Design of an autonomous charging system for robot NAO

The increasing adoption of socially assistive robots in healthcare and assisted living environments highlights the need for reliable autonomous recharging solutions that ensure continuous operation without human intervention. Although the NAO humanoid robot is widely used in therapeutic, educational, and assistive contexts due to its rich interaction capabilities, its limited battery autonomy and reliance on manual charging significantly constrain long-term deployment. This study presents an efficient and cost-effective autonomous charging system for NAO, expanding upon previous work by introducing a fully integrated solution that enables independent navigation, precise docking, and safe autonomous recharging. The proposed system combines a redesigned battery compartment interface with conductive charging pads, a compliant wall-mounted docking station, and an Internet of Things-based control architecture. A set of three time-of-flight distance sensors provides fine-grained distance and orientation estimation during the docking phase, allowing reliable alignment despite localisation uncertainty and kinematic variability. Bidirectional communication between the robot and the docking station enables verification of engagement through current monitoring and supports corrective repositioning in the event of improper contact. Experimental validation in an indoor environment representative of healthcare facilities demonstrates that the system provides stable distance and orientation measurements, robust mechanical engagement, and safe charging supervision. The autonomous charging mechanism is fully integrated into NAO’s behavioural architecture, allowing the robot to detect low battery levels, navigate to the docking station, complete the charging process without human assistance, and resume normal operation. Overall, the proposed solution significantly enhances NAO’s operational autonomy, reduces caregiver workload, and improves the feasibility of sustained deployment of socially assistive robots in real-world healthcare and assisted-living scenarios.