Genci Capi

Control of walking robots based on manipulation of the zero moment point

In this paper, a new application of the ZMP (Zero Moment Point) control law is presented. The objective of this control method is to obtain a smooth and soft motion based on a real-time control. In the controller, the ZMP is treated as an actuating signal. The coordinates of the robot body are fed back to obtain its position. The proposed control method was applied on two different biped robots, and its validity is verified experimentally.

Optimal trajectory generation for a prismatic joint biped robot using genetic algorithms

Abstract In this paper, a prismatic joint biped robot trajectory planning method is proposed. The minimum consumed energy is used as a criterion for trajectory generation, by using a real number genetic algorithm as an optimization tool. The minimum torque change cost function and constant vertical position trajectories are used in order to compare the results and verify the effectiveness of this method. The minimum consumed energy walking is stable and the impact of the foot with the ground is very small. Experimental investigations of a prismatic joint biped robot confirmed the predictions concerning the consumed energy and stability.

Real time gait generation for autonomous humanoid robots: A case study for walking

Abstract As autonomous humanoid robots assume more important roles in everyday life, they are expected to perform many different tasks and quickly adapt to unknown environments. Therefore, humanoid robots must generate quickly the appropriate gait based on information received from visual system. In this work, we present a new method for real time gait generation during walking based on Neural Networks. The minimum consumed energy gaits similar with human motion, are used to teach the Neural Network. After supervised learning, the Neural Network can quickly generate the humanoid robot gait. Simulation and experimental results utilizing the “Bonten-Maru I” humanoid robot show good performance of the proposed method.

A new control method for walking robots based on angular momentum

Abstract In this paper we present an efficient algorithm for controlling the angular momentum of walking robots through the manipulation of the zero moment point (ZMP). A remarkable feature of our control method is that the ZMP is considered an actuating signal of the controller. The proposed method can be applied in real time situations because it does not need an accurate tracking of joint angles. Its application to walking robots results in a smooth and soft motion. Experimental results, based on a theoretical explanation, verify the validity of the proposed method.

Multiobjective Evolution of Neural Controllers and Task Complexity

Robots operating in everyday life environments are often required to switch between different tasks. While learning and evolution have been effectively applied to single task performance, multiple task performance still lacks methods that have been demonstrated to be both reliable and efficient. This paper introduces a new method for multiple task performance based on multiobjective evolutionary algorithms, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent (CR) robot that has to switch properly between two distinctly different tasks: 1) protecting another moving robot by following it closely and 2) collecting objects scattered in the environment. Furthermore, the tasks and neural complexity are analyzed by including the neural structure as a separate objective function. The simulation and experimental results using the CR robot show that the multiobjective-based evolutionary method can be applied effectively for generating neural networks that enable the robot to perform multiple tasks simultaneously.

Evolution of recurrent neural controllers using an extended parallel genetic algorithm

Abstract Autonomous intelligent agents often must complete non-Markovian sequential tasks, which require complex recurrent neural controllers. In order to improve the convergence of evolution and reduce the computation time, this paper proposes application of an extended evolutionary algorithm. We implemented an extended multi-population genetic algorithm (EMPGA), where subpopulations apply different evolutionary strategies. In addition, subpopulations compete and cooperate among each other. Results show that EMPGA outperformed single population genetic algorithm (SPGA) by efficiently distributing the number of individuals among subpopulations as different strategies became successful during the course of evolution. In addition, the comparison with other multi-population GA shows that competition between subpopulations improved the quality of solution. The evolved neural controllers were also tested in the real hardware of Cyber Rodent robot.

A CORBA‐based approach for humanoid robot control

Recently, many control architectures for robots have been proposed. However, in these architectures, it is difficult to add new functions to existing applications or add new applications. Moreover, developing a robot control system using many researchers makes it difficult to cooperate with each other. In order to deal with these problems, we propose a Humanoid Robot Control Architecture (HRCA) based on Common Object Request Broker Architecture (CORBA). The proposed HRCA is organized as a client/server control architecture. The HRCA is implemented as an integration of many humanoid robot control modules, which correspond to CORBA servers and clients. By applying these to “Bonten‐Maru I” a humanoid robot, which is under development in our laboratory, we describe the HRCA modules and the effectiveness of HRCA. We confirmed the effectiveness of HRCA from simulation and experimental results. By using the proposed HRCA, the control of the humanoid robot in a distributed environment such as a Local Area Network (LAN) is possible and thus various humanoid robots in the world can share their own modules with each other via the Internet.

Evolution of Neural Architecture Fitting Environmental Dynamics

Temporal and sequential information is essential to any agent continually interacting with its environment. In this paper, we test whether it is possible to evolve a recurrent neural network controller to match the dynamic requirement of the task. As a benchmark, we consider a sequential navigation task where the agent has to alternately visit two rewarding sites to obtain food and water after first visiting the nest. To achieve a better fitness, the agent must select relevant sensory inputs and update its working memory to realize a non-Markovian sequential behavior in which the preceding state alone does not determine the next action. We compare the performance of a feed-forward and recurrent neural control architectures in different environment settings and analyze the neural mechanisms and environment features exploited by the agents to achieve their goal. Simulation and experimental results using the Cyber Rodent robot show that a modular architecture with a locally excitatory recur rent layer outperformed the general recurrent controller.

A New Humanoid Robot Gait Generation Based on Multiobjective Optimization

Up to now, the optimization algorithms are applied for humanoid robot gait generation, where a single fitness function drives the optimization process. But often, the humanoid robot gait generation problem is subject to several objectives. In order to deal with this problem, in this paper, we propose a new method based on multiobjective evolutionary algorithm. In order to verify the effectiveness of our proposed method, we considered two important conflicting objectives: minimum energy and minimum torque change, simultaneously. The angle trajectories are generated without neglecting the stability of humanoid robot. Results using the Bonten-Maru humanoid robot show a good performance of the proposed method.

AN EFFICIENT MULTI-PURPOSE OPTIMIZATION METHOD FOR QOS ROUTING USING GENETIC ALGORITHM

In order to support multimedia communication, it is necessary to develop routing algorithms that make decisions based on multiple Quality of Service (QoS) parameters. This is because new services such as video on demand and remote meeting systems have multiple QoS requirements. However, the problem of QoS routing is difficult because finding a feasible route with two independent path constraints is NP-complete problem. Also, QoS routing algorithms for broadband networks must be adaptive, flexible, and intelligent for efficient network management. In this paper, we propose a multi-purpose optimization method for QoS routing based on Genetic Algorithm (GA). The simulation results show that the proposed method has a good performance and therefore is a promising method for QoS routing.