Speaker
Description
The waste management industry faces challenges related to carbon emissions, labor shortages, and safety risks for sanitation workers. This report presents a conceptual design and technical evaluation of an autonomous electric garbage truck that integrates artificial intelligence (AI) for navigation, container manipulation, and real-time obstacle avoidance. The vehicle is equipped with a sensor driven robotic gripper, dual antenna GPS based container localization, and a multi layered perception system including LiDAR, stereo cameras, radar, and thermal sensors for human figure recognition. The methodology combines existing electric truck platforms (e.g., Mack LR Electric, Mercedes Benz eEconic) with state of the art AI perception algorithms (YOLOv5, LSTM for route optimization) and functional safety standards (ISO 26262, ISO 21448). Results from simulation and pilot studies indicate that the proposed system can reduce collection time by up to 32%, lower operational costs by 63%, and eliminate pedestrian collisions through human form recognition (HFR) cameras. Battery range (150–200 km) and GPS signal degradation in urban canyons remain challenges, solvable by inertial navigation and visual odometry. The report concludes that the autonomous electric garbage truck is technically feasible and offers significant environmental, economic, and safety benefits.