Control and Simulation of a 6-DOF Biped Robot based on Twin Delayed Deep Deterministic Policy Gradient Algorithm

Dynamic Control Algorithm for Biped Walking Based on Policy Gradient Fuzzy Reinforcement Learning

This paper presents a novel dynamic control approach to acquire biped walking of humanoid robots focussed on policy gradient reinforcement learning with fuzzy evaluative feedback . The proposed structure of controller involves two feedback loops: conventional computed torque controller including impact-force controller and reinforcement learning computed torque controller. Reinforcement learnin...

Deep Deterministic Policy Gradient for Urban Traffic Light Control

Traffic light timing optimization is still an active line of research despite the wealth of scientific literature on the topic, and the problem remains unsolved for any non-toy scenario. One of the key issues with traffic light optimization is the large scale of the input information that is available for the controlling agent, namely all the traffic data that is continually sampled by the traf...

Vision-based Motion Control of a Biped Robot Using 2 DOF Gaze Control Structure

Dynamic Control Algorithm for a Biped Robot

A not trivial problem in bipedal robot walking is the instability produced by violent transitions between the different walk phases. In this work a dynamic algorithm to control a biped robot is proposed. The algorithm is based on cubic polynomial interpolation of the initial conditions for the robot’s position, velocity and acceleration. This guarantee a constant velocity an a smooth transition...

Modeling and Simulation of a 6 DOF Robot

The purpose of this paper is to model and simulate a 6 DOF robotic system with revolute joints in order to optimize the motion law which results in uniform coating deposited by spray pyrolysis. The structure and the complexity of the robotized system are determined by the necessary movements in the spray pyrolysis process. The nozzle (end-effector of the robot manipulator) has two translations,...