LGCVMLNov 16, 2018

Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control

arXiv:1811.06817v1108 citations
Originality Synthesis-oriented
AI Analysis

This addresses safety concerns in self-driving cars, but it is incremental as it builds on existing uncertainty methods without major innovations.

The paper tackled the problem of improving safety in autonomous driving by evaluating uncertainty quantification in end-to-end controllers, finding that mutual information can predict crashes up to five seconds in advance.

A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical domains. One such domain, self-driving, has benefited from significant performance improvements, with millions of miles having been driven with no human intervention. Despite this, crashes and erroneous behaviours still occur, in part due to the complexity of verifying the correctness of DNNs and a lack of safety guarantees. In this paper, we demonstrate how quantitative measures of uncertainty can be extracted in real-time, and their quality evaluated in end-to-end controllers for self-driving cars. To this end we utilise a recent method for gathering approximate uncertainty information from DNNs without changing the network's architecture. We propose evaluation techniques for the uncertainty on two separate architectures which use the uncertainty to predict crashes up to five seconds in advance. We find that mutual information, a measure of uncertainty in classification networks, is a promising indicator of forthcoming crashes.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes