Cognitive prediction of obstacle's movement for reinforcement learning pedestrian interacting model

Recent studies in pedestrian simulation have been able to construct a highly realistic navigation behaviour in many circumstances. However, when replicating the close interactions between pedestrians, the replicated behaviour is often unnatural and lacks human likeness. One of the possible reasons is that the current models often ignore the cognitive factors in the human thinking process. Another reason is that many models try to approach the problem by optimising certain objectives. On the other hand, in real life, humans do not always take the most optimised decisions, particularly when interacting with other people. To improve the navigation behaviour in this circumstance, we proposed a pedestrian interacting model using reinforcement learning. Additionally, a novel cognitive prediction model, inspired by the predictive system of human cognition, is also incorporated. This helps the pedestrian agent in our model to learn to interact and predict the movement in a similar practice as humans. In our experimental results, when compared to other models, the path taken by our model’s agent is not the most optimised in certain aspects like path lengths, time taken and collisions. However, our model is able to demonstrate a more natural and human-like navigation behaviour, particularly in complex interaction settings.

3D Indoor Environment Abstraction for Crowd Simulations in Complex Buildings

This paper presents an approach for the automatic abstraction of built environments needed for pedestrian dynamics from any building configuration. The approach assesses the usability of navigation mesh to perform realistically pedestrian simulation considering the physical structure and pedestrian abilities for it. Several steps are examined including the creation of a navigation mesh, space subdivision, border extraction, height map identification, stairs classification and parametrisation, as well as pedestrian simulation. A social-force model is utilised to simulate the interactions between pedestrians and an environment. To perform quickly different 2D/3D geometrical queries various spatial indexing techniques are used, allowing fast identification of navigable spaces and proximity checks related to avoidance of people and obstacles in built environments. For example, for a moderate size building having eight floors and a net area of 13,000 m2, it takes only 104 s to extract the required building information to run a simulation. This approach can be used for any building configuration extracting automatically needed features to run pedestrian simulations. In this way, architects, urban planners, fire safety engineers, transport modellers and many other users without the need to manually interact with a building model can perform immediately crowd simulations.

Subdivided Cellular Automata Model Considering Anticipation Floor Field and Analysis of Pedestrian Detour Behavior

The micro-pedestrian simulation model represented by the cellular automata model is an important simulation model. Improvements in various aspects enable a better description of the various behaviors of pedestrians, such as pedestrian avoidance behavior, companion behavior, as well as transcendence behavior, waiting behavior and detour behavior. This paper takes the pedestrian detour behavior in the circle antipode experiment as the main entry point. The subdivision cellular automaton model is integrated into the prediction field to model and simulate the detour behavior. At the same time, it explores the degree of subdivision of the cell. Pedestrian heterogeneity and the influence of predicted field potential energy on the simulated pedestrian trajectory. Finally, based on the temporal and spatial indicators of pedestrian trajectory characteristics, the KS test and DTW method are used to evaluate the similarity of the trajectory distribution characteristics and time series characteristics with experimental samples, and evaluate and compare models with or without heterogeneity. The results show that the trajectory characteristics of heterogeneous pedestrians are closer to the experiment than homogeneous pedestrians.

Pedestrian Simulation In SUMO Through Externally Modelled Agents

Pedestrian simulation is often forgotten or implemented poorly in most high profile traffic simulators. This is the case of SUMO, where the pedestrian models are very simple and not based in real human behaviour, making it impossible to study pedestrian safety with it. With this in mind, the ability to externally control pedestrians in SUMO was explored. Using Unity3D to create an external three dimensional representation of a running SUMO simulation, we were able to create and control pedestrians through the TraCI API. This also opened the possibility to use virtual reality immersed subjects to participate in the simulation, opening the door to study real pedestrian behaviour to create more elaborate models. It also allowed us to completely offload the pedestrian simulation from SUMO to Unity3D, which was tested with the external implementation of the social forces model, without losing SUMO's interactions between pedestrians and motorized vehicles.