Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment
arXiv:1805.02754
Abstract
The autonomous car technology promises to replace human drivers with safer driving systems. But although autonomous cars can become safer than human drivers this is a long process that is going to be refined over time. Before these vehicles are deployed on urban roads a minimum safety level must be assured. Since the autonomous car technology is still under development there is no standard methodology to evaluate such systems. It is important to completely understand the technology that is being developed to design efficient means to evaluate it. In this paper we assume safety-critical systems reliability as a safety measure. We model an autonomous road vehicle as an intelligent agent and we approach its evaluation from an artificial intelligence perspective. Our focus is the evaluation of perception and decision making systems and also to propose a systematic method to evaluate their integration in the vehicle. We identify critical aspects of the data dependency from the artificial intelligence state of the art models and we also propose procedures to reproduce them.
References in corpus (8)
- The social dilemma of autonomous vehicles
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Robust Physical-World Attacks on Deep Learning Models
- Hierarchical Representations for Efficient Architecture Search
- Note on Attacking Object Detectors with Adversarial Stickers
- Blaming humans in autonomous vehicle accidents: Shared responsibility across levels of automation
- Driving Simulator Platform for Development and Evaluation of Safety and Emergency Systems