Modelling realistic human behaviours in simulation is an ongoing challenge that resides between several fields like social sciences, philosophy, and artificial intelligence. Human movement is a special type of behaviour driven by intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Services available online and offline do not normally consider the environment when planning a path, which is decisive especially on a leisure trip. Two novel algorithms have been presented to generate human-like trajectories based on environmental features. The Attraction-Based A* algorithm includes in its computation information from the environmental features meanwhile, the Feature-Based A* algorithm also injects information from the real trajectories in its computation. The human-likeness aspect has been tested by a human expert judging the final generated trajectories as realistic. This paper presents a comparison between the two approaches in some key metrics like efficiency, efficacy, and hyper-parameters sensitivity. We show how, despite generating trajectories that are closer to the real one according to our predefined metrics, the Feature-Based A* algorithm fall short in time efficiency compared to the Attraction-Based A* algorithm, hindering the usability of the model in the real world.

Modelling realistic human behaviour in simulation is an ongoing challenge that sits between several fields like social sciences, philosophy, and artificial intelligence. Human movement is a special type of behaviour driven by intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Services available online and offline do not normally consider the environment when planning the path, which is decisive especially on a leisure trip. This paper presents a comparison between different generative methods and variations of a path planning algorithm for the task of generating human- like trajectories based on environmental features. We show how a modified version of the well known A* algorithm outperforms different generative methods by computed evaluation metrics and by a human assessor for the task of generating bike trips in the area around Ljubljana, Slovenia.

This paper presents a new general framework for turning any auto-encoder into a generative model. Here, we focus on a specific instantiation of the auto-encoder that consists of the Short Time Fourier Transform as an encoder, and a composition of the Griffin-Lim Algo- rithm and the pseudo inverse of the Short Time Fourier Transform as a decoder. In order to allow sampling from this model, we propose to use the probabilistic Principal Component Analysis. We show preliminary results on the UrbanSound8K Dataset..

Modelling human behaviour in simulation is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Humans normally move driven by their intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Normal services available online and offline do not consider the environment when planning the path. Especially on a leisure trip, this is very important. This paper presents a comparison between different machine learning algorithms and a famous path planning algorithm in the task of generating human- like trajectories based on environmental features. We show how a modified version of the well known A* algorithm outperforms different machine learning algorithms by computed evaluation metrics and human evaluation in the task of generating bike trips in the area around Ljubljana, Slovenia.

Modelling human behaviour is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Since the research of a metric able to define all the aspect of the human nature is still an ambitious task, most current studies use concepts like social forces or handwritten rules for modelling. Following the growing trend behind a new branch of Artificial Intelligence called Generative AI, this paper presents the application of Turing Learning on the problem of modelling human movements. Turing Learning is a generative model that uses evolutionary algorithms as a way to learn behaviours without the need for predefined metrics and, using deep learning models, it is able to produce human-like trajectories. We show how the system is able to infer the behaviours of the trajectories in the ETH dataset, forecasting the next points with the truthfulness of being a possible human movement.