Demmler, Tobias (Robert Bosch GmbH), Häringer, Jakob (Robert Bosch GmbH), Tamke, Andreas (Bosch), Dang, Thao (University of Applied Sciences, Esslingen), Hegai, Alexander (Robert Bosch GmbH), Mikelsons, Lars (Augsburg University)

Beyond Features: How Dataset Design Influences Multi-Agent Trajectory Prediction Performance

Scheduled for presentation during the Regular Session "S08b-Intelligent Modeling and Prediction of Traffic Dynamics" (WE-EA-T8), Wednesday, November 19, 2025, 14:50−15:10, Coolangata 2

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 April 1, 2026

Abstract

Accurate trajectory prediction is critical for safe autonomous navigation, yet the impact of dataset design on model performance remains understudied. This work systematically examines how feature selection, cross-dataset transfer, and geographic diversity influence trajectory prediction accuracy in multi-agent settings. We evaluate a state-of-the-art model using our novel L4 Motion Forecasting dataset based on our own data recordings in Germany and the US. This includes enhanced map and agent features. We compare our dataset to the US-centric Argoverse 2 benchmark. First, we find that incorporating supplementary map and agent features unique to our dataset, yields no measurable improvement over baseline features, demonstrating that modern architectures do not need extensive feature sets for optimal performance. The limited features of public datasets are sufficient to capture convoluted interactions without added complexity. Second, we perform cross-dataset experiments to evaluate how effective domain knowledge can be transferred between datasets. Third, we group our dataset by country and check the knowledge transfer between different driving cultures.