Mehrnoosh Askarpour

Mehrnoosh Askarpour, Alan Wassyng, Mark Lawford et al.

Machine learning (ML) is finding its way into safety-critical systems (SCS). Current safety standards and practice were not designed to cope with ML techniques, and it is difficult to be confident that SCSs that contain ML components are safe. Our hypothesis was that there has been a rush to deploy ML techniques at the expense of a thorough examination as to whether the use of ML techniques introduces safety problems that we are not yet adequately able to detect and mitigate against. We thus conducted a targeted literature survey to determine the research effort that has been expended in applying ML to SCS compared with that spent on evaluating the safety of SCSs that deploy ML components. This paper presents the (surprising) results of the survey.

Mehrnoosh Askarpour

Human-robot collaboration (HRC) is an emerging trend of robotics that promotes the co-presence and cooperation of humans and robots in common workspaces. Physical vicinity and interaction between humans and robots, combined with the uncertainty of human behaviour, could lead to undesired situations where humans are injured. Thus, safety is a priority for HRC applications. Safety analysis via formal modelling and verification techniques could considerably avoid dangerous consequences, but only if the models of HRC systems are comprehensive and realistic, which requires reasonably realistic models of human behaviour. This paper explores state-of-the-art solutions for modelling human and discusses which ones are suitable for HRC scenarios.