NASA SBIR 2018-II Solicitation

Proposal Summary

 18-2- Z5.02-4103
 Robotic Systems - Mobile Manipulation
 ADAMANT: Adaptive Manipulation for Tasks
SMALL BUSINESS CONCERN (Firm Name, Mail Address, City/State/Zip, Phone)
TRACLabs, Inc.
100 North East Loop 410, Suite 520
San Antonio, TX 78216
(281) 461-7886

PRINCIPAL INVESTIGATOR (Name, E-mail, Mail Address, City/State/Zip, Phone)
Robert Burridge
100 North East Loop 410, Suite 520
San Antonio, TX 78216 - 1234
(404) 217-1805

BUSINESS OFFICIAL (Name, E-mail, Mail Address, City/State/Zip, Phone)
David Kortenkamp
100 North East Loop 410, Suite 520
San Antonio, TX 78216 - 1234
(281) 461-7886

Estimated Technology Readiness Level (TRL) :
Begin: 4
End: 6
Technical Abstract (Limit 2000 characters, approximately 200 words)

Robots will play an important role in NASA's upcoming missions to the Moon and beyond.  They will need to manipulate their environment in complex and useful ways - carrying objects, using tools, and assisting crew.  NASA’s humanoid robots have highly dexterous end-effectors, but developing software to fully utilize such hands remains a challenging task.  Grasping strategies are highly dependent on object models and localization.  Environmental obstacles or the object's intended use can strongly influence how best to grasp it. 

Previously with NASA, TRACLabs developed CRAFTSMAN, which supports robot-independent task descriptions, although grasp strategies are robot-specific.  Here, we extend CRAFTSMAN to handle grasping as a task-informed behavior.  This new system, called ADAMANT, will connect to other CRAFTSMAN software nodes to help find the best option for acquiring an object.  The result will be a robot grasping interface that produces more robust robot behaviors while reducing the cognitive load on remote robot operators.

The ADAMANT system uses sensor and/or model data in addition to a task description to develop a ranked list of potential grasps for an object, using user-selected grasp metrics.  These different grasps are explored in the context of the complete task to arrive at the strategy most likely to succeed. In Phase I, we demonstrated that we could describe tasks in terms of the effect on the object, rather than just a sequence of waypoints for a manipulator and gripper.  In Phase II, we will fully incorporate this object-centric idea into CRAFTSMAN, allowing the user to define tasks without a specific manipulator/gripper in mind.  The ADAMANT system will automatically figure out at run-time the best way to grasp an object given models of the hand and models (or sensor data) of the object.

This work will make it easier for NASA to use robots in conjunction with pre-existing operational procedures, and has many applications to industrial robotics.

Potential NASA Applications (Limit 1500 characters, approximately 150 words)

This work is immediately applicable to NASA robots such as Valkyrie, SPDM, SSRMS, and even Astrobee. Future NASA robots will perform repair tasks on satellites or the Deep Space Gateway, and caretaker robots will maintain dormant facilities. Robots will also assist humans on tasks such as habitat construction or surface exploration. The proposed system, integrated with CRAFTSMAN, will greatly improve the capabilities of these robots and facilitate the authoring and supervision of their tasks.

Potential Non-NASA Applications (Limit 1500 characters, approximately 150 words)

TRACLabs has an existing R\&D partnership with major automotive suppliers to integrate CRAFTSMAN into their plants. The first installation went live in September 2017 and operates continuously. The proposed research will be immediately applicable to their stated goals of deploying flexible workcells world-wide.  With this industrial validation, we expect much interest in this technology.

Duration: 24

Form Generated on 05/13/2019 13:34:23