Enabling a humanoid robot to drive a car, requires the development of a set of basic primitive actions. These include: walking to the vehicle, manually controlling its commands (e.g., ignition, gas pedal and steering), and moving with the whole-body, to ingress/egress the car. In this paper, we present a sensorbased reactive framework for realizing the central part of the complete task, consist...

In this paper, we propose a new approach to model irreversibility in robotic drive chains. Actually, some types of gears such as worm gears have an efficiency which varies according to the power flow direction. The irreversibility appears when the efficiency tends to zero in one direction only, usually, from the load to the motor. The proposed methodology consists of using a state machine to de...

The Grand Challenge by the Defense Advances Research Projects Agency (DARPA) got a great impact on Machine Learning and Computer Vision research. Stanley was the first robot which firstly was able to drive autonomously a 175 mile course in desert terrain which was a great success in autonomous driving which may be leading to autonomous cares in urban environment in the future. Stanley faced a b...

Existing self-reconfigurable robots achieve connections and disconnections by a separate drive of the docking system. In this paper, we present a new docking system with which the connections and disconnections are driven by locomotion actuators, without the need for a separate drive, which reduces the weight and the complexity of the modules. This self-reconfigurable robot consists of two type...

Manipulator kinetostatic performances are usually investigated considering only the geometrical structure of the robot, neglecting the effect of the drive system. In some circumstances this approach may leads to errors and mistakes. This may happen if the actuators are not identical to each other or when the employed transmission ratio are not identical and/or not constant. The paper introduces...

The human interaction with new kind of machines has made possible the development of new technics to drive and control devices in the robotics field. Specifically, on the control systems for walking machines there are several problems to be solved. Some of these problems are the free locomoction gaits. In this paper are shown the basic principles involved in the desing of free gaits to develop ...

Robot manipulations require mechanical interaction with the environment (i.e., the object being manipulated) which can constrain the robot endpoint in some or all directions. A sufficient condition for the stability of robot manipulators in constrained maneuvers is derived in the work presented here. Attention is focused on the class of direct drive robots whose rigid links dominate the robot's...

The paper deals with trajectory tracking of the differential drive robot with a mathematical model governing dynamics and kinematics. Motor dynamics and chassis dynamics are considered for deriving a linear state-space dynamic model. Basic nonlinear kinematic equations are linearized into a successively linearized state-space model. The dynamic and kinematic models are augmented to derive a sin...

The current work addresses the problem of designing and integrating brain-inspired artificial cognitive systems. Specifically, we introduce a new computational framework for modelling partial brain areas following a coevolutionary agent-based approach. Properly formulated neural agents are employed to represent brain areas. A cooperative coevolutionary method, with the inherent ability to co-ad...

In this paper we develop two noble mechanisms for im proving the motions of humanoid robots The double spherical joint is a six DOF joint that consists of six sin gle DOF mechanical pairs in series with their axes inter secting at a point The double spherical joint replaces two hip joints six DOF of humanoid robot and even provides the equivalent function of waist joints without actually adding...