This paper presents a hybrid dynamic control approach to the realisation of humanoid biped robotic walk, focusing on the policy gradient episodic reinforcement learning with fuzzy evaluative feedback. The proposed structure of controller involves two feedback loops: a conventional computed torque controller and an episodic reinforcement learning controller. The reinforcement learning part inclu...

In this paper we present an inverse optimal control based transfer of motions from human experiments to humanoid robots and apply it to walking in constrained environments. To this end we introduce a 3D template model, which describes motion on the basis of center of mass trajectory, foot trajectories, upper body orientation and phase duration. Despite of its abstract architecture with prismati...

Generally online walk pattern generators for humanoids are simplified, and don’t produce ideal gaits. Allowing the robot to ‘settle’ into a more natural gait through the modification of the low-level positional controller would provide significant benefits. In this paper we attempt to achieve this, by limiting the power available to each motor in a humanoid, hence restricting how rigidly the jo...

In this report, two systems have been developed for robot behavior acquisition using kinesthetic demonstrations. The first enables a humanoid robot to imitate constrained reaching gestures directed towards a target using a learning algorithm based on Gaussian Mixture Regression. The imitation trajectory can be reshaped in order to satisfy the constraints of the task and it can adapt to changes ...

One of the most important case in humanoid robot designing is hand, which it consider as an country development. High percentage of robot work quality depend on hand capability. A robot function increase with hand movement. One of important movement in artificial hand capability relate to fingers lateral movement. This case has more effect intake of special objects such as round shape or moving...

In this work, we present a design principle for building humanoid walking that puts emphasis on minimal control, minimal actuation, and minimal energy use in the design. This results in humanoid robots that are easier to develop and much cheaper to produce. We achieve this by utilising springs and the oscillatory motion of pendulums, e.g. the pendulums (or arms) create a 3D dynamic force profil...

The bipedal structure is one of the most versatile ones for the employment of walking robots. The biped robot has almost the same mechanisms as a human and is suitable for moving in an environment which contains stairs, obstacle etc, where a human lives. However, the dynamics involved are highly nonlinear, complex and unstable. So it is difficult to generate human-like walking motion. To realiz...

Fast and flexible walking is necessary for humanoid robots in the Robocup soccer competition. We propose a new fuzzy-logic control scheme that would enable the robot to realize flexible walking with high standard of stability by restricting the step length and inclining the body of robot to an appropriate logic body control scheme uses the desired walking direction and rotating angle as an inpu...

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 hu...

background and aims: this research evaluated the effects of humanoid robots on improvement of eye contact in autistic children. methods and materials: this research used a multiple baseline, single-subject design with control to test 5 autistic children (2 girls and 3 boys) in tehran during 2010. the children aged 7 to 9 years and were tested by gilliam autism rating scales (gars) to ensure the...