This paper proposes a novel framework to generate an optimal gait trajectory with respect to the energy consumption for a planar one-legged robot via iterative learning control. The proposed method is based on the symmetric property of the variational systems of Hamiltonian systems called variational symmetry. This technique allows one to obtain solutions of a class of optimal control problems ...

Gait generation for hexapod robots can be accomplished with a two-phase process, whereby leg cycles that effectively provide thrust are learned and then the proper selection and coordination of these cycles needed to produce a gait are learned. Genetic algorithms can be used to learn both the leg cycles and the coordination. In previous work, this technique was used successfully to generate gai...

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...

Layered learning is a general hierarchical machine learning paradigm that leverages a given task decomposition to learn complex tasks efficiently. Though it has been validated previously in simulation, this paper presents the first application of layered learning on a physical robot. In particular, it enables the learning of a high-level grasping behavior that relies on a gait which itself must...

A power assisted gait rehabilitation robot system by which a patient who has difficulty in walking can exercise is proposed. Our developed system consists of a robotic manipulator which can adjust the height of the system according to the user and a mobile base with two-driving wheels. It is similar to the architecture of a mobile manipulator. The neural network based control algorithm for a mo...

We have designed an architecture that allows a gait planner to effectively control primitive walking behaviors. The behaviors ensure safe and efficient walking, even without planning; the addition of planning improves performance in rough terrain by allowing the robot to anticipate changes in its gait. We have implemented our approach and demonstrated it on a real robot, Dante II, and on a simu...

We present a dedicated video-based monitoring system for quantification of patient’s attention to visual feedback during robot assisted gait rehabilitation. Two different approaches for eye gaze and head pose tracking are tested and compared. Several metrics for assessment of patient’s attention are also presented. Experimental results with healthy volunteers demonstrate that unobtrusive video-...

Biped robot locomotion is one of the active research areas in robotics. In this area, real-time stable walking with proper speed is one of the main challenges that needs to be overcome. Central Pattern Generators (CPG) as one of the biological gait generation models, can produce complex nonlinear oscillation as a pattern for walking. In this paper, we propose a model for a biped robot joint tra...

The purpose of this paper is to give a short overview of the ongoing work of the combined four-legged and wheeled walking machine ALDURO with special consideration to gait generation in unstructured terrain.

The ability to carry large payloads could greatly increase the applications of small, low cost climbing robots. We present a linear inchworm gait that uses a single powerful actuator to climb. To make this gait possible, we leveraged two new methods of achieving controllable, anisotropic adhesion (one method produces over 200 times stronger adhesion in the preferred direction). With controllabl...