The ongoing research at Tampere University is focused on developing flexible safety systems for highly automated off-road mobile machinery to meet the needs of the industry. The research has identified significant gaps in compliance with legislation related to public safety when using mobile working machines that are controlled by artificial intelligence.
As the use of highly automated off-road machinery becomes more common, there is a growing need for strong safety measures. Traditional safety procedures often do not take into account the health and safety risks associated with systems controlled by artificial intelligence (AI).
Marea de Koning, a doctoral researcher focusing on automation at Tampere University, is conducting research to ensure public safety while still advancing technology. She is developing a safety framework specifically designed for autonomous mobile machines working with humans. This framework aims to enable the safe and effective use of AI-controlled machinery.
The original equipment manufacturers (OEM), safety & system engineers, and industry stakeholders work together to develop safety systems that meet the changing legislation.
Striking a balance between humans and autonomous machines
It is nearly impossible to anticipate all the potential ways a hazard can arise and to ensure that the AI can handle hazardous situations safely. We need to shift our safety approach to focus more on finding ways to effectively handle unforeseen events.
We require strong risk management systems, often including a human-in-the-loop safety option. In this scenario, a human supervisor is supposed to intervene when necessary.It is important for autonomous machinery to be able to operate without relying on human intervention, as human intervention is not always practical. According to de Koning, when automation is used, there can be noticeable declines in human performance, including boredom, confusion, cognitive abilities, loss of situational awareness, and automation bias. These factors have a significant impact on safety, and it is essential for a machine to be able to safely manage its own behavior.
“My approach takes into account hazards associated with AI-driven decision-making, risk assessment, and adaptability to unforeseen scenarios. I believe it is crucial to actively collaborate with industry partners to ensure real-world applicability.”Thank you. She suggests that by working with manufacturers, it is possible to close the gap between theoretical frameworks and practical implementation. The framework aims to assist OEMs in designing and developing safety systems that comply with regulations and evolve with time. Marea de Koning began her research in November 2020 and plans to complete it by November 2024. The project is funded in part by the Doctoral School of Industry Innovations and in part by a Finnish system supplier. Her next step is to integrate the framework into existing machinery.The research project, which will start in April, will concentrate on integrating a portion of her safety framework and thoroughly testing its effectiveness. Regulation 2023/1230 will replace Directive 2006/42/ec as of January 2027, posing significant challenges for OEMs.
“I am making every effort to ensure that safety remains a top priority in technological advancements,” she states.
The research offers valuable insights for policymakers, engineers, and safety professionals. The article presenting the findings titled A Comprehensive Approach to Safety for Highly Automated Off-Road Machinery under Regulation 2023/1230 was published in the prestigious
Journal Reference:
- Marea de Koning, Tyrone Machado, Andrei Ahonen, Nataliya Strokina, Morteza Dianatfar, Fransesco De Rosa, Tatiana Minav, Reza Ghabcheloo. A comprehensive approach to safety for highly automated off-road machinery under Regulation 2023/1230. Safety Science, 2024; 175: 106517 DOI: 10.1016/j.ssci.2024.106517