Abstract — This paper describes the application of Particle Swarm Optimization (PSO) for gait optimization on a humanoid robot. The biped gait is modeled by a number of parameterizable trajectories. To achieve omni-directional walking, different sets of gait parameters are optimized for specific walk directions and interpolated later. By using a fitness test based on an acceleration walk, the optimized sets of parameters are suitable for a wide range of walk speeds. We tested the applicability of the approach by performing gait optimization for several walk directions on a modified Kondo KHR-1 robot. Keywords—gait modeling, gait optimization, particle swarm optimization (PSO), acceleration walk, omni-directional gait I.

Abstract. This paper describes the hardware and software design of the kidsize humanoid robot systems of the Darmstadt Dribblers in 2007. The robots are used as a vehicle for research in control of locomotion and behavior of autonomous humanoid robots and robot teams with many degrees of freedom and many actuated joints. The Humanoid League of RoboCup provides an ideal testbed for such aspects of dynamics in motion and autonomous behavior as the problem of generating and maintaining statically or dynamically stable bipedal locomotion is predominant for all types of vision guided motions during a soccer game. A modular software architecture as well as further technologies have been developed for efficient and effective implementation and test of modules for sensing, planning, behavior, and actions of humanoid robots. 1

Abstract — Many different and high-quality humanoid motions have been developed based on a tailored, 55cm tall humanoid robot kinematics and design using 21 servo motors and inertial sensors for stabilization. These include fast forward walking of about 1.5 km/h in permanent operation, multidirectional walking capabilities, a variety of standard and spectacular kicks, standing up motions as well as motions displaying an emotional state of the robot. While all robot motions are executed in real-time on a controller board an adaptive selection of different motions and autonomous robot behavior are controlled by hierarchical state machine executed on an onboard Pocket PC. Information about the current state of the dynamic environment in a soccer game is obtained from two directed cameras with wide and narrow angles. During RoboCup 2006 the robot demonstrated the fastest walking of all kid- and teen-size humanoid robots on regular terrain as well as in the rough terrain challenge. Also a large variety of different motions as well as individual and team behaviors during successful autonomous soccer games have been demonstrated including the scoring of a goal with the first autonomously performed backheel kick of a humanoid robot.

Abstract — This paper presents an approach for learning complex tasks on real robots, like walking or kicking in a humanoid soccer robot, profiting at most from the possibility to run simulations of a virtual model of the robot. This approach avoids to damage the real robot in the time consuming trials needed to learn a correct behavior and avoids to overfit the virtual robot model. The basic idea is to run most of the learning steps in simulation and to use a few learning steps on the real robot to assess discrepancies between the simulation and the reality. The calculated discrepancies are used to correct the fitness function used in simulation. Experiments on interleaving the learning between a real robot (Robovie-M by VStone) and its virtual model in USARSim are presented. They show that the proposed method is effective and significantly reduces learning time. I.

This paper presents an embedded control architecture constructed for Robo-Erectus, a soccer-playing humanoid robot developed at the Advanced Robotics and Intelligent Control Centre of Singapore Polytechnic. The Robo-Erectus team has participated in the KidSize category of RoboCup’s Humanoid League since 2002, collecting different awards. The latest version of Robo-Erectus has many capabilities that can be exploited to improve the robot’s behavior. The new embedded controller has made possible the first stage of the performance (displayed during RoboCup 2007), including network communication, mapping, and localization. The new mechanical, electronic design, embedded control architecture, and control schemes are described in this paper. In addition to the hardware, the paper presents details of the modules for gait generation, vision, behavior control, and communication.

Abstract—The numerical optimization of continuous parameters in electrotechnical design using electromagnetic field simulation is already standard. When integer-valued variables are involved, the complexity of the optimization problem rises drastically. In this paper, we describe a new sequential surrogate optimization approach for simulation-based mixed-integer nonlinear programming problems. We apply the method for the optimization of combined integer- and real-valued geometrical parameters of the coils of a superconductive magnet. I.

Summary. In this paper key aspects and several methods for modeling, simulation, optimization and control of the locomotion of humanoid robots and humans are discussed. Similarities and differences between walking and running of humanoid robots and humans are outlined. They represent several, different steps towards the ultimate goals of understanding and predicting human motion by validated simulation models and of developing humanoid robots with human like performance in walking and running. Numerical and experimental results are presented for modelbased optimal control as well as for hardware-in-the-loop optimization of humanoid robot walking and for forward dynamics simulation and optimization of a human kicking motion. 1