Abstract:
The deployment of autonomous robots in various areas, including transportation and human-robot collaboration, requires strong safety measures for effective interaction with the physical world. Traditional safe control algorithms work well in controlled settings but struggle to adapt to more interactive and unpredictable real-world scenarios. This thesis emphasizes the need to explore beyond traditional robot safety by investigating adaptive safe control strategies, aiming to broaden the operational domain of robots into everyday life. We approach adaptive robotic tasks by defining general tasks as optimization problems that include an arbitrary control objective subject to constraints that model system dynamics and safety requirements. This comprehensive framework allows flexibility to adapt to different settings, such as diverse task goals influenced by unpredictable elements like human preferences, varying system dynamics due to perturbations to the robot’s physical conditions, and complex interactions between articulated robots and the environment.

Thesis Committee Members:
Changliu Liu, Chair
Zachary Manchester
Guanya Shi
Chuchu Fan, Massachusetts Institute of Technology

More Information