Abstract:
Modern planning methods are effective in computing feasible and optimal plans for robotic tasks when given access to accurate dynamical models. However, robots operating in the real world often face situations that cannot be modeled perfectly before execution. Thus, we only have access to simplified but potentially inaccurate models. This imperfect modeling can lead to highly suboptimal plans or even the inability to reach the goal during execution. Existing approaches present a learning-based solution where real-world experience is used to learn a complex dynamical model that is subsequently used for planning. However, this requires a prohibitively large amount of experience over the entire state space, and can be wasteful if we are interested in completing the task and not in modeling the dynamics accurately. Furthermore, real robots often have operating constraints and cannot spend hours acquiring experience to learn dynamics. This thesis argues that by updating the behavior of the planner and not the dynamics of the model, we can leverage simplified and potentially inaccurate models and significantly reduce the amount of real-world experience needed to provably guarantee that the robot completes the task.

More Information

We support this argument through both algorithmic and theoretical contributions that will be explored in the talk. We conclude by pointing out several directions for future work highlighting that there are still a bountiful of exciting challenges that remain to be solved in this space.

Thesis Committee Members:
Maxim Likhachev, Co-Chair
J. Andrew Bagnell, Co-Chair
Oliver Kroemer
Leslie Pack Kaelbling, MIT