Small Business Innovation Research/Small Business Tech Transfer
Deft Control Software (DCS) for Remote Robotic Operations with Underlying Structure
Project Description
Future space missions will increasingly rely upon tele-operated robots to perform work remotely. This will require substantial improvements in robotic function, cognition, and human/machine interaction. The goal of this work is to realize this future by addressing key challenges in robotic space operations.BluHaptics has successfully demonstrated both the feasibility and potential impact of using our Deft Control Software (DCS) to provide pilot assistance to enable safe, intuitive and efficient remote teleoperation of NASA’s robotic systems. The primary goal of our Phase II effort is to develop and deliver a solution that enables intuitive tele-robotic control in dynamic scenarios, such as when targets and possibly interfering objects are moving in the workspace. This proposed approach combines 3D sensing and novel machine learning algorithms with simultaneous localization and mapping (SLAM) for workspace visualization SLAM, to obtain real-time tracking that provides pilot guidance. By increasing situational awareness and implementing safety features such as collision-avoidance, DCS can garner pilot trust, improvesafety, mitigate training time and support rapid task switching.We will perform physical experiments and task demonstrations using two separate robotic platforms that are readily available to our team: (1) MANTIS -- a compact and highly dexterous manipulator designed to fit inside an ExpressRack locker; and (2) Schilling Titan4 -- a work-class hydraulic manipulator commonly used in offshore oil and gas operations. Phase II work will demonstrate how these operator assistance capabilities impact the feasibility and effectiveness of complex robotic operations in two task scenarios that are key to the success of future NASA missions.
More »
Anticipated Benefits
Even before commencement of this Phase II program, BluHaptics will collaborate with TUI first in their MANTIS Phase II program, and then within a soon-to-be proposed MANTIS Phase III program, where BluHaptics Dex-OS will provide basic control of the KRAKEN arm to enable swapping of microplate sample trays. This initial integration effort will also provide a foundation for the additional MANTIS related work as proposed here. Dex-OS can then be further developed for other programs such as TUI's orbital FabLab, which uses the KRAKEN arm to handle 3D printed parts and perform self maintenance. This type of joint development and collaboration provides a perfect example of how BluHaptics general commercialization strategy is applied in practice. DCS algorithms will enable operations support on earth to utilize simulation-based unsupervised machine learning and one- touch minimally supervised machine learning to quickly train the control system to enable assistive control to perform tasks with underlying structure on the ISS. BluHaptics will pursue Phase III programs with NASA to amplify the capabilities of platforms such as Robonaut2 to enable (for example) telerobotic work on the ISS such as swapping of express lockers, connecting/disconnecting cables, flipping switches and other repetitive tasks that could free up astronauts to perform higher value tasks.
The DCS algorithms developed throughout this program will position BluHaptics to fill a major capability gap for the US Navy, which is the ability to autonomously (minimally supervised) connect electronic and communications subsea assets and to perform periodic maintenance. At a high level, the Navy would like to covertly install/maintain subsea monitoring systems, which is logistically difficult now as a surface vessel is required for the task. The machine learning algorithms developed as part of the program will allow naval operations to use reconnaissance data to train robots for intervention tasks to close the capability gap. Outside the USG sector, DCS algorithms can be adapted and integrated into Dex-OS to support advanced capabilities for the offshore energy industry, who seek to reduce operations expenses by moving control stations from the ship onto shore and also reduce dependencies on large support ships by making the ROVs resident near major subsea asset clusters. DCS algorithms can evolve as intervention tasks become more challenging either due to complexity or due to bandwidth and latency constraints. More »
The DCS algorithms developed throughout this program will position BluHaptics to fill a major capability gap for the US Navy, which is the ability to autonomously (minimally supervised) connect electronic and communications subsea assets and to perform periodic maintenance. At a high level, the Navy would like to covertly install/maintain subsea monitoring systems, which is logistically difficult now as a surface vessel is required for the task. The machine learning algorithms developed as part of the program will allow naval operations to use reconnaissance data to train robots for intervention tasks to close the capability gap. Outside the USG sector, DCS algorithms can be adapted and integrated into Dex-OS to support advanced capabilities for the offshore energy industry, who seek to reduce operations expenses by moving control stations from the ship onto shore and also reduce dependencies on large support ships by making the ROVs resident near major subsea asset clusters. DCS algorithms can evolve as intervention tasks become more challenging either due to complexity or due to bandwidth and latency constraints. More »
Project Library
Primary U.S. Work Locations and Key Partners
| Organizations Performing Work | Role | Type | Location |
|---|---|---|---|
| BluHaptics, Inc. | Lead Organization | Industry | Seattle, Washington |
Johnson Space Center
(JSC)
|
Supporting Organization | NASA Center | Houston, Texas |
Primary U.S. Work Locations
-
Texas
-
Washington
Suggest an Edit
Recommend changes and additions to this project record.