Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning

By Rowan Thomas McAllister, Yarin Gal, Alex Kendall, Mark van der Wilk, Amar Shah, Roberto Cipolla, Adrian Weller. 2017

345 citations recorded by the source corpus.

Adrian Weller acknowledges support by the Alan Turing Institute under the EPSRC grant EP/N510129/1, and by the Leverhulme Trust via the CFI.

Subfields: Artificial Intelligence, Automotive Engineering, Civil and Structural Engineering, Safety, Robustness & Interpretability, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Civil and Structural Engineering

In Safety, Robustness & Interpretability

In Robotics & Control

Citations in the corpus

Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks (2019, background): “Additionally, users generally trust a model more when they understand its decision process and are able to anticipate or verify outputs [30].”
Challenges for Transparency (2017, methodology): “Some of our observations have been made previously (Lipton, 2016; Doshi-Velez and Kim, 2017; McAllister et al., 2017).”
A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, background): “pipeline of separate components linking sensory inputs to actuator outputs [11].”
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners (2018, background): “Yet, significant technical obstacles, such as the necessary robustness of driving models to adverse weather/illumination conditions [2,3,4] or the capability to anticipate potential risks in advance [16,17], must be overcome before assisted driving can be turned into full-fletched automated driving.”
Transparency: Motivations and Challenges (2019, background): “Some of our observations have been made previously [42, 16, 46].”
Planning and Decision-Making for Autonomous Vehicles (2018, background): “(66), estimating and propagating uncertainty from every component throughout the entire system pipeline using a principled Bayesian framework would enable the autonomous vehicle to cope appropriately with high uncertainty.”
Transparency: Motivations and Challenges (2017, background): “er features where transparency can provide helpful insight include safety, fairness, verication and causality. There is a rapidly growing literature on methods to try to address these areas directly [17,21,27,31,3,67,46,52]. 3 Possible Dangers of Transparency In this section, we begin to examine way”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “Scrutability / diagnosis The capacity of a method for explainability to inspect a training process that fails to converge or does not achieve an acceptable performance [90, 71, 55] Security The reliability of a model to perform to a safe standard across all reasonable contexts [92]”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, background): “, [106] for medical applications and in [90] for autonomous driving, why it is important to make the uncertainty of model decisions accessible to users.”
Can deep learning beat numerical weather prediction? (2021, background): “engineering domains, for example in medical diagnosis [137] or autonomous driving [138].”
PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings (2019, background): “Since robots are not merely passive observers, but one of potentially many agents, the ability to anticipate how they affect others is critical to their ability to plan useful, safe, and effective actions, critical to their utility within a planning and control framework [22].”