Group formed at UC Berkeley to improve human interaction with automated cars, drones

Researchers at the University of California, Berkeley, have formed a group to develop and verify the design of human-machine interfaces for controlling so-called cyber-physical systems, such as self-driving cars and autonomous delivery drones, which integrate computational and physical components to improve productivity, efficiency and the quality of life.

Known as VeHICaL, for Verified Human Interfaces, Control, and Learning for Semi-Autonomous Systems, the group is funded with 4.6 million U.S. dollars over five years from the U.S. National Science Foundation (NSF) and, as it draws upon interdisciplinary research, includes researchers from the California Institute of Technology and the University of North Carolina, Chapel Hill.

Project leader Sanjit Seshia, a professor of electrical engineering and computer sciences at UC Berkeley, said VeHICaL aims to gain a deeper understanding of how humans and machines can collaborate to perform safety- and mission-critical tasks like semi-autonomous driving, shared control of drones, computer-assisted medicine and surgery, and advanced manufacturing.

"Our project aims to significantly impact the way humans collaborate and interact with automation," Seshia was quoted as saying by a UC Berkeley news release.

"As intelligent cyber-physical systems are deployed in critical sectors such as transportation, aerospace and health care, there is a pressing need to design for their interaction with humans so as to ensure that safety, security, privacy and performance objectives are met."

The researchers are expected to combine ideas from several areas including formal methods, control theory, robotics and perception, cognitive science, machine learning, security and privacy, and human-machine interfaces to generate theory and tools for designers of human-cyber physical systems, so as to create the next generation of verified intelligent systems that collaborate with humans to perform complex tasks with provable guarantees on safety, privacy and performance.

In addition, they are supposed to demonstrate their work on practical testbeds and in collaboration with industry partners, and to provide recommendations to regulatory agencies.

"The ability to design complex systems that include both human and cyber-physical elements, especially in safety-critical applications, is very much in its infancy," said co-principal investigator Richard Murray, a professor of control and dynamical systems and bioengineering at Caltech. "This project will help expand the tools required to deliver on the promise of such systems." Endit