NASA SBIR 2004 Solicitation

FORM B - PROPOSAL SUMMARY


PROPOSAL NUMBER: 04 B5.02-8260
SUBTOPIC TITLE: Flight Payload Logistics, Integration, Processing, and Crew Activities
PROPOSAL TITLE: Intelligence-Based Multi-Resolution 3D Visual Modeling, Registration And Obstacle Avoidance Capabilities For Unmanned Vehicles

SMALL BUSINESS CONCERN (Name, E-mail, Mail Address, City/State/Zip, Phone)
UTOPIACOMPRESSION, CORPORATION
11150 W. Olympic Blvd. Suite 1020
Los Angeles, CA 90064-1825
(310)473-1500

PRINCIPAL INVESTIGATOR/PROJECT MANAGER (Name, E-mail, Mail Address, City/State/Zip, Phone)
Dr. Pierre Grinspan
pierre@utopiacompression.com
11150 W. Olympic Blvd. Suite 1020
Los Angeles, CA 90064-1825
(310)473-1500

TECHNICAL ABSTRACT (LIMIT 200 WORDS)
The use of truly autonomous vehicles (UV) has been hampered by a lack of sophisticated and resource efficient obstacle avoidance systems. Current approaches have focused on either expensive active sensor systems or inferential processing techniques that are computationally intensive. In this proposal, UtopiaCompression Corporation (UC) presents a layered, intelligent and adaptive system concept that will facilitate true UV autonomous operations by solving the collision avoidance problem using inexpensive imaging sensors and modest computational resources.
UtopiaCompression proposes focused research to push the limits of automation in the 3D arena by providing a real-time, end-to-end solution tailored to NASA's sensor data and mission requirements. This would be accomplished by deriving and using 3D structures obtained from inexpensive sensors to compute and model a spatio-temporal vector field. UC's novel, iterative refinement, multi-resolution registration algorithms enable the inexpensive and efficient generation of the 3D structures. These methods would be integrated into navigation strategies utilized to command UVs for safe cruising (avoiding collision) through cluttered environments.

POTENTIAL NASA COMMERCIAL APPLICATIONS (LIMIT 100 WORDS)
UC/DRA's technology, if integrated into the payload delivery and control mechanisms of orbiting and exploration machinery, would enable automated collision avoidance. This capability would measurably increase the safety of space exploration, both manned and unmanned, and decrease costs associated with equipment damage resultant from collisions. The proposed technology will minimize the crew time required for spacecraft operations through automation, enabling the most productive use of minimal personnel. In addition, the object avoidance capabilities can be integrated into unmanned space vehicles and exploration machinery such as the Mars Rovers, enhancing their mission capabilities and facilitating a greater degree of remote exploration.

POTENTIAL NON-NASA COMMERCIAL APPLICATIONS (LIMIT 100 WORDS)
UC/DRA's adaptive obstacle avoidance technology has extensive utility for military and commercial uses. First, intelligent collision avoidance will greatly enhance the combat effectiveness of autonomous air vehicles in heterogeneous, 3D environments. The technology could be extended to include auto detection and tracking capabilities to detect anomalies, identify unusual or risk-associated patterns as well as appearances of certain targeted objects. Second, the commercial benefits would be to greatly increase the safety and effectiveness of public roads and highways as a means of transportation for trucking and passenger transport.