Pedestrian tactical choices and operational movement in evacuations essentially pertain to decision-making under risk and uncertainty. However, in microscopic evacuation models, this attribute has been greatly overlooked, even lacking a methodology to delineate the related decision characteristics (bounded rationality and risk attitudes), let alone their effects on evacuation processes. This work presents an innovative two-layer floor field cellular automaton model framework, where three intertwined sub-modules respectively dedicated to modelling the exit choice, the locomotion movement and the exit-choice changing behaviours are proposed and integrated as an entity. By introducing various decision-making elements computed by the proposed algorithm, Cumulative Prospect Theory (CPT) is proposed for the first time to model the exit choice and locomotion decision-making under risk and uncertainty. In the exit-choice changing module, attractive and repulsive forces are invented to jointly describe the tendency to revisit the routing decision. Each sub-module and the whole framework are validated in manifold indoor environments. The simulation results of the modules with CPT accord with the empirics from the evacuation experiments and are superior over those from the state-of-the-art models. The degree of rationality and risk attitudes are proven to have significant impacts on tactical and operational decisions. Furthermore, irrational behaviour in decision-making is not variably detrimental to locomotion efficiency of pedestrians. The proposed framework can serve as an elegant tool to predict pedestrian dynamics. The behavioural findings shed new light on understanding and modelling the tactical and operational decisions in evacuations.

Numerous evacuation performance data for the utilization in evacuation modelling and simulations have been established for the conventional/widely studied scenarios, such as building evacuation scenarios. However, such data are typically scarce for a new scenario in literature — evacuation from high-deck coaches. This paper fulfills this gap by presenting empirical high-deck coach evacuation data-sets that can be used for model configuration and validation. To this end, firstly, five essential and commonly used performance metrics, i.e., evacuation time, flow rate, alighting time gap, velocity on stairways and exit choice, were collected and derived from two series of controlled experiments with 7 and 22 runs that involved 44 and 96 participants respectively. Then, all these datasets were structured in the distribution form, based on which three critical behavioural insights are revealed regardless of the evacuation conditions (the types of high-deck coaches, lighting conditions, and age groups). First, the evacuation behaviour in normal (experimental) conditions conforms to a multi-stage pattern (a modified four-stage pattern, i.e., reaction, acceleration, fluctuation and saturation stages). Second, the instantaneous flow rate can be well captured by the Burr, Loglogistic and Lognormal distributions, and the alighting time gap can be represented by the Burr distribution. Third, more than 50% of passengers evacuate through the rear door in the front-and-rear-door evacuations. The frequency of choosing the front door is found to shift towards the direction of the rear door compared to the ideal results (based on the shortest distance calculation) with a magnitude of approximately 1.95 seat rows. The presented data-sets are valuable resources for the development of high-deck coach evacuation models. The empirical findings promote the understanding upon the evacuation behaviour of high-deck coach passengers.

With increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This has motivated regulation efforts, including the Proposal of an EU AI Act. This interdisciplinary position paper considers various concerns surrounding fairness and discrimination in AI, and discusses how AI regulations address them, focusing on (but not limited to) the Proposal. We first look at AI and fairness through the lenses of law, (AI) industry, sociotechnology, and (moral) philosophy, and present various perspectives. Then, we map these perspectives along three axes of interests: (i) Standardization vs. Localization, (ii) Utilitarianism vs. Egalitarianism, and (iii) Consequential vs. Deontological ethics which leads us to identify a pattern of common arguments and tensions between these axes. Positioning the discussion within the axes of interest and with a focus on reconciling the key tensions, we identify and propose the roles AI Regulation should take to make the endeavor of the AI Act a success in terms of AI fairness concerns.

High-deck coaches form an essential component of mass transportation systems in China. Safe evacuation from high-deck coaches is facing dire challenges. However, evacuation behaviour from high-deck coaches has not been deeply understood yet. In this study, a novel conceptual framework is firstly proposed to capture the evacuation behaviour of coach passengers, and next based on which 22 full-scale experiments have been conducted to examine the effect of three selected factors: available exits, lighting conditions and age groups on the evacuation behaviour of Chinese passengers in a high-deck coach, in a systematic and quantitative way. Four performance indicators of evacuation behaviour, i.e., evacuation time, pre-evacuation time, flow rate and crowdedness, were collected and analysed. The results indicate that limited available exits and the dim lighting condition (less than 1 lux) significantly reduce the evacuation efficiency and increase the crowdedness within the aisle area regardless of the age groups. Compared to young students, the evacuation of middle-aged people is observed to have a significantly longer pre-evacuation time, lower evacuation efficiency, and higher level of crowdedness. In addition, young students’ pre-evacuation times are found to conform to the Weibull distribution, whereas middle-aged people’ pre-evacuation times could be modelled with the Loglogistic distribution. Empirical results of this study could be helpful for the improvement of the safety design of high-deck coaches, and provide valuable benchmarks for the development of coach evacuation behaviour and simulation models.