Design and Pso-Based Optimization of an Intelligent Autonomous Mobile Robot for Environmental Risk Detection and Disinfection

The increasing threat of viral disease transmission in healthcare and public environments has created a need for automated, contactless and efficient environmental disinfection technologies. This study presents the design and optimization of an intelligent mobile robot for autonomous environmental-risk detection and disinfection, with particular consideration of resource-constrained environments in Nigeria. The proposed system integrates ultrasonic, infrared, gas and thermal sensors with autonomous navigation, proportional-integral-derivative (PID) motor control, sensor-fusion-based environmental assessment and a UV-C disinfection unit. Particle Swarm Optimization (PSO) was incorporated to minimize robot travel distance, disinfection time and energy consumption while maximizing environmental coverage. The robot was evaluated in a controlled 5 m × 5 m indoor test environment containing representative obstacles. Performance was assessed using coverage efficiency, disinfection time, energy consumption and environmental-risk detection accuracy. The PSO-optimized configuration achieved 92% coverage efficiency, compared with 72% for the non-optimized configuration. Disinfection time decreased from 35 to 25 min, representing a 28.6% reduction, while energy consumption decreased from 120 to 96 Wh, corresponding to a 20.0% reduction. Sensor fusion improved environmental-risk classification accuracy from 78% for a single-sensor configuration to 91%, representing a 13-percentage-point improvement. The findings demonstrate that combining sensor fusion, autonomous navigation and PSO-based path optimization can substantially improve the operational efficiency of mobile robotic disinfection. The proposed architecture provides a practical foundation for contactless environmental disinfection in hospitals, schools and other high-risk facilities, although biological validation and direct pathogen sensing remain necessary before clinical deployment.