SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs

TL;DR

SemanticFormer introduces a holistic approach for trajectory prediction in autonomous driving by reasoning over semantic traffic scene graphs with high-level meta-paths, improving accuracy and integrating with existing methods.

Contribution

The paper presents SemanticFormer, a novel hybrid model that uses knowledge graphs and attention mechanisms for more accurate multimodal trajectory prediction.

Findings

Outperforms several state-of-the-art methods on nuScenes benchmark.

Enhances existing graph-based models (VectorNet, Laformer) by integrating knowledge graphs, boosting performance.

Achieves 5% and 4% performance improvements when added to VectorNet and Laformer, respectively.

Abstract

Trajectory prediction in autonomous driving relies on accurate representation of all relevant contexts of the driving scene, including traffic participants, road topology, traffic signs, as well as their semantic relations to each other. Despite increased attention to this issue, most approaches in trajectory prediction do not consider all of these factors sufficiently. We present SemanticFormer, an approach for predicting multimodal trajectories by reasoning over a semantic traffic scene graph using a hybrid approach. It utilizes high-level information in the form of meta-paths, i.e. trajectories on which an agent is allowed to drive from a knowledge graph which is then processed by a novel pipeline based on multiple attention mechanisms to predict accurate trajectories. SemanticFormer comprises a hierarchical heterogeneous graph encoder to capture spatio-temporal and relational information across agents as well as between agents and road elements. Further, it includes a predictor to fuse different encodings and decode trajectories with probabilities. Finally, a refinement module assesses permitted meta-paths of trajectories and speed profiles to obtain final predicted trajectories. Evaluation of the nuScenes benchmark demonstrates improved performance compared to several SOTA methods. In addition, we demonstrate that our knowledge graph can be easily added to two graph-based existing SOTA methods, namely VectorNet and Laformer, replacing their original homogeneous graphs. The evaluation results suggest that by adding our knowledge graph the performance of the original methods is enhanced by 5% and 4%, respectively.