SCENE: Reasoning About Traffic Scenes Using Heterogeneous Graph Neural Networks

Monninger, Thomas; Schmidt, Julian; Rupprecht, Jan; David, Raba,; Jordan, Julian; Frank, Daniel N.; Staab, Steffen; Dietmayer, Klaus

doi:10.1109/lra.2023.3234771

Cited by 14 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated the effectiveness of the proposed method with various GNN architectures. While we used 5-Layer GIN as the GNN architecture in the main experiments, we explored the suitability of other commonly used GNN architectures that are capable of handling edge features: MPNN, graph attention network (GAT), , graph transformer network (GTN), and 3-Layer GIN. Table S2 presents the predictive performance of pretrained GNNs using these architectures on the METLIN-SMRT data set.…”

Section: Resultsmentioning

confidence: 99%

Retention Time Prediction through Learning from a Small Training Data Set with a Pretrained Graph Neural Network

Kwon,

Han

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

Graph neural networks (GNNs) have shown remarkable performance in predicting the retention time (RT) for small molecules. However, the training data set for a particular target chromatographic system tends to exhibit scarcity, which poses a challenge because the experimental process for measuring RT is costly. To address this challenge, transfer learning has been used to leverage an abundant training data set from a related source task. In this study, we present an improved transfer learning method to better predict the RT of molecules for a target chromatographic system by learning from a small training data set with a pretrained GNN. We use a graph isomorphism network as the architecture of the GNN. The GNN is pretrained on the METLIN-SMRT data set and is then fine-tuned on the target training data set for a fixed number of training iterations using the limitedmemory Broyden−Fletcher−Goldfarb−Shanno optimizer with a learning rate decay. We demonstrate that the proposed method achieves superior predictive performance on various chromatographic systems compared with that of the existing transfer learning methods, especially when only a small training data set is available for use. A potential avenue for future research is to leverage multiple small training data sets from different chromatographic systems to further enhance the generalization performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Retention Time Prediction through Learning from a Small Training Data Set with a Pretrained Graph Neural Network

Kwon,

Han

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…We found that the rejection method is very effective regarding safety considerations. For future work, a more sophisticated approach could use a generic graph encoding [24] and formulate the TL2LA task as link prediction in graphs.…”

Section: Discussionmentioning

confidence: 99%

Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data

Monninger,

Weber,

Staab

2023

2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)

Self Cite

View full text Add to dashboard Cite

Understanding which traffic light controls which lane is crucial to navigate intersections safely. Autonomous vehicles commonly rely on High Definition (HD) maps that contain information about the assignment of traffic lights to lanes. The manual provisioning of this information is tedious, expensive, and not scalable. To remedy these issues, our novel approach derives the assignments from traffic light states and the corresponding motion patterns of vehicle traffic. This works in an automated way and independently of the geometric arrangement. We show the effectiveness of basic statistical approaches for this task by implementing and evaluating a pattern-based contribution method. In addition, our novel rejection method includes accompanying safety considerations by leveraging statistical hypothesis testing. Finally, we propose a dataset transformation to re-purpose available motion prediction datasets for semantic map learning. Our publicly available API for the Lyft Level 5 dataset enables researchers to develop and evaluate their own approaches 5 .

show abstract

“…The publicly available source code of our navigation map API for Argoverse enables other researchers to develop and evaluate their own navigation map-based approaches for motion prediction with ease. It remains to be investigated whether similar results are achievable using navigation maps in other HD map-reliant application areas beyond motion prediction, for instance traffic scene reasoning [35].…”

Section: Discussionmentioning

confidence: 99%

CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention

Schmidt

Jordan

Gritschneder

et al. 2022

2022 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

The prediction of surrounding agents' motion is a key for safe autonomous driving. In this paper, we explore navigation maps as an alternative to the predominant High Definition (HD) maps for learning-based motion prediction. Navigation maps provide topological and geometrical information on road-level, HD maps additionally have centimeteraccurate lane-level information. As a result, HD maps are costly and time-consuming to obtain, while navigation maps with near-global coverage are freely available. We describe an approach to integrate navigation maps into learningbased motion prediction models. To exploit locally available HD maps during training, we additionally propose a modelagnostic method for knowledge distillation. In experiments on the publicly available Argoverse dataset with navigation maps obtained from OpenStreetMap, our approach shows a significant improvement over not using a map at all. Combined with our method for knowledge distillation, we achieve results that are close to the original HD map-reliant models. Our publicly available navigation map API for Argoverse enables researchers to develop and evaluate their own approaches using navigation maps 4 .

show abstract

SCENE: Reasoning About Traffic Scenes Using Heterogeneous Graph Neural Networks

Cited by 14 publications

References 27 publications

Retention Time Prediction through Learning from a Small Training Data Set with a Pretrained Graph Neural Network

Retention Time Prediction through Learning from a Small Training Data Set with a Pretrained Graph Neural Network

Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data

CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention

Contact Info

Product

Resources

About