Learning In A Hierarchical Control System: 4D/RCS In The DARPA LAGR Program

reportActive / Technical Report | Accession Number: ADA510326 | Open PDF

Abstract:

The Defense Applied Research Projects Agency DARPA Learning Applied to Ground Vehicles LAGR program aims to develop algorithms for autonomous vehicle navigation that learn how to operate in complex terrain. Over many years, the National Institute of Standards and Technology NIST has developed a reference model control system architecture called 4DRCS that has been applied to many kinds of robot control, including autonomous vehicle control. For the LAGR program, NIST has embedded learning into a 4DRCS controller to enable the small robot used in the program to learn to navigate through a range of terrain types. The vehicle learns in several ways. These include learning by example, learning by experience, and learning how to optimize traversal. Learning takes place in the sensory processing, world modeling, and behavior generation parts of the control system. The 4DRCS architecture is explained in the paper, its application to LAGR is described, and the learning algorithms are discussed. Results are shown of the performance of the NIST control system on independently-conducted tests. Further work on the system and its learning capabilities is discussed.

Author(s):
Albus, Jim ; Bostelman, Roger ; Chang, Tommy ; Hong, Tsai ; Shackleford, Will ; Schneier, Michael
Author Organization(s):
NATIONAL INST OF STANDARDS AND TECHNOLOGY GAITHERSBURG MD
Descriptive Note:
Journal article
Supplementary Note:
Submitted to the Jnl. of Field Robotics.
Pagination:
0036

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Monitor Series:
DARPA
 Subject Terms
Joint Capability Areas:
JCA_3_Force Application; JCA_3.1.1_Maneuver to Engage; JCA_3.1_Maneuver; JCA_5_Command and Control; JCA_8_Building Partnerships; JCA_8.1_Communicate; JCA_8.1.3_Influence Adversary and Competitor Audiences; JCA_5.3_Planning; JCA_5.5_Direct; JCA_5.5.1_Communicate Intent and Guidance; JCA_4.6.1_General Engineering; JCA_4.6_Engineering; JCA_6_Net Centric; JCA_6.1.2_Wireless Transmission; JCA_6.1.3_Switching and Routing; JCA_6.1_Information Transport; JCA_2_Battlespace Awareness; JCA_2.1_Planning and Direction; JCA_2.1.3_Task and Monitor Resources; JCA_5.3.1_Analyze Problem; JCA_5.2.2_Develop Knowledge and Situational Awareness
Modernization Areas:
Autonomy; Quantum Science and Computing
Communities of Interest:
Materials and Manufacturing Processes
Descriptor(s):
*ALGORITHMS, *CONTROL SYSTEMS, *INERTIAL NAVIGATION, *AUTONOMOUS NAVIGATION, *ROBOTICS, *GROUND VEHICLES, ARCHITECTURE, HIERARCHIES, EMBEDDING, LEARNING, TERRAIN, ROBOTS, MODELS, COMPUTER PROGRAMS, GLOBAL POSITIONING SYSTEM
Field(s)/Group(s):
Numerical Mathematics, Computer Programming and Software, Cybernetics, Surface Transportation and Equipment, Navigation and Guidance
Keyword(s):
*HIERARCHICAL CONTROL SYSTEM, *RD RCS REFERENCE MODEL ARCHITECTURE, *AUTONOMOUS VEHICLE NAVIGATION, LAGR(LEARNING APPLIED TO GROUND VEHICLES), ROBOTIC VEHICLES, HAND TUNED ALGORITHMS, RCS(REAL TIME CONTROL SYSTEM), COMPUTATIONAL NODES
Report Date:
2009 Jan 01
Creation Date:
2009 Dec 23