ADRIS: The new open-source accessible driving simulator for training and evaluation of driving abilities. (June 2022)

• Record Type: Journal Article
• Authors: Ricci, S.; Gandolfi, F.; Marchesi, G.; Bellitto, A.; Basteris, A.; Canessa, A.; Massone, A.; Casadio, M.
• Is Part Of: Computer methods and programs in biomedicine. Volume 221(2022)
• Publication Date: 2022-06
• Subjects: Driving simulator -- Virtual reality -- Open-source -- Customizable -- Various difficulties scenarios; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106857
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: This work presents ADRIS, an open source, accessible, VR-based driving simulator. The simulator can train and test the driving skills of people with disability. Traffic volume, road type, visibility, and distractors can be customized. ADRIS provides performance data to assess compliance with traffic rule. The system collects electromyography to investigate driving-related mechanisms. Abstract: 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.