Long-term Traffic Scene Prediction via Polynomial Representations in Autonomous Driving

2026-08-04

AI Summary

This work addresses the challenges of noise robustness, generalization, and computational efficiency in traffic scene prediction for autonomous driving by proposing a unified representation of vehicle trajectories and map geometry using medium-order polynomials, integrated within a diffusion-based multi-agent scene generation framework. The approach preserves trajectory smoothness and behavioral plausibility while significantly enhancing cross-dataset generalization and inference efficiency. Experimental results on benchmarks such as Argoverse 2 and Waymo Open demonstrate that the method achieves near state-of-the-art prediction accuracy, with notable advantages in out-of-distribution generalization, computational overhead, and long-term prediction coherence.

Abstract

This thesis addresses fundamental challenges in traffic scene prediction for autonomous driving by introducing robust and computationally efficient models based on polynomial representations. While conventional sequence-based representations often struggle with noise and generalization, this work demonstrates that polynomial representations offer significant advantages in computational efficiency, generalization, and prediction plausibility. Through theoretical analysis and empirical validation, this thesis demonstrates that moderate-degree polynomials capture real-world motion dynamics with high fidelity without constraining predictive performance. Building on this foundation, a prediction model representing both trajectories and map geometry with polynomial representations achieves near state-of-the-art accuracy on standard benchmarks while substantially improving generalization under distribution shift. Extending this concept, a diffusion- based generative framework enables multi-agent scene generation, producing traffic continuations that are more plausible and kinematically consistent than those generated by conventional baselines. Evaluations on the Argoverse 2 and Waymo Open datasets confirm that polynomial representations reduce computational cost, enhance cross-dataset generalization, and yield smoother trajectories and higher behavioral plausibility. The findings reveal that standard in-distribution evaluation and regression-based metrics may fail to reflect true model generalization and prediction plausibility. By providing theoretical justification and empirical validation, this dissertation estab- lishes polynomial trajectory representations as an efficient, expressive, and generalizable foundation for traffic scene prediction in safety critical autonomous driving.

Problem

• traffic scene prediction
• autonomous driving
• generalization
• computational efficiency
• prediction plausibility

Innovation

• polynomial representations
• traffic scene prediction
• distribution shift generalization
• diffusion-based generation
• autonomous driving