With our core product RMStudio a cloud-based software product, Robotic Materials Inc. is actively developing cutting-edge robotics technology to enable future autonomous manufacturing systems.
Robotics is a systems challenge that tightly integrates sensing, actuation, computation and mechanism design. Unlike in other disciplines, these four are very tightly coupled, and small improvements in one can dramatically simplify a specific solution. Robotics therefore requires computer scientists, electrical and mechanical engineers to work hand-in-hand.
Supported by NSF and NIST, RM’s robotic hand combines novel mechanism design with state-of-the-art embedded computing and stereo vision hardware to create an award-winning, fully self-contained robotic hand that is able to pick up objects as small as a screw and as large as a toner cartridge, while being as gentle to handle a strawberry and as strong as needed to assemble a machine.
The patent-pending, smart hand is the core of our RMHandle™ product and demonstrates integration of computer vision and 3D perception into even the tightest of spaces and compact machines.
We are proudly using Intel’s RealSense line of stereo and solid-state Lidar cameras, providing ranges from 0.11m to 9m, depth images with resolution of up to 1280×720 as fast as 300 frames per second (dependent on use case).
Tight integration of sensing and control has allowed RM engineers to solve a series of hard manipulation problems ranging from autonomous assembly of industrial parts to bin picking and mobile manipulation in retail and manufacturing environments.
We are relying on the Nivida Jetson family of embedded computing devices that combine a powerful CPU with a GPU, which provides critical performance gains in machine learning and computer vision applications.
Ranging from 0.5-10 TFLOPS with a power consumption from 5-30W and a footprint as small as a few centimeters square, we can offer both powerful edge computing solution as well as fully autonomous machines.
Watson, James, Austin Miller, and Nikolaus Correll. “Autonomous industrial assembly using force, torque, and RGB-D sensing.” Advanced Robotics 34, no. 7-8 (2020): 546-559.
Von Drigalski, Felix, Christian Schlette, Martin Rudorfer, Nikolaus Correll, Joshua C. Triyonoputro, Weiwei Wan, Tokuo Tsuji, and Tetsuyou Watanabe. “Robots assembling machines: learning from the World Robot Summit 2018 Assembly Challenge.” Advanced Robotics 34, no. 7-8 (2020): 408-421.
Correll, Nikolaus. From Mainframes to PCs: what robotic startups can learn from the Computer revolution. IEEE Spectrum Automaton Blog, October 2019.
Correll, Nikolaus. Robots getting a grip on general manipulation. IEEE Spectrum Automaton Blog, November 2018.
Correll, Nikolaus, Kostas E. Bekris, Dmitry Berenson, Oliver Brock, Albert Causo, Kris Hauser, Kei Okada, Alberto Rodriguez, Joseph M. Romano, and Peter R. Wurman. “Analysis and observations from the first Amazon picking challenge.” IEEE Transactions on Automation Science and Engineering 15, no. 1 (2016): 172-188.