Verifiable autonomous systems using rational agents to provide assurance about decisions made by machines

How can we provide guarantees of behaviours for autonomous systems such as driverless cars? This tutorial text, for professionals, researchers and graduate students, explains how autonomous systems, from intelligent robots to driverless cars, can be programmed in ways that make them amenable to form...

Full description

Bibliographic Details
Main Authors: Dennis, Louise, Fisher, Michael (Author)
Format: eBook
Language:English
Published: Cambridge, United Kingdom Cambridge University Press 2023
Subjects:
Online Access:
Collection: Cambridge Books Online - Collection details see MPG.ReNa
LEADER 02060nmm a2200289 u 4500
001 EB002168278
003 EBX01000000000000001305610
005 00000000000000.0
007 cr|||||||||||||||||||||
008 230705 ||| eng
020 |a 9781108755023 
050 4 |a TJ217.2 
100 1 |a Dennis, Louise 
245 0 0 |a Verifiable autonomous systems  |b using rational agents to provide assurance about decisions made by machines  |c Louise A. Dennis, University of Manchester, Michael Fisher, University of Manchester 
260 |a Cambridge, United Kingdom  |b Cambridge University Press  |c 2023 
300 |a xi, 378 pages  |b digital 
653 |a Robust control 
653 |a Automatic control 
653 |a Machine learning 
653 |a Computer programs / Verification 
700 1 |a Fisher, Michael  |e [author] 
041 0 7 |a eng  |2 ISO 639-2 
989 |b CBO  |a Cambridge Books Online 
028 5 0 |a 10.1017/9781108755023 
856 4 0 |u https://doi.org/10.1017/9781108755023  |x Verlag  |3 Volltext 
082 0 |a 629.8 
520 |a How can we provide guarantees of behaviours for autonomous systems such as driverless cars? This tutorial text, for professionals, researchers and graduate students, explains how autonomous systems, from intelligent robots to driverless cars, can be programmed in ways that make them amenable to formal verification. The authors review specific definitions, applications and the unique future potential of autonomous systems, along with their impact on safer decisions and ethical behaviour. Topics discussed include the use of rational cognitive agent programming from the Beliefs-Desires-Intentions paradigm to control autonomous systems and the role model-checking in verifying the properties of this decision-making component. Several case studies concerning both the verification of autonomous systems and extensions to the framework beyond the model-checking of agent decision-makers are included, along with complete tutorials for the use of the freely-available verifiable cognitive agent toolkit Gwendolen, written in Java