Workshop Overview

Accurate prediction of probabilistic and interactive human behavior is a prerequisite to enable full autonomy of mobile robots (e.g., autonomous vehicles) in complex scenes. To enable accurate predictions, two fundamental problems should be addressed: 1) datasets of human behavior and motions in interactive tasks and scenarios, and 2) evaluation metrics and benchmarks for extensive prediction models/algorithms. As more and more datasets focusing on interactive driving scenarioshave been constructed (e.g., the INTERACTION dataset), the second problem remains open. Evaluation metrics are upon discussion and benchmarks are yet to be established to guide the design of prediction algorithms, from problem formulation, to input/output interface design, and to the quantification of performance, particularly when specific behavior generation strategies are involved.

This workshop aims to address the above fundamental challenges regarding the prediction problem in autonomous driving.

Organizers