Optimized Operation Management With Predicted Filling Levels of the Litter Bins for a Fleet of Autonomous Urban Service Robots

Abstract

Autonomous smart waste management services are becoming an essential component of sustainable urbanization. However, the lack of data and insights from current service-providers impedes a reliable transition from labor-intensive to autonomous services. Deploying information gathering devices make services expensive and resource-demanding. In project MARBLE (Mobile Autonomous RoBot for Litter Emptying) we are currently investigating the implementation of a fleet of service robots. In this framework, we could show that the absent filling data of litter bins (LBs) hinders the possibility of providing an energy-efficient and time-effective service. Hence, we introduce an approach where machine learningbased predictions for filling levels of LBs, derived from our extensive data gathering, are used to effectively manage the autonomous emptying process. The novel Simulated Rebalancing approach in route-planning combined with the Knapsack algorithm ensures efficient service, in comparison to the Nearest Neighbor algorithm. A promising 82% filling level prediction accuracy was achieved with the XGBoost binary classifier, as compared to the 59% baseline accuracy. Through incorporating the reliable predicted filling level data in the Simulated Rebalancing approach, a reduction of 26% in operational time and 31% in energy consumption was achieved for our simulated tests for service-event-area (SEA) James-Simon-Monbijoupark in Berlin with 49 LBs.

Service centric design methodology for integrated robot-infrastructure systems

“…We manually collected data from 51 LBs for three weeks, achieving 83% accurate filling predictions, and integrated this into the route planning algorithm. We introduced a machine learning (ML) based Simulated Rebalancing based Route Planning (SRRP) strategy, deferring LB emptying below 25% full until the next day, resulting in a significant 45% energy reduction and a 30% decrease in overall operation time (Pollak et al, 2024).…”