Online learning and controller adaptation will be an essential component for legged robots in the next few years as they begin to leave the laboratory setting and join our world. I present the first example of a learning system which is able to quickly and reliably acquire a robust feedback control policy for 3D dynamic bipedal walking from a blank slate using only trials implemented on the phy...

The use of a proposed recurrent neural network control system to control a four-legged walking robot is presented in this paper. The control system consists of a neural controller, a standard PD controller, and the walking robot. The robot is a planar four-legged walking robot. The proposed Neural Network (NN) is employed as an inverse controller of the robot. The NN has three layers, which are...

119004-7272 IJMME-IJENS © August 2011 IJENS I J E N S  Abstract—In this paper, diagonal walking strategy on inclined floor is proposed. In conventional methods, bipedal robots walking on inclined floor are solved only in straight direction. When a biped walks on flat floor, the pelvis orientation is always parallel with the floor surface. However, walking on inclined floor will make the robot ...

Changes in pedality can occur in animals due to injury, congenital defects, or behaviour. Here, an attempt is made to reproduce similar conditions on a nominally quadrupedal robot upon losing functionality in one leg, rendering it tripedal. The change in walking speed and energy efficiency are examined for both quadrupedal amble and basic tripedal walking gaits.

The inverse kinematics of a 12 degrees-of-freedom (DOFs) biped robot is formulated in terms of certain parameters. The biped walking gaits are developed using the parameters. The walking gaits are optimized using genetic algorithm (GA). The optimization is carried out considering relative importance of stability margin and walking speed. The stability margin depends on the position of zero-mome...

Locomotor malfunction represents a major problem in some neurological disorders like stroke and spinal cord injury. Robot-assisted walking devices have been used during rehabilitation of patients with these ailments for regaining and improving walking ability. Previous studies showed the advantage of brain-computer interface (BCI) based robot-assisted training combined with physical therapy in ...

In this paper, micro controller is used to control the thermal states of Flexinol wires which actuating legs of the insect-like legged robot. The design emphasizes mechanical simplicity as well as power and computational autonomy for lightweight walking robot applications. The kinematics workspace characteristics has been applied on to a test rig to examine and improve the motion feasibility wi...

Humanoid robot is a type of robot that the overall appearance is based on that of the human body. Humanoid robots include a rich diversity of projects where perception, processing and action are embodied in a recognizably anthropomorphic form in order to emulate some subset of the physical, cognitive and social dimensions of the human body and experience. The research on humanoid robots spans f...

Recently many biped walking robots are developed, and almost all the researches about those robots adopt mass-link models to control and referring zero moment point not to fall over while walking. Here we position these conventional control methods as “model-based control”. Features of the method are that the robot moves accurate and rigid at low efficiency. So it is also important to remember ...

It is well known that passive walking robot can dynamically walk down with a steady gait by only powered gravity. The dynamics of passive walking has interesting characteristics of stability and bifurcation. Since passive gait is natural motion, investigation of passive walking may lead us to understand human locomotion and design for active walking robot. In this paper, the dynamics of passive...