An End-to-End Learning Approach for Trajectory Prediction in Pedestrian Zones
arXiv:2004.04787v21 citations
Originality Synthesis-oriented
AI Analysis
This addresses trajectory prediction for pedestrian zones, but appears incremental as it builds on existing attention-based methods.
The paper tackles trajectory prediction in heterogeneous pedestrian zones by proposing an end-to-end learning framework with an attention mechanism to improve accuracy, though no concrete numbers are provided.
This paper aims to explore the problem of trajectory prediction in heterogeneous pedestrian zones, where social dynamics representation is a big challenge. Proposed is an end-to-end learning framework for prediction accuracy improvement based on an attention mechanism to learn social interaction from multi-factor inputs.