The Vulnerability-Adaptive Protection Paradigm.

This article explores the ways in which the trade-off between resiliency and cost in producing safe autonomous machines can be minimized to ensure resilience at low cost. The authors describe their vulnerability-adaptive protection (VAP) paradigm and apply it to a review of the design landscape for...

Full description

Bibliographic Details
Published in:	Communications of the ACM Vol. 67; no. 9; pp. 66 - 78
Main Authors:	Wan, Zishen, Gan, Yiming, Yu, Bo, Liu, Shaoshan, Raychowdhury, Arijit, Zhu, Yuhao
Format:	Article
Published:	Association for Computing Machinery Sep2024
Subjects:	Autonomous vehicles Drone aircraft Computer software safety measures Cost effectiveness Kernel operating systems Computer reliability
Online Access:	View this record in EBSCOhost

Description
Summary:	This article explores the ways in which the trade-off between resiliency and cost in producing safe autonomous machines can be minimized to ensure resilience at low cost. The authors describe their vulnerability-adaptive protection (VAP) paradigm and apply it to a review of the design landscape for resilient autonomous machines. In addition, the authors characterize the inherent resilience in a variety of widely used tasks in open source software stacks for both autonomous vehicles and drones.