Project Description

Project TED2021-131759A-I00 funded by MCIN/ AEI /10.13039/501100011033 and by the "European Union NextGenerationEU/PRTR"

The urban population growth and the skyrocketing acceptance of e-commerce have generated an increasing freight transportation which is particularly stressed during last-mile deliveries. Todays logistics operations in city centers lead to very negative effects: increase in traffic congestion; air and noise pollution; or safety problems for pedestrians, bikers and deliverers. Besides, it is estimated that almost half the costs of logistics are due to these last-mile operations. To improve them, researchers and institutions suggest a more integrated logistics system, with coordinated movements, shippers and carriers, and with the freight transportation consolidated into the same green vehicles, while avoiding some business models depending on unfair and low-cost labor (e.g., e-riders). In this sense, the AUDEL project aims at developing key capabilities that will enable autonomous delivery devices for last-mile operations. These autonomous systems will reduce emissions, congestions, parking problems and delivery costs.

Despite the efforts, the state-of-the-art solutions, in terms of algorithms and technological developments, are still far from the maturity needed to safely operate in complex and highly uncertain intracity scenarios (e.g., suffering perception degradation, with dynamic obstacles or navigating among pedestrians). AUDEL is the third project we undertake at IRI devoted to last-mile logistics. In contrast to AUDEL, in the first ongoing project, ROCOTRANSP, our efforts are directed to study human-robot interactions, including robot companion, reinforcement learning and the handover of the goods. Further, ROCOTRANSP is investigating how the urban areas, buildings and houses have to be designed to allow the robots share urban spaces with humans. Our second ongoing project, LOGISMILE, aims at providing the first autonomous hub vehicle that works in cooperation with smaller delivery devices. To control the robots and remotely coordinate the fleet operations, a back-end control center will also be piloted in LOGISMILE. In AUDEL, we will focus on the autonomous navigation part of individual robotic delivery devices under challenging conditions and in realistic city scenarios. In particular, we will leverage the expertise of the research team to investigate on robust ego-motion estimation, detection and tracking of vulnerable road users (VRU), semantic understanding (augmented mapping) and predictive control.

In the course of AUDEL, results will be demonstrated in a number of robotic prototypes with increasing level of complexity. The works related to motion estimation and scene representation (e.g., detection and tracking of VRU or semantic understanding) will be developed first for hand-held sensor suites moving freely in 3D. In the same way, the control algorithms will be first developed for simulated settings, then for the non-holonomic motion of the CARNET Autonomous Delivery Device (i.e., a rover), and finally for the complex case of the open-source quadruped robot SOLO. A company established in the last-mile logistics has already shown interest in the project objectives and is expectant of its outcome. When the time comes, we will seek the transfer of project results to their platform.