Scene-Aware Explainable Multimodal Trajectory Prediction
This work addresses the need for interpretable and accurate trajectory prediction in complex traffic environments, which is crucial for the practical deployment of automated vehicles, though it is incremental in combining existing techniques.
The paper tackles the problem of lacking explainability and joint reasoning in trajectory prediction for automated vehicles by introducing an explainable conditional diffusion-based multimodal model, which significantly outperforms baseline models in accuracy on the Waymo Open Motion Dataset.
Advancements in intelligent technologies have significantly improved navigation in complex traffic environments by enhancing environment perception and trajectory prediction for automated vehicles. However, current research often overlooks the joint reasoning of scenario agents and lacks explainability in trajectory prediction models, limiting their practical use in real-world situations. To address this, we introduce the Explainable Conditional Diffusion-based Multimodal Trajectory Prediction (DMTP) model, which is designed to elucidate the environmental factors influencing predictions and reveal the underlying mechanisms. Our model integrates a modified conditional diffusion approach to capture multimodal trajectory patterns and employs a revised Shapley Value model to assess the significance of global and scenario-specific features. Experiments using the Waymo Open Motion Dataset demonstrate that our explainable model excels in identifying critical inputs and significantly outperforms baseline models in accuracy. Moreover, the factors identified align with the human driving experience, underscoring the model's effectiveness in learning accurate predictions. Code is available in our open-source repository: https://github.com/ocean-luna/Explainable-Prediction.