Konstantinidis, Fabian (CARIAD SE), Dallari Guerreiro, Ariel (Technical University of Munich), Trumpp, Raphael (Technical University of Munich), Sackmann, Moritz (CARIAD SE), Hofmann, Ulrich (CARIAD SE Ingolstadt), Caccamo, Marco (Technical University of Munich), Stiller, Christoph (Karlsruhe Institute of Technology)

From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving

Scheduled for presentation during the Regular Session "S31a-AI-Driven Motion Prediction and Safe Control for Autonomous Systems" (FR-LM-T31), Friday, November 21, 2025, 11:50−12:10, Southport 1

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Accurate motion prediction of surrounding traffic participants is crucial for the safe and efficient operation of automated vehicles in dynamic environments. Marginal prediction models commonly forecast each agent's future trajectories independently, often leading to inconsistent planning decisions for an automated vehicle. In contrast, joint prediction models explicitly account for the interactions between agents, yielding socially and physically consistent predictions on a scene level. However, existing approaches differ not only in their problem formulation but also in the model architectures and implementation details used, making it difficult to compare them. In this work, we systematically investigate different approaches to joint motion prediction, including post-processing of the marginal predictions, explicitly training the model for joint predictions, and framing the problem as a generative task. We evaluate each approach in terms of prediction accuracy, multi-modality, and inference efficiency, offering a comprehensive analysis of the strengths and limitations of each approach.