Agent‐based approach for crowded pedestrian evacuation simulation

Automated analysis of pedestrian walking behaviour at a signalised intersection in China

“…In particular, collision avoidance and safety monitoring applications can greatly benefit of the automatic identification of violators [59][60][61]. The results in this paper, can also be used during the calibration of pedestrian simulation models [62,63]. Such research direction is currently under investigation at the UBC transportation research team, with promising early results indicate the benefits of using gait attributes in improving pedestrian modelling.…”

An Enhanced Model-Free Reinforcement Learning Algorithm to Solve Nash Equilibrium for Multi-Agent Cooperative Game Systems

“…According to [25], [26], for fixed neighbor policies u −i = {u j : j ∈ N i }, assume there exist an admissible policy u i . Let Q π * i (ε ik , u * ik ) satisfying (32) or (33), and agent i uses control policy (18). Then:…”

“…Multiagent RL algorithms can be model-based or model-free [16], [17], where models are used to represent environments. Normally, models can be very helpful for the agent to deal with various situations and choose the best action [18]. However, the model building process requires a lot of information and time [19].…”

Exploring Trust in Tsunami Evacuation Decision: An Initial Study

“…However, although the government has prepared and implemented an evacuation strategy, there are some people who are relatively hard to engage in the evacuation activity when disasters occur. According to a study by [6], this might happen due to their different human behavior. The researchers claimed that human behaviors are somewhat random and difficult to model since different people would have different perceptions of danger and would react differently to emergencies.…”