# Vectorized Scenario Description and Motion Prediction for Scenario-Based Testing

arXiv: https://arxiv.org/abs/2302.01161 · HTML: https://mlsanity.com/paper/2302.01161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 11 of 11)

- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios](https://mlsanity.com/paper/2210.06609/) (2022)
- [SceneGen: Learning to Generate Realistic Traffic Scenes](https://mlsanity.com/paper/2101.06541/) (2021)
- [A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems](https://mlsanity.com/paper/2005.02979/) (2020)
- [Scenarios for Development, Test and Validation of Automated Vehicles](https://mlsanity.com/paper/1801.08598/) (2018)
- [6-Layer Model for a Structured Description and Categorization of Urban Traffic and Environment](https://mlsanity.com/paper/2012.06319/) (2020)
- [Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review](https://mlsanity.com/paper/2110.08664/) (2021)
- [Finding Failures in High-Fidelity Simulation using Adaptive Stress Testing and the Backward Algorithm](https://mlsanity.com/paper/2107.12940/) (2021)
- [Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios](https://mlsanity.com/paper/2110.02892/) (2021)
- [Toward a Consistent Taxonomy for Scenario-Based Development and Test Approaches for Automated Vehicles: A Proposal for a Structuring Framework, a Basic Vocabulary, and its Application](https://mlsanity.com/paper/2104.09097/) (2021)
- [Transfer Importance Sampling -- How Testing Automated Vehicles in Multiple Test Setups Helps With the Bias-Variance Tradeoff](https://mlsanity.com/paper/2204.07619/) (2022)

## Abstract (arXiv)

Automated vehicles (AVs) are tested in diverse scenarios, typically specified by parameters such as velocities, distances, or curve radii. To describe scenarios uniformly independent of such parameters, this paper proposes a vectorized scenario description defined by the road geometry and vehicles' trajectories. Data of this form are generated for three scenarios, merged, and used to train the motion prediction model VectorNet, allowing to predict an AV's trajectory for unseen scenarios. Predicting scenario evaluation metrics, VectorNet partially achieves lower errors than regression models that separately process the three scenarios' data. However, for comprehensive generalization, sufficient variance in the training data must be ensured. Thus, contrary to existing methods, our proposed method can merge diverse scenarios' data and exploit spatial and temporal nuances in the vectorized scenario description. As a result, data from specified test scenarios and real-world scenarios can be compared and combined for (predictive) analyses and scenario selection.