A Trajectory Generator for High-Density Traffic and Diverse Agent-Interaction Scenarios

2025-10-02

AI Summary

Existing autonomous driving trajectory prediction benchmarks suffer from severe long-tailed data distributions: high-density traffic scenarios and safety-critical maneuvers (e.g., lane changes, overtaking, turning) are underrepresented, leading to poor model generalization and overly optimistic evaluation. To address this, we propose a behavior-aware structured trajectory generation framework. For the first time, it integrates Frenet-coordinate-based trajectory smoothing and dynamic feasibility constraints into grid-based multi-agent simulation, coupled with a rule-driven behavioral triggering mechanism to synthesize highly dense, diverse, and realistic interactive scenes. Our method substantially alleviates the long-tail problem—on Argoverse 1 and 2, it increases agent density and coverage of rare maneuvers while ensuring strong kinematic plausibility and scene-level safety. The generated data significantly improves the robustness and accuracy of downstream trajectory prediction models in complex interactive scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Accurate trajectory prediction is fundamental to autonomous driving, as it underpins safe motion planning and collision avoidance in complex environments. However, existing benchmark datasets suffer from a pronounced long-tail distribution problem, with most samples drawn from low-density scenarios and simple straight-driving behaviors. This underrepresentation of high-density scenarios and safety critical maneuvers such as lane changes, overtaking and turning is an obstacle to model generalization and leads to overly optimistic evaluations. To address these challenges, we propose a novel trajectory generation framework that simultaneously enhances scenarios density and enriches behavioral diversity. Specifically, our approach converts continuous road environments into a structured grid representation that supports fine-grained path planning, explicit conflict detection, and multi-agent coordination. Built upon this representation, we introduce behavior-aware generation mechanisms that combine rule-based decision triggers with Frenet-based trajectory smoothing and dynamic feasibility constraints. This design allows us to synthesize realistic high-density scenarios and rare behaviors with complex interactions that are often missing in real data. Extensive experiments on the large-scale Argoverse 1 and Argoverse 2 datasets demonstrate that our method significantly improves both agent density and behavior diversity, while preserving motion realism and scenario-level safety. Our synthetic data also benefits downstream trajectory prediction models and enhances performance in challenging high-density scenarios.

Problem

• Addresses underrepresentation of high-density traffic scenarios in autonomous driving datasets
• Enhances behavioral diversity for lane changes, overtaking and turning maneuvers
• Generates realistic trajectories with complex multi-agent interactions and safety constraints

Innovation

• Grid representation for path planning and coordination
• Behavior-aware generation with rule triggers and smoothing
• Synthetic high-density scenarios with complex interactions