Toward Meta-Level Control of Autonomous Agents

被引：6

作者：

Dannenhauer, Dustin ^{[1
]}

Cox, Michael T. ^{[2
]}

Gupta, Shubham ^{[3
]}

Paisner, Matt ^{[4
]}

Perlis, Don ^{[4
]}

机构：

[1] Lehigh Univ, Bethlehem, PA 18015 USA

[2] Wright State Res Inst, Beavercreek, OH 45431 USA

[3] Thomas Jefferson High Sch Sci & Technol, Alexandria, VA 22312 USA

[4] Univ Maryland, College Pk, MD 20742 USA

来源：

5TH ANNUAL INTERNATIONAL CONFERENCE ON BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES, 2014 BICA | 2014年 / 41卷

关键词：

Computational metacognition; cognitive architecture; metareasoning; long-duration autonomy;

D O I：

10.1016/j.procs.2014.11.107

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Metareasoning is an important capability for autonomous systems, particularly for those being deployed on long duration missions. An agent with increased self-observation and the ability to control itself in response to changing environments will be more capable in achieving its goals. This is essential for long-duration missions where system designers will not be able to, theoretically or practically, predict all possible problems that the agent may encounter. In this paper we describe preliminary work that integrates the metacognitive architecture MIDCA with an autonomous TREX agent, creating a more self-observable and adaptive agent.

引用

页码：226 / 232

页数：7

共 50 条

[31] Experiments in meta-level learning with ILP
Todorovski, L
Dzeroski, S
[J]. PRINCIPLES OF DATA MINING AND KNOWLEDGE DISCOVERY, 1999, 1704 : 98 - 106
[32] Meta-level service type specifications
Puder, A
Geihs, K
[J]. OPEN DISTRIBUTED PROCESSING AND DISTRIBUTED PLATFORMS, 1997, : 74 - 84
[33] Discovering Rules by Meta-level Abduction
Inoue, Katsumi
Furukawa, Koichi
Kobayashi, Ikuo
Nabeshima, Hidetomo
[J]. INDUCTIVE LOGIC PROGRAMMING, 2010, 5989 : 49 - +
[34] Extensibility via a meta-level architecture
Demeyer, S
[J]. JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2001, 24 (01) : 63 - 74
[35] A Meta-level Approach to Approximate Probability
Niskanen, Vesa A.
[J]. KNOWLEDGE-BASED AND INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT IV, 2010, 6279 : 116 - 123
[36] Meta-level control under uncertainty for handling multiple consumable resources of robots
Le Gloannec, S
Mouaddib, AI
Charpillet, F
[J]. 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vols 1-4, 2005, : 550 - 555
[37] Meta-level Control of Multiagent Learning in Dynamic Repeated Resource Sharing Problems
Noda, Itsuki
Ohta, Masayuki
[J]. PRICAI 2008: TRENDS IN ARTIFICIAL INTELLIGENCE, 2008, 5351 : 296 - 308
[38] USING META-LEVEL INFORMATION FOR EXPERT SYSTEM CONTROL - A BLENDING TRANSFORMER APPROACH
COSMADOPOULOS, YA
SOUTHWICK, RW
[J]. RESEARCH AND DEVELOPMENT IN EXPERT SYSTEMS VI, 1989, : 54 - 65
[39] A Meta-level Approach for Multilingual Taint Analysis
Lyons, Damian M.
Becaj, Dino
[J]. PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON SOFTWARE TECHNOLOGIES (ICSOFT), 2021, : 69 - 77
[40] META-LEVEL TRACKING FOR GESTURAL INTENT RECOGNITION
Fanaswala, Mustafa
Krishnamurthy, Vikram
[J]. 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 5600 - 5604

← 1 2 3 4 5 →