SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
This work addresses trajectory prediction for autonomous systems in crowded environments, representing an incremental improvement over existing LSTM-based methods.
The paper tackles pedestrian trajectory prediction in crowd scenarios by proposing SR-LSTM, a state refinement module for LSTM that incorporates current neighbor intentions through message passing, achieving state-of-the-art results on ETH and UCY datasets.
In crowd scenarios, reliable trajectory prediction of pedestrians requires insightful understanding of their social behaviors. These behaviors have been well investigated by plenty of studies, while it is hard to be fully expressed by hand-craft rules. Recent studies based on LSTM networks have shown great ability to learn social behaviors. However, many of these methods rely on previous neighboring hidden states but ignore the important current intention of the neighbors. In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism. To effectively extract the social effect of neighbors, we further introduce a social-aware information selection mechanism consisting of an element-wise motion gate and a pedestrian-wise attention to select useful message from neighboring pedestrians. Experimental results on two public datasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed SR-LSTM and we achieves state-of-the-art results.