TY - JOUR A1 - Zieher, Simon A1 - Olcay, Ertug A1 - Kefferpütz, Klaus A1 - Salamat, Babak A1 - Olzem, Sebastian-Sven A1 - Elsbacher, Gerhard A1 - Meeß, Henri T1 - Drones for automated parcel delivery: Use case identification and derivation of technical requirements JF - Transportation Research Interdisciplinary Perspectives N2 - Drone-based parcel delivery is a rapidly growing domain posing many technological and operational challenges. Drone technologies have been under increasing levels of investigation and development over the past years. Since the realization of drone-based delivery can only be economically feasible at large scales, it requires processes that address the outstanding challenges holistically. However, the majority of research focuses on individual aspects such as environmental perception, route planning, operational design, and business models without addressing the challenges in the overall system. This paper conducts a quantitative analysis of the requirements for identified use cases that are considered relevant for the upcoming future. We provide a comprehensive technology overview and derive requirements and specifications for the targeted use cases that are not fulfilled by the current state-of-the-art. The use cases are not only related to last-mile delivery but also long-distance (hub-to-hub) logistics as well as courier and express delivery. UR - https://doi.org/10.1016/j.trip.2024.101253 Y1 - 2024 UR - https://doi.org/10.1016/j.trip.2024.101253 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53303 SN - 2590-1982 VL - 2024 IS - 28 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Salamat, Babak A1 - Olzem, Sebastian-Sven A1 - Elsbacher, Gerhard A1 - Tonello, Andrea M. T1 - Global Multi-Phase Path Planning Through High-Level Reinforcement Learning JF - IEEE Open Journal of Control Systems N2 - In this paper, we introduce the Global Multi-Phase Path Planning ( GMP3 ) algorithm in planner problems, which computes fast and feasible trajectories in environments with obstacles, considering physical and kinematic constraints. Our approach utilizes a Markov Decision Process (MDP) framework and high-level reinforcement learning techniques to ensure trajectory smoothness, continuity, and compliance with constraints. Through extensive simulations, we demonstrate the algorithm's effectiveness and efficiency across various scenarios. We highlight existing path planning challenges, particularly in integrating dynamic adaptability and computational efficiency. The results validate our method's convergence guarantees using Lyapunov’s stability theorem and underscore its computational advantages. UR - https://doi.org/10.1109/OJCSYS.2024.3435080 Y1 - 2024 UR - https://doi.org/10.1109/OJCSYS.2024.3435080 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-52776 SN - 2694-085X VL - 3 SP - 405 EP - 415 PB - IEEE CY - Piscataway ER -