VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users

• Published in: Electronic Imaging Vol. 32; no. 16; pp. 109-1 - 109-10
• Main Authors: Ranga, Adithya, Giruzzi, Filippo, Bhanushali, Jagdish, Wirbel, Emilie, Pérez, Patrick, Vu, Tuan-Hung, Perotton, Xavier
• Format: Journal Article
• Language: English
• Published: 7003 Kilworth Lane, Springfield, VA 22151 USA Society for Imaging Science and Technology 26.01.2020
• Subjects: Activity Classification; Behavior Prediction; Joint Attention For Autonomous Driving (jaad); Multitask Learning; Pedestrian Intention; Trajectory Prediction; Vulnerable Road Users (VRU)
• ISSN: 2470-1173; 2470-1173
• DOI: 10.2352/ISSN.2470-1173.2020.16.AVM-109

Advanced perception and path planning are at the core for any self-driving vehicle. Autonomous vehicles need to understand the scene and intentions of other road users for safe motion planning. For urban use cases it is very important to perceive and predict the intentions of pedestrians, cyclists, scooters, etc., classified as vulnerable road users (VRU). Intent is a combination of pedestrian activities and long term trajectories defining their future motion. In this paper we propose a multi-task learning model to predict pedestrian actions, crossing intent and forecast their future path from video sequences. We have trained the model on naturalistic driving open-source JAAD [1] dataset, which is rich in behavioral annotations and real world scenarios. Experimental results show state-of-the-art performance on JAAD dataset and how we can benefit from jointly learning and predicting actions and trajectories using 2D human pose features and scene context.