Topic

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted AI and Autonomy; Integrated Sensing and Cyber; Advanced Infrastructure & Advanced Manufacturing The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. OBJECTIVE: research, evaluate, and develop a compact, image-based tactile sensor with robustness suitable for industrial environments. Additionally, develop learning algorithms to successfully demonstrate dexterous manipulation tasks including pose estimation for part handling and placement. DESCRIPTION: The use of robots in different industries has become widespread, though use cases are primarily limited to repetitive tasks involving moving components between known locations. As such, many tasks in manufacturing and maintenance activities still require manual labor from skilled human hands. The ability to automate dexterous manipulation tasks using robots would dramatically expand the use of robots in manufacturing and maintenance. Recent developments in robotics using image-based tactile sensors have shown great progress towards dexterous manipulation. These sensors have demonstrated the ability to sense both shear and normal forces, detect slip, and determine the pose of an object in the grasp. High-resolution implementations of image-based tactile sensors have also demonstrated the ability to measure 3D surface geometry to micron-scale precision with broad applications in aircraft manufacturing and maintenance. Commercially available image-based tactile sensors have been used successfully for academic research and development. To be deployed in industrial environments, these sensors need to be improved in several ways. The first area of improvement is form factor. Commercial image-based tactile sensors are between 25 mm to 30 mm thick due to the optical design. This device thickness limits integration into robotic hands and other gripper designs used for dexterous manipulation. The second area of improvement for these sensors is the robustness of the elastomeric sensor. In industrial settings, these sensors should survive at least 50,000 grasps before requiring replacement. This durability specification is at least an order of magnitude larger than the performance of current commercial elastomeric sensors. Still another area of improvement for these sensors is data rate. A higher-speed camera and faster algorithms could deliver 3D data at 50 fps as compared to the 25 fps delivered by current sensors. PHASE I: For this Direct-to-Phase II topic, evaluators are expecting that the submittal firm demonstrate tactile sensors with the ability to perform intelligent tactile sensing tasks, including texture recognition, 3D shape estimation, and local force measurement. The submittal firm should demonstrate how the data from the sensors is used by an automation system to complete a tactile manipulation task. PHASE II: Explore image sensor and optical designs to reduce device thickness. Evaluate elastomer formulations for durability in robotic grasping tasks. Explore tradeoffs between resolution and robustness. Develop prototype elastomeric sensors for testing in industrial environments and facilitate integration with a robotic system at an air logistics complex. Develop software algorithms for sensor simulation and sim-to-real transfer of tactile manipulation tasks. Quantify the accuracy of 3D shape measurement and local force measurement. PHASE III DUAL USE APPLICATIONS: If the Phase II is successful in developing the technology, air logistics complexes will pursue Phase III opportunities to refine hardware and software in order to increase accuracy and reliability and scale to other systems at air logistics complexes and similarly situated operations. Achieve production-ready state for marketing to the Air Force, other related federal agencies, and private industry. REFERENCES: 1. Johnson and Adelson. “Retrographic sensing for the measurement of surface texture and shape” IEEE Conference on Computer Vision and Pattern Recognition, 2009. 2. Yuan, et al. “Measurement of shear and slip with a GelSight tactile sensor”, IEEE International Conference on Robotics and Automation, 2015 3. Johnson et al. “Microgeometry capture using an elastomeric sensor” ACM Transactions on Graphics (ACM SIGGRAPH), 2011. KEYWORDS: Industrial Tactile Sensing; Robotic Touch; Touch Sensor