Sensor-Based Integration of Full-Body Object Manipulation Based on Strategy Selection in a Life-Sized Humanoid Robot

Abstract

The novel method we propose involves a humanoid robot manipulating objects of varying size and weight. How an object is manipulated is generally determined by size and weight. The motion generation system we developed 1) utilizes manipulation strategies defined by which contact points on the robot are to be used, 2) selects the adequate manipulation strategy based on the object, and 3) generates a full-body posture sequence for the humanoid robot with controlled reaction forces and full-body balance using the manipulation strategy as an initial condition. Our system enables the robot to manipulate an object of weight thanks to multiple strategies. Our method’s effectiveness is confirmed in experiments in which a humanoid robot manipulates six different types of objects.