A sustainable approach towards smart waste management means reduced impact on the health of the workers, lower greenhouse gas emissions and low operational costs. Incorporating fleets of the robot MARBLE (Mobile Autonomous RoBot for Litter Emptying) effectuates these requirements for autonomously emptying the dustbins on the streets of Berlin. The dedicated waypoints for the route formulation are the global positions of the dustbins, and the garbage emptying position from the robots after reaching the maximum compressed-garbage storage capacity. In this paper, we provide a cost function efficient solution for providing global routes to the robots. The cost function includes operational energy expenditure. After conducting numerous experiments with varying algorithm parameter values, the specific weightage of route permutation operators and the initial temperature for a simulated annealing method with nearest neighbour approach was narrowed down as a well-performing set. This set was used in three different operation scenarios. The results of the cost function on the basis of the chosen parameters show an improvement of average 28% for two different exemplary datasets, and 30% improvement for an implementation in an actual existing park in Berlin for operation scenarios as compared to results from a nearest neighbour heuristic.

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 makes 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 absence of 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 learning-based 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 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.

Efficient waste management is a defining feature of a future smart city and one of the core challenges to reduce the environmental impact of its inhabitants. Given the growing amount of waste that is discarded into public dustbins and the labour required for their maintenance, autonomous robots to empty the bins could help in mitigating those challenges. For this task, the mobile robotics platform MURMEL (Mobiler Urbaner Roboter zur Mülleimer EntLeerung) has been designed. However, the acceptance of this solution by the municipality and the public highly depends on the efficiency of task performance and the environmental impact of the system. To achieve that, we propose a communication framework involving smart dustbins, which inform a central planning entity about the filling level. A novel route planning algorithm is proposed based on the filling level communicated over LoRaWAN. It can avoid unavailing rides, where the robots cannot empty the dustbins due to its capacity limits and assembles a route to exploit the full capacity. We demonstrate the feasibility of our approach using a realistic simulation of 52 dustbins in an urban park, resulting in 13% less energy consumption, 29% less round-trips and a 42% increase in capacity utilization compared to a baseline route planning without communication.

Many service robots have to operate in a variety of different Service Event Areas (SEAs). In the case of the waste collection robot MARBLE (Mobile Autonomous Robot for Litter Emptying) every SEA has characteristics like varying area and number of litter bins, with different distances between litter bins and uncertain filling levels of litter bins. Global positions of litter bins and garbage drop-off positions from MARBLEs after reaching their maximum capacity are defined as task-performing waypoints. We provide boundary delimitation for characteristics that describe the SEA. The boundaries interpolate synergy between individual SEAs and the developed algorithms. This helps in determining which algorithm best suits an SEA, dependent on the characteristics. The developed route-planning methodologies are based on vehicle routing with simulated annealing (VRPSA) and knapsack problems (KSPs). VRPSA uses specific weighting based on route permutation operators, initial temperature, and the nearest neighbor approach. The KSP optimizes a route’s given capacity, in this case using smart litter bins (SLBs) information. The game-theory KSP algorithm with SLBs information and the KSP algorithm without SLBs information performs better on SEAs lower than 0.5 km${}^2$, and with fewer than 50 litter bins. When the standard deviation of the fill rate of litter bins is ≈$10\%$, the KSP without SLB is preferred, and if the standard deviation is between 25 and 40%, then the game-theory KSP is selected. Finally, the vehicle routing problem outperforms in SEAs with an area of $0.5\le 5$ km², 50–450 litter bins, and a fill rate of 10–40%.

Product development and operational methods of autonomous robot MURMEL (Mobiler Urbaner Roboter zur MüllEimer Leerung) for smart waste management focuses on all three aspects of sustainability. The robot autonomously empties the dustbins on the streets of Berlin, and concentrates on social sustainability by reducing the impact on the health of the workers. As one of the approaches towards efficient ecological and economical sustainability, MURMEL has its own route planning method delivered from an operation management model. For the operation management, the dustbins are allocated waypoints to the robot. In this paper, a cost function considering energy consumption is optimized in order to improve the robot's global route planning. By conducting numerous experiments with varying algorithm parameter values, the specific weightage of route permutation operators and the initial temperature for a simulated annealing method with nearest neighbour approach was narrowed down to a well-performing set. For an implementation in an actual existing park in Berlin for operation scenario, our simulation results show an average overall reduction of 11 % energy consumption as compared to results from a nearest neighbour heuristic.

The ongoing development of technology and AI facilitates the emergence of service robots in various application fields. Hence, the development of robot-infrastructure product-service systems (PSS) will become increasingly important. Based on the existing literature we propose a new methodological approach for a joint development of robot and infrastructure in the context of a socio-technical system with various stakeholders. We suggest digital models and physical prototypes to synchronize service and product development. The applicability is demonstrated for autonomous waste management robots.