DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting
This addresses trajectory forecasting for autonomous agents like self-driving cars, but it appears incremental as it builds on existing attention and graph neural network methods.
The paper tackles the problem of multi-modal human trajectory forecasting by proposing a recurrent generative model that incorporates both individual agents' future goals and interactions between agents, achieving state-of-the-art results in urban and sports environments.
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric environment. This is non-trivial because human motion is inherently multi-modal: given a history of human motion paths, there are many plausible ways by which people could move in the future. Additionally, people activities are often driven by goals, e.g. reaching particular locations or interacting with the environment. We address the aforementioned aspects by proposing a new recurrent generative model that considers both single agents' future goals and interactions between different agents. The model exploits a double attention-based graph neural network to collect information about the mutual influences among different agents and to integrate it with data about agents' possible future objectives. Our proposal is general enough to be applied to different scenarios: the model achieves state-of-the-art results in both urban environments and also in sports applications.