Assured Autonomy (Briefing Charts)

reportActive / Technical Report | Accesssion Number: AD1167570 | Open PDF

Abstract:

Impressive progress in machine learning in last decade, but challenges remain for use in safety critical systems. Assurance and trustworthiness critical for use in safety critical systems. Program developing an assurance architecture and toolbox for assurance of learning-enabled systems, released through research community platform (CPS-VO) and (planned) through DoD platform (JAIC). www.assured-autonomy.org. Established community of researchers and practitioners in AI safety. AI safety workshops, NN verification competition, CPS-VO community and design studios. Publications in top AI, CPS and Control conferences. International collaborations.

Author(s):
Neema, Sandeep
Author Organization(s):
DEFENSE ADVANCED RESEARCH PROJECTS AGENCY ARLINGTON VA
Funding Organization(s):
DEFENSE ADVANCED RESEARCH PROJECTS AGENCY ARLINGTON VA, ARLINGTON , VA
Document Type:
Technical Report/Briefing Charts
Publication Date:
2022 Apr 11
Pagination:
25

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution Code:
A - Approved For Public Release
Distribution Statement: Public Release

RECORD

Collection: TRECMS
Subject Terms
Modernization Areas:
Autonomy
Communities of Interest:
Autonomy
Descriptor(s):
neural networks, change detection, computational science, artificial intelligence, artificial intelligence software, machine learning, simulations, autonomous systems, computer languages, reinforcement learning, training, anomaly detection, autonomous underwater vehicles, autonomous vehicles, autonomy, command and control, detection
Keyword(s):
safety critical systems, Assurance and trustworthiness critical
Subject Categories:
Mathematical and Computer Sciences; Space Technology
Creation Date:
2022 Apr 28
Update Date:
2022 Jul 01