Control-ITRA: Controlling the Behavior of a Driving Model

2025-01-17

AI Summary

To address the challenge of simultaneously achieving controllability and realism in autonomous driving simulation testing, this paper proposes a fine-grained behavior regulation method tailored for general-purpose driving models. Built upon a conditional generative modeling framework, the approach integrates waypoint conditioning and target speed modulation to enable real-time, decoupled control over trajectory shape and driving aggressiveness. To our knowledge, it is the first method that, while guaranteeing zero traffic violations, consistently enhances both trajectory fidelity and controllability across diverse scenarios—including both seen and unseen road layouts. Extensive experiments demonstrate that the proposed method significantly outperforms existing baselines, maintaining high regulatory compliance, photorealistic trajectory generation, and strong generalization capability—particularly in complex urban environments.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Simulating realistic driving behavior is crucial for developing and testing autonomous systems in complex traffic environments. Equally important is the ability to control the behavior of simulated agents to tailor scenarios to specific research needs and safety considerations. This paper extends the general-purpose multi-agent driving behavior model ITRA (Scibior et al., 2021), by introducing a method called Control-ITRA to influence agent behavior through waypoint assignment and target speed modulation. By conditioning agents on these two aspects, we provide a mechanism for them to adhere to specific trajectories and indirectly adjust their aggressiveness. We compare different approaches for integrating these conditions during training and demonstrate that our method can generate controllable, infraction-free trajectories while preserving realism in both seen and unseen locations.

Problem

• Autonomous Vehicles
• Simulation Driving
• Safe Driving

Innovation

• Control-ITRA
• Precise Behavior Control
• Safe Simulation Training