ROAD-R: The Autonomous Driving Dataset with Logical Requirements

Abstract

Neural networks have proven to be very powerful at computer vision tasks. However, they often exhibit unexpected behaviours, violating known requirements expressing background knowledge. This calls for models (i) able to learn from the requirements, and (ii) guaranteed to be compliant with the requirements themselves. Unfortunately, the development of such models is hampered by the lack of datasets equipped with formally specified requirements. In this paper, we introduce the ROad event Awareness Dataset with logical Requirements (ROAD-R), the first publicly available dataset for autonomous driving with requirements expressed as logical constraints. Given ROAD-R, we show that current state-of-the-art models often violate its logical constraints, and that it is possible to exploit them to create models that (i) have a better performance, and (ii) are guaranteed to be compliant with the requirements themselves.

References in corpus (7)

• ROAD: The ROad event Awareness Dataset for Autonomous Driving
• A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• Deep Learning with Logical Constraints
• Multi-Label Classification Neural Networks with Hard Logical Constraints
• HLVU : A New Challenge to Test Deep Understanding of Movies the Way Humans do
• Coherent Hierarchical Multi-Label Classification Networks
• Neuro-Symbolic Constraint Programming for Structured Prediction

Cited by in corpus (1)

• Comparing differentiable logics for learning with logical constraints