Qualitative Prediction of Multi-Agent Spatial Interactions
This work addresses the need for service robots to reason about interactions in crowded environments, but it is incremental as it builds on existing methods like the Qualitative Trajectory Calculus and deep neural networks.
The paper tackled the problem of predicting multi-agent spatial interactions in dense, dynamic scenes by proposing three new approaches, including a qualitative representation, and found that the purely data-driven method generally outperformed the others on a robot dataset.
Deploying service robots in our daily life, whether in restaurants, warehouses or hospitals, calls for the need to reason on the interactions happening in dense and dynamic scenes. In this paper, we present and benchmark three new approaches to model and predict multi-agent interactions in dense scenes, including the use of an intuitive qualitative representation. The proposed solutions take into account static and dynamic context to predict individual interactions. They exploit an input- and a temporal-attention mechanism, and are tested on medium and long-term time horizons. The first two approaches integrate different relations from the so-called Qualitative Trajectory Calculus (QTC) within a state-of-the-art deep neural network to create a symbol-driven neural architecture for predicting spatial interactions. The third approach implements a purely data-driven network for motion prediction, the output of which is post-processed to predict QTC spatial interactions. Experimental results on a popular robot dataset of challenging crowded scenarios show that the purely data-driven prediction approach generally outperforms the other two. The three approaches were further evaluated on a different but related human scenarios to assess their generalisation capability.