From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909677699203072 |
|---|---|
| author | Konstantinidis, Fabian Guerreiro, Ariel Dallari Trumpp, Raphael Sackmann, Moritz Hofmann, Ulrich Caccamo, Marco Stiller, Christoph |
| author_facet | Konstantinidis, Fabian Guerreiro, Ariel Dallari Trumpp, Raphael Sackmann, Moritz Hofmann, Ulrich Caccamo, Marco Stiller, Christoph |
| contents | 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 sub-optimal 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. Several prediction examples are available at https://frommarginaltojointpred.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05254 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving Konstantinidis, Fabian Guerreiro, Ariel Dallari Trumpp, Raphael Sackmann, Moritz Hofmann, Ulrich Caccamo, Marco Stiller, Christoph Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multiagent Systems Robotics 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 sub-optimal 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. Several prediction examples are available at https://frommarginaltojointpred.github.io/. |
| title | From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multiagent Systems Robotics |
| url | https://arxiv.org/abs/2507.05254 |