CDJMP: an adaptive conditional diffusion model for multi-agent joint motion prediction in autonomous driving

In autonomous driving trajectory prediction, it is important to generate multi-modal trajectories. As a generative method, diffusion model has been increasingly adopted in the field of trajectory prediction. In this paper, we propose CDJMP (Conditional Diffusion model-based Joint Motion Prediction), an adaptive conditional diffusion framework designed for multi-agent trajectory forecasting in autonomous driving. However, when conventional diffusion models generate multi-modal trajectories, particularly for multi-agent joint prediction, they often fail to balance the diversity of generated trajectories and the accuracy of prediction. At the same time, diffusion models also suffer from time-consuming inference. To address these issues, CDJMP utilizes a two-stage framework to generate diverse and highly accurate trajectories. In the first stage, a probabilistic initializer predicts proposal trajectories together with adaptive denoising steps. In the second stage, a group-aware conditional encoder captures dynamic multi-agent interactions and guides the diffusion process to produce coherent multimodal outcomes. Experiments on the INTERACTION and Argoverse datasets demonstrate that CDJMP achieves state-of-the-art performance, reducing minADE and minFDE by up to 9% and 10%, respectively, on the INTERACTION dataset. Ablation experiments demonstrate that CDJMP can effectively reduce inference time while maintaining prediction accuracy. These results highlight the potential of CDJMP as an efficient and accurate framework for real-time multi-agent trajectory prediction in autonomous driving.