You are here

ORION: Operational Robot with Intelligent Off-road Navigation

Award Information
Agency: Department of Defense
Branch: Army
Contract: W56KGU-17-C-0058
Agency Tracking Number: A17A-019-0134
Amount: $150,000.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: A17A-T019
Solicitation Number: 2017.0
Timeline
Solicitation Year: 2017
Award Year: 2017
Award Start Date (Proposal Award Date): 2017-09-21
Award End Date (Contract End Date): 2018-03-19
Small Business Information
15400 Calhoun Drive
Rockville, MD 20855
United States
DUNS: 161911532
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: No
Principal Investigator
 Dr. Yoichiro Endo
 Lead Scientist/Program Manager
 (301) 294-4621
 yendo@i-a-i.com
Business Contact
 Mr. Mark James@i-a-i.com
Phone: (301) 294-5221
Email: mjames@i-a-i.com
Research Institution
 Rutgers, The State University of New Jersey
 Melissa Matsil, J.D.
 
33 Knightsbridge Road, 2 East Wing
Piscataway, NJ 08854
United States

 (846) 932-4461
 Nonprofit College or University
Abstract

For operational robots to be truly effective in the battlefield, they would need to be integrated with intelligent decision-making capabilities. In particular, the following capabilities would help them to deal with the challenging real-world problems of off-road navigation, namely, traversability assessment (Capability 1), optimal trajectory computation (Capability 2), and optimal maneuver selection (Capability 3). In this STTR effort, we propose to develop ORION, a computational framework that provides an operational robot with intelligent capabilities to effectively deal with real-world problems of off-road navigation. ORION treats Capability 1 as a classification problem, and addresses it by employing state-of-art deep learning techniques. It treats Capability 2 as a heuristic motion planning problem, and solves it by applying state-of-art classical artificial intelligence (AI) techniques of sampling-based kinodynamic planning. Finally, it treats Capability 3 as a policy mapping problem, and solves it by utilizing standard reinforcement learning.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government