ARCANE-PedSynth: Synthetic Multi-Pedestrian Datasets with Behavioural Crossing Annotations
For autonomous driving researchers, this framework provides a reproducible way to generate diverse pedestrian crossing scenarios with dense annotations, addressing the scarcity of such data.
ARCANE-PedSynth is a framework for generating synthetic multi-pedestrian datasets with behavioural annotations, overcoming CARLA's low crossing rate (9%) to achieve configurable rates up to 75%. The generated PedSynth++ dataset includes 533 clips across 12 weather conditions with RGB, LiDAR, and DVS data.
We present ARCANE-PedSynth, an open-source CARLA-based software framework for generating synthetic multi-pedestrian datasets with dense behavioural annotations for pedestrian crossing prediction in autonomous driving. The framework overcomes CARLA's native 9% crossing rate through a hybrid AI-manual pedestrian control architecture, enabling configurable target rates up to 75%. A 12-state behavioural finite state machine with five character archetypes produces diverse crossing behaviours. The framework generates synchronised RGB, LiDAR, and DVS data with per-frame crossing labels, behavioural states, and estimated 2D pose keypoints. We demonstrate ARCANE-PedSynth through PedSynth++, an example dataset generated with the framework, comprising 533 multi-pedestrian clips across 12 weather conditions with RGB, LiDAR, and DVS streams. ARCANE-PedSynth is fully reproducible via CLI parameterisation and Docker containerisation.