CITRIS People and Robots focuses on theory, benchmarks, software, and approaches that address challenges in the interest of society.
About CITRIS People and Robots (CPAR)
CITRIS People and Robots is advancing robotics research, focusing on Deep Learning, Cloud Robotics, Human-Centric Automation, Precision Agriculture, and Bio-Inspired Robotics, developing socially responsible technology, which is critical as robotics is deployed widely in the world. Robotics and automation are advancing rapidly due to innovations in sensors, devices, UAVs, networks, optimization, and machine learning, accelerated by corporate and private investment. These systems have enormous potential to reduce drudgery and improve human experience in healthcare, manufacturing, transportation, safety, and a broad range of other applications in the interests of society. Achieving this will require sensitivity to human issues, rigorous theory evaluated on standard benchmarks, and modular systems built on shared software toolkits.
People and robots are not mutually exclusive. Predictions of the “singularity” are a distraction from a more important concept that might be characterized as “multiplicity,” an emerging category of systems where diverse groups of humans work together with diverse groups of machines to solve difficult problems. Multiplicity combines emerging results in collective intelligence and cloud computing, building on research in ensemble learning, big data, and open-source software. Research in psychology, law, ethics, art, and the humanities are essential to provide historical and cultural context and develop appropriate methods for system and policy design that address human issues such as inclusion, privacy, and alienation. Robotics can also enhance education, inspiring interest in STEM topics for students of all ages.
Multidisciplinary research is needed to investigate the basic and applied science for design of systems and robust performance, addressing the inherent uncertainty in sensing, modeling, and actuation used for control, learning, and systems identification. Cloud Computing can provide access to large datasets and clusters of remote processors to filter, model, optimize, and share data across systems to improve performance over time.
CPAR catalyzes new research by faculty and students from the four CITRIS campuses, building on 40 years of research that has produced significant results, a network of alumni, and many active labs and projects. CPAR also catalyze new research with software, datasets, seminars and collaborations with industry, labs, and public outreach.
In this project we are developing deep learning methods for robotics. Deep learning is a branch of machine learning that is concerned with learning structure, […]
A key focus of this initiative is human-centered automation, that is, designing automation that works well with people. We are developing a principled design framework […]
In times of unprecedented drought, great benefit could be obtained with centimeter-scale data on moisture levels and the ability to respond with equally precise and […]