Robo-Erectus: a low-cost autonomous humanoid soccer robot

The humanoid soccer robot league is a new international initiative to foster robotics and AI technologies using soccer games [1]. This paper provides a brief description of a low-cost autonomous humanoid soccer robot called Robo-Erectus (RE), which has been developed in the Center for Advanced Robotics and Intelligent Control (ARICC) at Singapore Polytechnic since 2001. To develop a low-cost humanoid platform which is affordable for many researchers, our RE humanoid robots have been intentionally designed using low-torque servo motors and low-precision mechanical structures so that the cost can be significantly reduced. We demonstrate that the humanoid biped locomotion can be formulated as an optimization problem with consideration of some constraints. In the frame of gait synthesis tied with constraint functions, computational learning methods, e.g. fuzzy reinforcement learning (FRL), can be incorporated to further improve the gait [2]. The proposed control and learning methods have been successfully tested on our RE humanoid soccer robots which finished second in the RoboCup 2002 Humanoid Walk competition and first in the RoboCup 2003 Humanoid Free Performance competition.