Browsing by Subject "Trajectory prediction"
Now showing 1 - 1 of 1
- Results Per Page
- Sort Options
Item On the motion and action prediction using deep graph models(2022-07-01) Mohamed, Abduallah Adel Omar; Tewfik, Ahmed; Claudel, Christian; Bovik, Alan; Thomaz, Edison; Boyles, StephenMotion and action prediction is a crucial component of autonomous systems and robotics. This component is vital for accidents predictions or prevention, motion planning, surveillance systems and behavior analysis. Typically, the problem involves the observation of multiple agents’ motion or actions across a span of time then predict the future motion and actions. Classical approaches which are model based failed in the complex situations that require a proper modeling of the interactions between the agents. Data driven approaches, specifically deep learning ones, had a better performance in modeling these interactions. Yet, these deep models were using classical deep learning techniques, such as recurrent and convolutional architectures. These approaches are not representative of the spatial and temporal aspects of the observations. This dissertation presents novel approaches using spatio-temporal graphs to model the observations. We model each agent as a graph node and define their spatial configuration by using the graph edges. For the temporal relationship, we represent it by propagating the graph nodes across time. This representation is powerful in capturing the spatial and temporal relationships in comparison with prior methods. Also, several deep architectures based on graph convolutional neural networks were investigated. These architectures were explored from different perspectives, such as the kernel function of the graph edges and the embedding representation of the spatio-temporal relationships in both observations and predictions. Also, the proposed models are shown to have real run-time capabilities in comparison with prior methods. Besides, the shortcomings of current evaluation metrics in assessing the quality of motion prediction models were investigated in which new metrics were proposed.