Safe road-crossing by self-driving vehicles is a crucial problem to address in smart-cities. We have recently introduced a multi-sensor fusion approach to support road-crossing decisions in a system composed by an autonomous wheelchair and a flying drone featuring a robust sensory system made of diverse and redundant components. To that aim, we designed an analytical danger function based on explainable physical conditions evaluated by single sensors, including those using machine learning and artificial vision. As a proof-of-concept, we performed an experimental evaluation in the IDSIA Autonomous Robotics lab to show the advantages of using multiple sensors, which can improve decision accuracy and effectively support safety assessment.
The work has been developed in the context of the European project named REXASI-PRO, which is focused on trustworthy artificial intelligence for social navigation of people with reduced mobility.
The preprint of the paper presenting the first results of the experimentation can be downloaded from:
https://arxiv.org/abs/2403.08984
The dataset is accessible from:
https://github.com/CarloGrigioni/safe_roadcrossing_aw
https://huggingface.co/datasets/carlogrigioni/safe-road-crossing-aw-dataset
