Abstract
Multiple Task Optimization using Dynamical Movement Primitives for Whole-Body Reactive Control
Whole-body controllers provide the tools to execute
multiple simultaneous tasks on humanoid robots, but
given the robot’s internal and external constraints, interferences
are often generated which impede task completion. Priorities
can be assigned to each task to manage these interferences,
unfortunately, this is often done at the detriment of one or
more tasks. In this paper we present a novel framework for
defining and optimizing multiple tasks in order to resolve
potential interferences prior to task execution and remove the
need for prioritization. Our framework parameterizes tasks
with Dynamical Movement Primitives, simulates and evaluates
their execution, and optimizes their parameters based on a
general compatibility principle which is independent of the
robot’s topology, tasks or environment. Two test cases on a
simulation of a humanoid robot are used to demonstrate the
successful optimization of initially interfering tasks using this
framework.