The State of Solutions for Autonomous Systems Safety

Autonomous Systems are seeing increasing use and increasingly safety-significant application. Consequently, the safety of autonomous systems is an important topic. To reflect this importance the Safety Critical Systems Club (SCSC) has established the Safety of Autonomous Systems Working Group (SASWG). This paper introduces the SASWG and describes (and justifies) the approach it is taking. A running example is used to illustrate challenges, which are organised against three “difficulty horizons”. Potential solutions to some of the challenges are outlined; possible research directions are suggested for other challenges. Some proposed but invalid solutions are also identified. Overall, whilst the SASWG acknowledges the very significant benefits that could accrue from autonomous systems, it believes their development and implementation should be pursued carefully and thoughtfully.

• Publication year

  2018

• Venue

  Evolution of System Safety

• Publication date

  2018-02-06

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.65391/r920
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars

  2017cited by this paper
• Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

  2017cited by this paper
• Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning

  2017cited by this paper
• Claims and Architectures to Rationate on Automatic and Autonomous Functions

  2016cited by this paper
• Concrete Problems in AI Safety

  2016cited by this paper
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier

  2016cited by this paper
• Big Holes in Big Data: A Monte Carlo Algorithm for Detecting Large Hyper-Rectangles in High Dimensional Data

  2016cited by this paper
• Environmental Hazard Analysis - a Variant of Preliminary Hazard Analysis for Autonomous Mobile Robots

  2014cited by this paper
• Uniformity of Point Samples in Metric Spaces Using Gap Ratio

  2014cited by this paper
• Explaining and Harnessing Adversarial Examples

  2014cited by this paper
• Intriguing properties of neural networks

  2013cited by this paper
• A unifying view on dataset shift in classification

  2012cited by this paper
• A Critique of the " Unmanned Systems Safety Guide for Dod Acquisition "

  2009cited by this paper
• Artificial Neural Networks in Safety-critical Applications

  2002cited by this paper

• AI-Driven Human-Autonomy Teaming in Tactical Operations: Proposed Framework, Challenges, and Future Directions

  2024cites this paper
• VINCY: A Smart-contract based Data Integrity and Validation Tooling for Automated Vehicle Incident Investigation

  2023cites this paper
• Toward a hybrid causal framework for autonomous vehicle safety analysis

  2021cites this paper
• License Plate Detection with Machine Learning Without Using Number Recognition

  2019cites this paper
• Paradigms of Artificial General Intelligence and Their Associated Risks

  2019cites this paper
• Verification for Machine Learning, Autonomy, and Neural Networks Survey

  2018cites this paper