and Sensor Augmentation

Abstract

The rise in elderly populations requires new innovations to further help combatthe growing population. One innovation that is currently being used is mobile robots to navigate around nursing homes and other medical facilities to further help care workers. One such example of this is the robot Pepper, which is used in nursing homes to navigate to the residents and perform various exercises and therapies. However this model of robot lacks adequate tracking sensors to be able to navigate effectively(Ghit,˘a et al. 2020)(Wauters 2018). To help Pepper map the nursing home for navigation, Pepper was equipped with a LIDAR detector and an NVIDIA Nano(Khan, Zurales, and Kameli 2022). However, the Pepper robot and the Jetson Nano were unable to communicate gracefully due to issues with time synchronization and inaccurate navigation. As such we looked into two solutions to solve this issue. An early solution explored removing the Nvidia Jetson Nano, but due to constraints within Pepper’s OS, it was not accomplished.The second solution used Chrony and NTP to ensure that Pepper and Jetson synced to the same NTP servers and synced to each other. The Jetson changed its timestamp to match Pepper’s; this solution was successful. The navigation files were tuned to function appropriately in a nursing home environment.