Runtime Safety Assurance of Autonomous Last-Mile Delivery Vehicles in Urban-like Environment

Abstract

<div class="section abstract"><div class="htmlview paragraph">The conventional process of last-mile delivery logistics often leads to safety problems for road users and a high level of environmental pollution. Delivery drivers must deal with frequent stops, search for a convenient parking spot and sometimes navigate through the narrow streets causing traffic congestion and possibly safety issues for the ego vehicle as well as for other traffic participants. This process is not only time consuming but also environmentally impactful, especially in low-emission zones where prolonged vehicle idling can lead to air pollution and to high operational costs. To overcome these challenges, a reliable system is required that not only ensures the flexible, safe and smooth delivery of goods but also cuts the costs and meets the delivery target. In the dynamic landscape of last-mile delivery, LogiSmile, an EU project, introduced a solution to urban delivery challenges through an innovative cooperation between an Autonomous Hub Vehicle (AHV) and an Autonomous Delivery Device (ADD). This work addresses not only these challenges but also provides insight into a future where last-mile delivery is safer, more efficient and nature friendly. As a part of this project, an integrated safety system architecture has been developed for the AHV, featuring a dependability cage (DC) for onboard monitoring of a single autonomous vehicle and a remote command control center (CCC) for offboard monitoring of a fleet of autonomous vehicles. Operating at SAE levels 3/4 (SAE L3/4), the AHV incorporates a safety driver and a monitoring system, ensuring compliance with SAE guidelines. The DC enables safe transitions to degraded/ fail-safe driving modes in response to safety violations of the autonomous driving system (ADS), optimizing the vehicle's operational safety. Additionally, the CCC enhances autonomy by redundantly monitoring the fleet of vehicles via real-time sensor streams, also facilitating the communication with the ADD and the reconfiguration of the driving mode depending on the current road scenario. The project results were successfully demonstrated in Hamburg in 2022, showcasing the practical implementation of the developed safety architecture and the insights gained.</div></div>