Title: Safe Autonomy: Why Learning Needs Control

Abstract: As robotic systems pervade our everyday lives, especially those that leverage complex learning and autonomy algorithms, the question becomes: how can we trust that robots will operate safely around us?  An answer to this question was given, in the abstract, by famed science fiction writer Isaac Asimov: the three laws of robotics.  These laws provide a safety layer between the robot and the world that ensures trustworthy behavior.  In this presentation I will propose a mathematical formalization of the three laws of robots, encapsulated by control barrier functions (CBFs).  These generalizations of (control) Lyapunov functions ensure forward invariance of “safe” sets.  Moreover, CBFs lead to the notion of a safety filter that minimally modifies an existing controller to ensure safety of the system—even if this controller is unknown, the result of a learning-based process, or operating as part of a broader layered autonomy stack.  The utility of CBFs will be demonstrated through their extensive implementation in practice on a wide variety of highly dynamic robotic systems: from ground robots, to drones, to legged robots, to humanoid robots, to robotic assistive devices.

Bio: Aaron D. Ames is the Bren Professor of Mechanical and Civil Engineering and Control and Dynamical Systems at the California Institute of Technology (Caltech).  He received a B.S. in Mechanical Engineering and a B.A. in Mathematics from the University of St. Thomas in 2001 and received a M.A. in Mathematics and a Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2006.  He served as a Postdoctoral Scholar in Control and Dynamical Systems at Caltech from 2006 to 2008, began his faculty career at Texas A&M University in 2008, and was an Associate Professor in Mechanical Engineering and Electrical & Computer Engineering at the Georgia Institute of Technology before joining Caltech in 2017 .  He is an IEEE Fellow and has received multiple awards for his research in control, including: the NSF CAREER award in 2010, the 2015 Donald P. Eckman Award, and the 2019 Antonio Ruberti Young Researcher Prize.  Additionally, his work has received numerous best paper awards at top conferences on robotics and control, e.g., the Best Paper Award of ICRA (in 2020 and 2023).  His research interests span the areas of nonlinear control, safety-critical, cyber-physical and hybrid systems, with a special focus on applications to robotic systems—both formally and through experimental validation.  The application of these ideas ranges from enabling autonomy in robotic systems while ensuring safety, to improving the locomotion capabilities of the mobility impaired. 

Title: Safe Autonomy: Why Learning Needs Control

Abstract: As robotic systems pervade our everyday lives, especially those that leverage complex learning and autonomy algorithms, the question becomes: how can we trust that robots will operate safely around us?  An answer to this question was given, in the abstract, by famed science fiction writer Isaac Asimov: the three laws of robotics.  These laws provide a safety layer between the robot and the world that ensures trustworthy behavior.  In this presentation I will propose a mathematical formalization of the three laws of robots, encapsulated by control barrier functions (CBFs).  These generalizations of (control) Lyapunov functions ensure forward invariance of “safe” sets.  Moreover, CBFs lead to the notion of a safety filter that minimally modifies an existing controller to ensure safety of the system—even if this controller is unknown, the result of a learning-based process, or operating as part of a broader layered autonomy stack.  The utility of CBFs will be demonstrated through their extensive implementation in practice on a wide variety of highly dynamic robotic systems: from ground robots, to drones, to legged robots, to humanoid robots, to robotic assistive devices.

Bio: Aaron D. Ames is the Bren Professor of Mechanical and Civil Engineering and Control and Dynamical Systems at the California Institute of Technology (Caltech).  He received a B.S. in Mechanical Engineering and a B.A. in Mathematics from the University of St. Thomas in 2001 and received a M.A. in Mathematics and a Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2006.  He served as a Postdoctoral Scholar in Control and Dynamical Systems at Caltech from 2006 to 2008, began his faculty career at Texas A&M University in 2008, and was an Associate Professor in Mechanical Engineering and Electrical & Computer Engineering at the Georgia Institute of Technology before joining Caltech in 2017 .  He is an IEEE Fellow and has received multiple awards for his research in control, including: the NSF CAREER award in 2010, the 2015 Donald P. Eckman Award, and the 2019 Antonio Ruberti Young Researcher Prize.  Additionally, his work has received numerous best paper awards at top conferences on robotics and control, e.g., the Best Paper Award of ICRA (in 2020 and 2023).  His research interests span the areas of nonlinear control, safety-critical, cyber-physical and hybrid systems, with a special focus on applications to robotic systems—both formally and through experimental validation.  The application of these ideas ranges from enabling autonomy in robotic systems while ensuring safety, to improving the locomotion capabilities of the mobility impaired.