USA flag logo/image

An Official Website of the United States Government

Incremental Learning for Robot Sensing and Control

Award Information

Agency:
Department of Defense
Branch:
Army
Award ID:
94870
Program Year/Program:
2010 / STTR
Agency Tracking Number:
A09A-030-0090
Solicitation Year:
N/A
Solicitation Topic Code:
ARMY 09T030
Solicitation Number:
N/A
Small Business Information
Net-Scale Technologies, Inc.
281 State Highway 79 Morganville, NJ 07751-1157
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
 
Phase 1
Fiscal Year: 2010
Title: Incremental Learning for Robot Sensing and Control
Agency / Branch: DOD / ARMY
Contract: W56HZV-10-C-0027
Award Amount: $100,000.00
 

Abstract:

This proposal addresses key open challenges identified during the LAGR program for the practical use of adaptive, vision-based robot navigation in commercial settings. First, the adaptive vision system learns quickly, but forgets as quickly. This will be addressed by using an ensemble of "expert" classifiers, each of which specializes for a particular environment and can be quickly activated when the environment matches its domain of validity. Second, a new type of cost map will be used which accumulates high-level feature vectors, rather than traversability values. A global cost map will also be integrated. Third, we will pre-train the convolutional net feature extractor using the latest unsupervised algorithms for learning hierarchies of invariant features. Fourth, the limited power of general-purpose CPUs will be lifted by using a highly compact, dedicated FPGA-based hardware platform to run computationally intensive parts of the system. Implementations on commercially available GPUs will also be explored. Finally, to achieve portability and modularity, we will make our implementation independent of a particular robot platform and support a wide range of sensor types including stereo cameras and LIDAR. The result will be a highly-compact, low-power, self-contained, low-cost, vision-based navigation system for autonomous mobile robots.

Principal Investigator:

Urs Muller
CEO
7329701441
urs@net-scale.com

Business Contact:

Paula Muller
Vice President
7329701441
paula@net-scale.com
Small Business Information at Submission:

Net-Scale Technologies, Inc.
281 State Highway 79 Morganville, NJ 07751

EIN/Tax ID: 721522574
DUNS: N/A
Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
Research Institution Information:
New York University
715 Broadway
New York, NY 10004
Contact: Yann Lecun
Contact Phone: 2129983283