Task Constrained Motion Planning in Robot Joint Space
Smith Hall 100
Refreshments 4:15 pm
Talk 4:30 pm
In this talk I will explore randomized joint space path planning for articulated robots that are subject to task space constraints. Constrained joint space planning is important for many real world problems involving redundant manipulators. On the one hand, tasks are designated in work space coordinates: rotating doors about fixed axes, sliding drawers along fixed trajectories or holding objects level during transport. On the other, joint space planning gives alternative paths that use redundant degrees of freedom to avoid obstacles or satisfy additional goals while performing a task. I will present a representation of constrained motion for joint space planners and introduce two simple and efficient methods for constrained sampling of joint configuraitons: Tangent Space Sampling (TS) and First-Order Retraction (FR). In our ongoing simulations, these methods have proven to be faster and significantly more invariant to problem/algorithm parameters than existing techniques.