This paper proposes a modular framework to generate robust biped locomotion using tight coupling between an analytical walking approach and deep reinforcement learning. is composed of six main modules which are hierarchically connected reduce the overall complexity increase its flexibility. The core this specific dynamics model abstracts humanoid’s into two masses for modeling upper lower body....

In this letter, we present a novel two-level variable Horizon Model Predictive Control (VH-MPC) framework for bipedal locomotion. framework, the higher level computes landing location and timing (horizon length) of swing foot to stabilize unstable part center mass (CoM) dynamics, using feedback from CoM states. The lower takes into account dynamics generates dynamically consistent trajectories ...

Gait generation for bipedal robots is a very complex problem. The basic cycle of a bipedal gait, called a stride, consists of two main phases, namely the single-support phase and the double-support phase, which take place in sequence. During the single-support phase, one foot is in contact with the ground and the other foot is in swing motion, being transferred from back to front position. In t...

Over the past few years in Japan, the number of senior citizens has increased remarkably, and around 1,650,000 of them have gait disorders. Gait disorder means to become difficult of gait by many kinds of cause. For examples, cerebrovascular disorders and joint trouble are the main causes of gait disorders, which are common ailments among those aged 65 to 74. They may be unrelated to the workin...

Objectives This paper presents an optimal trajectory generation method for the biped walking on inclined surfaces by changing some boundary conditions. The minimal energy is used as a criterion to propose a dynamically stable and optimal trajectory generation method for the impactless biped walking. Methods A biped robot should be able to navigate artificial environments including stair-cases, ...

Legged locomotion is a desirable ability for robotic systems thanks to its agile mobility and wide range of motions that it provides. In this paper, the use neural network-based nonlinear controller structures which consist recurrent feedforward layers have been examined in dynamically stable walking problem two-legged robots. detail, hybrid controllers, long short-term memory type neuron model...