Real-Time Decision Making and Path Planning for Robotic Autonomous Luggage Trolley Collection at Airports

In this article, a two-level planner is proposed to provide a solution to the autonomous luggage trolley collection problem at the airport. In the higher level planner, a decision-making problem is tackled where a sequence of luggage trolleys is determined with which the robot can collect them one by one. Based on the traditional traveling salesman problem (TSP), this decision-making problem is formulated as an open dynamic traveling salesman problem with fixed start (ODTSP-FS). Incorporating the modified transition rule, elitist global update rule, and additional local update rule, an efficient algorithm is proposed to handle this decision-making problem. The experimental results demonstrate that the proposed algorithm achieves fast convergence and smaller cost compared with the state-of-the-art algorithms. In the lower level planner, based on the pipeline of rapid-exploring random tree (RRT) scheme, a novel real-time path planning algorithm is introduced, which can adjust itself to moving obstacles and moving targets by retaining the whole tree and using two rewiring strategies. Finally, the proposed two-level planner is evaluated in a simulation environment similar to the airport to validate the effectiveness and efficiency of the proposed algorithm.