Showing cs.ROShow all
3 papers · 1 filter
cs.RO2025
Beyond Features: How Dataset Design Influences Multi-Agent Trajectory Prediction Performance
Tobias Demmler, Jakob Häringer, Andreas Tamke +3
Accurate trajectory prediction is critical for safe autonomous navigation, yet the impact of dataset design on model performance remains understudied. This work systematically exam…
cs.RO2025
Dynamic Intent Queries for Motion Transformer-based Trajectory Prediction
Tobias Demmler, Lennart Hartung, Andreas Tamke +4
In autonomous driving, accurately predicting the movements of other traffic participants is crucial, as it significantly influences a vehicle's planning processes. Modern trajector…
cs.RO2024
Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention
Tobias Demmler, Andreas Tamke, Thao Dang +2
In autonomous driving, accurately interpreting the movements of other road users and leveraging this knowledge to forecast future trajectories is crucial. This is typically achieve…