MEAM Seminar: “Exploiting Environmental Fields for Orienteering and Planning Problems”

Robots are increasingly being used to complete tasks in complex environments. To complete these tasks, two of the most fundamental choices that the robot must make are (1) task planning: which tasks to complete and in what order, and (2) path planning: what path to take when navigating between those tasks. In this seminar, I will consider robots operating in environments where the vehicle dynamics are impacted by the dynamics of the environment (environments with flows) while they complete these tasks. I begin by exploring several limitations of existing strategies that tackle task and path planning in environments with flows as separate problems. First, I examine a problem that focuses on the high level problem of task planning, but abstracts away the environment and assumes that the low-level path planning work is solved independently. This helps simplify the problem, but neglects to include environmental information in the problem. In order to address this limitation, I consider a path planning algorithm in an environment where the flow field can be designed. In particular, I consider a scenario where a magnetic force field is used to manipulate the flow field. In this case, I show how a topological approach can be used to take advantage of the structures in the field. Finally, I examine a scenario where the flow field is determined by ocean currents and therefore cannot be controlled. I will present an integrated solution approach to task and path planning that unifies the two problems in the presence of ocean currents.