NASA SBIR 2006 Solicitation


PROPOSAL NUMBER: 06-2 X7.02-9316
SUBTOPIC TITLE: Human-System Interaction
PROPOSAL TITLE: A Software Framework for Coordinating Human-Robot Teams

SMALL BUSINESS CONCERN (Firm Name, Mail Address, City/State/Zip, Phone)
Traclabs, Inc.
8610 N. New Braunfels, Suite 110
San Antonio, TX 78217 - 2356
(210) 822-2310

PRINCIPAL INVESTIGATOR/PROJECT MANAGER (Name, E-mail, Mail Address, City/State/Zip, Phone)
Debra Schreckenghost
8610 N. New Braunfels, Suite 110
San Antonio, TX 78217 - 0000
(281) 573-8342

TECHNICAL ABSTRACT (Limit 2000 characters, approximately 200 words)
Robots are expected to fulfill an important role in manned exploration operations. They will perform precursor missions to pre-position resources for manned missions. They will assist astronauts in site preparation, buildup, and maintenance of a lunar outpost. To support these roles, new forms of human-robot interaction are needed. Task-level commanding and predictive interaction are promising for tasks where time delay and limited bandwidth make tele-operations difficult. Supervised autonomy has potential to make better use of human resources by reducing the mission preparation time for routine tasks. But these new types of operations require human operators to support new types of tasks. TRACLabs proposes to develop a software framework that facilitates human-robot teaming. This software framework will provide tools for human supervisors to use when monitoring the performance and health of robots. The framework also will assist task coordination by applying operational protocols for information communication and allocation of control during remote distributed operations. This work is an innovative combination of technologies to support the new human tasks that arise when operating robots at different levels of autonomy. For performance monitoring, we propose to develop tools for users to define and adjust monitoring conditions, computations, and summaries in response to changing situations and missions. Additionally we will provide software to aid understanding of operational events and their relationship to underlying data. To support coordinating tasks, we propose to integrate our existing agent technology for role-based notification using communication protocols with new technology for authorizing the handover of robotic control. Phase II will produce a software framework for human-robot teaming.

POTENTIAL NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
Unmanned air and ground vehicles are becoming more common in battlefield situations. Future Combat Systems envision manned and unmanned vehicles of all sizes working side-by-side. Additionally, Congress has mandated that one-third of all military vehicles must be unmanned by 2015. The military envisions robots and soldiers working side-by-side to accomplish missions, as well as remote operators supervising robot teams. Currently several operators control one autonomous vehicle. The proposed framework for human-robot interaction will help reverse this ratio. The software developed under Phase II also has potential application for commercial robots. Health and performance monitoring of robots becomes particularly important when deploying robots for long-term, arduous operation. And the ability to notify personnel of trends and issues using a variety of widely available communication modalities enables broader marketability. The software for performance monitoring has potential application beyond the area of robotics. As household and workplace automation becomes pervasive, this type of technology is needed for health and performance monitoring. Software to create custom summaries of data and notify users based on their situation and preferences has wide application with the growth of online information access and the availability of wireless devices.

POTENTIAL NON-NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
Exploration missions will require that humans and robots work together. Robots will perform high risk tasks like EVA and routine or repetitive tasks to improve crew productivity. Introducing robots into manned space operations, however, will change the way these operations are conducted. It will introduce new supervisory tasks for crew and ground control, including maintaining awareness of robotic activities and handling problems the robot cannot resolve. The proposed software framework for human-robot teaming will enable effective human interaction with robots at different levels of autonomy. Such capability will first be needed for lunar surface operations and will be enabling for manned missions into deep space. During Phase I we established productive collaborations with robotics technology organizations at JSC and ARC for Phase II. We will collaborate with JSC on the proposed development and evaluation of software to support situation awareness across time delay and safe handover of control. We also identified potential for integrating our software framework with user interfaces in the JSC Cockpit. We will collaborate with ARC on the identification and computation of health and performance metrics for human-robot teams. This includes providing summaries and reports of robot performance and behavior.

NASA's technology taxonomy has been developed by the SBIR-STTR program to disseminate awareness of proposed and awarded R/R&D in the agency. It is a listing of over 100 technologies, sorted into broad categories, of interest to NASA.

Autonomous Reasoning/Artificial Intelligence
Human-Computer Interfaces

Form Generated on 08-02-07 14:39