TRAFFIC MANAGEMENT CONCEPT EVALUATION

Award Information
Agency:
Department of Transportation
Branch
n/a
Amount:
$50,000.00
Award Year:
1987
Program:
SBIR
Phase:
Phase I
Contract:
n/a
Agency Tracking Number:
6885
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
Akm Associates Inc
635 Mariners Island Blvd #205, San Mateo, CA, 94404
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
MS ANNA M OKSENIUK
PRINCIPAL INVESTIGATOR
() -
Business Contact:
() -
Research Institution:
n/a
Abstract
AN AIR-TRAFFIC FLOW MANAGEMENT (ATFM) TOOL BASED EITHER ON STRICT MATHEMATICAL FORMULATION AND OPTIMIZATION, AND/OR ONEBASED ON HEURISTIC KNOWLEDGE ABOUT DISTRIBUTING THE FLOW OVER THE NETWORK MAY PROVIDE A SOLUTION TO THE PROBLEM, PERHAPS MUCH BETTER AND OBJECTIVE THAN THE ONE MADE PRESENTLY BY A CADRE OF EXPERTS UNDER STRESSFUL CONDITIONS. THE SYSTEM SHOULD COMPLEMENT THE HUMAN DECISIONS MADE DAILY TO SMOOTH THE FLOW OF AIR TRAFFIC, AND THEREBY MINIMIZE DELAYS WITHOUT SACRIFICING SAFETY. IT WILL BE QUITE VALUABLE IF THE SYSTEM IS ABLE TO EPLAIN SUGGESTED ADVICE INA WAY COMPREHENSIBLE TO THE HUMAN EXPERTS. THE SPECIFIC PHASE I TECHNICAL OBJECTIVES TOWARDS THE DEVELOPMENT THE ATFM SYSTEM ARE: (1) DEVELOP A PROOF-OF-CONCEPT HEURISTIC KNOWLEDGE BASE GATHERED FROM THE EXPERIENCE OF HUMAN EXPERTS; (2) FORMULATE THE DYNAMIC PROGRAMMING APPROACH; (3) COMBINE DYNAMIC PROGRAMMING METHODOLOGY WITH HEURISTIC OPTIMIZATION; (4) DEVELOP A BOUNDED IMPLEMENTATION AS A PROOF OF CONCEPT; THE PROOF-OF-CONCEPT SYSTEM WILL BE IMPLEMENTED ON AKM ASSOCIATES SYMBOLIC 3650 AI WORKSTATION USING THE WELL KNOWNKEE-3 KNOWLEDGE ENGINEERING ENVIRONMENT TOOL. WE CHOSE THIS SOFTWARE ENVIRONMENT, BECAUSE IT WILL GUARANTEE THE QUICK IMPLEMENTATION/MODIFICATION OF THE PROTOTYPE SYSTEM DURING THE SIX MONTHS OF PHASE I EFFORT.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government