Background and objective: Independent living and transportation are crucial aspects for people living with a disability. After an injury, it is important to assess driving ability, in terms of physical and psychological conditions, and to test the effects of prescribed drugs. Within this framework, driving simulators are suitable tools for training driving skills; however, available tools are expensive or lack appropriate sets of behavioral measures to fully characterize the drivers’ ability. Methods: This work presents the first step toward the development of ADRIS, a new open-source, accessible, realistic virtual reality simulator for training and testing driving skills of people with sensory-motor disability. This includes a prototype based on an open-source simulator for autonomous driving research (CARLA), with the addition of customized features such as adaptable driving controllers, a virtual reality headset, and the possibility to collect behavioral and physiological data. Also, the new system allows to set different environmental conditions, to include and control the timing of potentially dangerous situations, and to set scenarios with various difficulty levels. Results: Tests on 17 healthy participants demonstrated that the simulator is well tolerated in terms of discomfort, physical fatigue, and mental effort. Also, the system is easy to use and is capable of providing a realistic driving experience, allowing the extraction of reliable behavioral parameters. Conclusions: ADRIS combines a high-fidelity virtual world, with customizable features specifically designed for the training and testing of people living with a disability, thus making it usable in many contexts such as home training, rehabilitation, education, and research.

The main driver of aerospace structures design is the increase in performances of currently in use components. The behavior of structures is investigated by means of highly accurate finite elements (FE) analysis. The problem related to this kind of simulations is the high computational time required to obtain the structural response associated with nonlinear phenomena. This aspect is particularly significant during the preliminary phase, especially when the analysis involves an optimization procedure. One strategy to overcome this problem is the introduction of artificial intelligence techniques in the design phase. This work proposes an optimization framework based on the approximation of the structural behavior through an artificial neural network (ANN). The net is exploited during the optimization, performed with a particle swarm optimizer, in order to reduce the computational effort. FE analysis are used to train the ANN and to validate the results. The methodology is applied to the optimization of the fibers shape of variable stiffness cylindrical shells, with the goal of maximize the critical load taking into account also manufacturing constraints. The higher accuracy offered by ANN with respect to other global approximation techniques and the time saving, resulting from the developed methodology, are both highlighted.