Control-ITRA: Controlling the Behavior of a Driving Model

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lioutas, Vasileios, Scibior, Adam, Niedoba, Matthew, Zwartsenberg, Berend, Wood, Frank
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913659796586496
author Lioutas, Vasileios
Scibior, Adam
Niedoba, Matthew
Zwartsenberg, Berend
Wood, Frank
author_facet Lioutas, Vasileios
Scibior, Adam
Niedoba, Matthew
Zwartsenberg, Berend
Wood, Frank
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Control-ITRA: Controlling the Behavior of a Driving Model
Lioutas, Vasileios
Scibior, Adam
Niedoba, Matthew
Zwartsenberg, Berend
Wood, Frank
Artificial Intelligence
Machine Learning
Robotics
Systems and Control
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.
title Control-ITRA: Controlling the Behavior of a Driving Model
topic Artificial Intelligence
Machine Learning
Robotics
Systems and Control
url https://arxiv.org/abs/2501.12408