Complementary Situation Awareness (CSA) framework

The five-year, $3.6 million project, titled Complementary Situational Awareness for Human-Robot Partnerships is a close collaboration among research teams directed by Nabil Simaan, associate professor of mechanical engineering at Vanderbilt University; Howie Choset, professor of robotics at Carnegie Mellon University and Russell Taylor, the John C. Malone Professor of Computer Science at Johns Hopkins University.  "Our goal is to establish a new concept called complementary situational awareness," said Simaan. "Complementary situational awareness refers to the robot's ability to gather sensory information as it works and to use this information to guide its actions."

"This work will advance human-robot partnerships by establishing a new concept called complementary situational awareness (CSA), which is the simultaneous perception and use of the environment and operational constraints for task execution. The proposed CSA is transformative because it ushers in a new era of human-robot partnerships where robots act as our partners, not only in manipulation, but in perception and control. This research will establish the foundations for CSA to enable multifaceted human-robot partnerships. Three main research objectives guide this effort: 1) Real-time Sensing during Task Execution: design low-level control algorithms providing wire-actuated or flexible continuum robots with sensory awareness by supporting force sensing, exploration, and modulated force interaction in flexible unstructured environments; 2) Situational Awareness Modeling: prescribe information fusion and simultaneous localization and mapping (SLAM) algorithms suitable for surgical planning and in-vivo surgical plan adaptation; 3) Telemanipulation based on CSA: Design, construct, and integrate robotic testbeds with telemanipulation algorithms that use SLAM and exploration data for online adaptation of assistive telemanipulation virtual fixtures. This research also includes investigation of previously unaddressed questions on how sensory exploration and palpation data can be used to enable online-adaptation of assistive virtual fixtures based on force and stiffness data while also taking into account preoperative data and intraoperative correction of registration parameters.

The proposed work will restore the situational awareness readily available in open surgery to minimally invasive surgery. This will benefit patients by enabling core technologies for effective and safe natural orifice surgery or single port access surgery. The societal impact of the proposed work on these two surgical paradigms is reduced pain for patients, shorter hospital stay, improved cosmesis and patients' self image, and lower costs. We also believe that CSA will impact manufacturing where its future will require people and robots working together in a shared space on collaborative tasks. Also, the same concepts of CSA apply to telemanipulation in constrained and unstructured environments and the proposed research has direct relevance to robot-human partnerships for space exploration. To ensure this broader impact will be achieved, an advisory board has been assembled with experts from medicine, manufacturing and aerospace. Finally, the PIs will facilitate collaboration in the medical robotics research community by making our software and hardware designs available on-line and using commercial-grade hardware available at multiple institutions."

Source: NSF, DREB


Popular Posts