Toward Robot Autonomy
PickNik’s Director of Research, Dr. Mark Moll, gave a public Tech Talk at Galois this past May entitled “Toward Robot Autonomy: Tasks, Plans, and Policies.” Dr. Moll discusses how tasks, plans, and policies determine outcomes of robotic behavior.
Find the original post here at Galois.
Robots are increasingly deployed outside of carefully controlled factory settings. Advances in robot motion planning have made it possible to compute feasible motions for complex systems. My work is focused on increasing the abstraction level and time horizon of the types of robot tasks that (a) can be specified, (b) are computationally tractable, and (c) can be successfully executed on robotic hardware. The goal is to reduce the amount of user input required to command a robot and enable ever greater levels of autonomy. In this presentation, I will first give a brief overview of sampling-based motion planning, a class of methods that has been successfully applied to a broad range of complex systems. Next, I will describe how this type of low-level planning can be interleaved with high-level symbolic task planning within a synergistic framework. Finally, I will describe how this framework can be extended to policy synthesis. Throughout, I will use my work with NASA Johnson Space Center on the Robonaut 2, a humanoid robot designed to operate aboard the International Space Station, as a motivating example.
Mark Moll is the Director of Research at PickNik, a robotics software development and consultancy company that is supporting the MoveIt motion planning framework. He is also a senior research scientist in the Computer Science Department at Rice University. He has worked in robotics for more than 20 years, with a focus on motion planning. He is leading the development of the Open Motion Planning Library (OMPL), which is widely used in industry and academic research (often via MoveIt / ROS). He has over 80 peer-reviewed publications with research contributions in applied algorithms for problems in robotics and computational structural biology. He has extensive experience deploying novel algorithms on a variety of robotic platforms, ranging from NASA’s Robonaut 2 to autonomous underwater vehicles and self-reconfigurable robots.
Mark Moll received an M.S. in Computer Science from the University of Twente in the Netherlands and a Ph.D. in Computer Science from Carnegie Mellon University. Since then he has held research scientist positions at the University of Southern California’s Information Sciences Institute and Rice University. In September 2019 he joined PickNik.