The following Great Innovative Idea is from John E. Laird from the Unversity of Michigan. Laird was one of the Blue Sky Award winners at the Association for the Advancement of Artificial Intelligence Conference (AAAI-18) for his paper, coauthored with Shiwali Mohan from the Palo Alto Research Center, on Learning Fast and Slow: Levels of Learning in General Autonomous Intelligent Agents. The Idea Our cool idea is that there are two distinct levels at which humans and general AI systems can learn. Level 1 encompasses innate architectural learning mechanisms that are automatic, online, and effortless – capturing knowledge from the agent’s ongoing experience, such as learning skills, experiential knowledge, or facts. Level 2 encompasses deliberate learning strategies that are realized through the […]

The following Great Innovative Idea is from Tamraparni Dasu, Yaron Kanza, and Divesh Srivastava, from AT&T Labs-Research. They were one of the Blue Sky Award winners at the ACM SIGSPATIAL 2017 conference for their paper, Geotagging IP Packets for Location-Aware Software-Defined Networking in the Presence of Virtual Network Functions. The Idea When routing IP packets on the Internet, the geographic location of routers and switches can be taken into account and utilized, to improve security and support applications such as copyright protection, location-based services, etc. Our main idea is to add to IP packets geotags with spatio-temporal information about the traveled route, e.g., the geographic location of the source. We suggest to use packet encapsulation to add geotags without […]

The following Great Innovative Idea is from Jaime Fernandez Fisac, a Ph.D. Candidate in Electrical Engineering and Computer Sciences Department at the University of California, Berkeley, in the area of Control, Intelligent Systems and Robotics. Fisac was one of the Blue Sky Award winners at the International Symposium on Robotics Research (ISRR 17) in Puerto Varas, Chile for his paper, Pragmatic-Pedagogic Value Alignment. The Idea Advances in robotics and AI are making robots increasingly capable and autonomous, but how will we ensure they understand what things they should or should not do? Our insight is that a competent robot collaborator should behave like a keen apprentice: humans are naturally skilled at social collaboration, and robots can exploit this fact to tap into […]

The following Great Innovative Idea is from Christopher Jonathan, a Ph.D. Candidate at the University of Minnesota-Twin Cities. His paper Toward a Unified Spatial Crowdsourcing Platform, co-authored by Mohamed F. Mokbel, was one of the winners of the  Computing Community Consortium (CCC) sponsored a Blue Sky Ideas Conference Track at the 15th International Symposium on Spatial & Temporal Databases (SSTD), August  21-23, 2017 in Arlington, VA. The Idea In recent years, we saw a surge of popularity of applications that provide many kinds of spatial tasks in our life, such as ride-sharing, delivery service, translation task, reviewing restaurants or other point of interests, and many more. While these applications are important to our every day lives, there are lots of […]

The following Great Innovative Idea is from Po-Jung Huang and Jun Kameoka. Their paper called Pneumatic Actuated Soft Micromold (PASMO) device for Creating 3D Collagen Microparticles was one of the featured talks at the Computing Community Consortium (CCC) sponsored Material Robotics (MaRo) Workshop at the 2017 Robotics Science and Systems (RSS) Conference. The Idea Three-dimensional cell culture is the method that can simply the process for in vivo test. Unlike two-dimensional cell culture, three-dimensional cell culture provides sufficient information, like cell-cell communication and cell-matrix interaction to simulate real human tissue. Pneumatic actuated soft micromold (PASMO) provides a method to generate collagen based three-dimensional microenvironment for simulating progression of tumor and extending to cancer model. PASMO device is integrated […]

The following Great Innovative Idea is from Jun Zhang and Michael Yip. Their paper called Three-Dimensional Hysteresis Modeling of Robotic Artificial Muscles with Application to Shape Memory Alloy Actuators was one of the featured talks at the Computing Community Consortium (CCC) sponsored Material Robotics (MaRo) Workshop at the 2017 Robotics Science and Systems (RSS) Conference. The Idea Robotic artificial muscles are actuators that can make robots move. Unlike electric motors, robotic artificial muscles are compliant and can generate straight contractions just like our biological muscles. Recently, they are increasingly popular in many exciting areas, such as biomimetic robots, soft robots, and safe human-robot interaction. To practically use robotic artificial muscles, it is crucial to have an accurate model […]