The Impact of Medio-lateral Trunk Movement on Mechanical Energy Generation and Distribution during Gait

A typical gait pattern of a healthy individual is characterized by coordinated kinematics of body segments that minimize the energy cost of transport. This is achieved by a well-coordinated sequence of energy generation, transmission, and absorption by muscles. Knowing the energy...

Trajectory Optimization For Hybrid Walking-Driving Motions On Wheeled Quadrupedal Robots

Wheeled-legged (hybrid) robots have the potential for highly agile and versatile locomotion in any real-world application requiring rapid, long-distance mobility skills on challenging terrain. The ability to walk and drive simultaneously is an attractive feature of these hybrid systems, but is unexplored in literature. This thesis work presents...

On correction prediction in man and robot using the cerebellar model articulation controller

The subject of this thesis is to investigate whether the Cerebellar Model Articulation Controller (CMAC) can be used to anticipate controller corrections and increase performance by reducing delays in humanoid robots. This question can be divided into two subquestions. Firstly, whether the CMAC is a suitable architecture for the prediction of...

Fast Self-Stable Planar Bipedal Running

Bipedal running gaits may be self-stable if they rely on the intrinsic system dynamics to attenuate deviations. This use of passive dynamics for gait stability has been observed in biological running and applied for running robotics, supported with the results of numerical simulations. It is an important aspect of the development of fast and...

Active inference for adaptive and fault tolerant control: An application to robot manipulators

Dealing with inherently unmodeled dynamics and large parameter variations or faults, is a challenging task while controlling robot manipulators. Classical control techniques cannot usually provide satisfactory responses, and often external supervision systems have to be designed to handle the faults. Recent research has shown that active...

Fault Diagnosis of Neural Network Modelled Mechanical Systems using a Sparse Bayesian Learning Framework

The increasing complexity of mechanical systems has resulted in an increased usage and dependence on data driven modelling techniques in order to obtain simple yet accurate models of these systems. Neural networks have emerged as a popular modelling choice due to their proven ability to learn complex nonlinear relationships between inputs and...

Humanoid Robot Balance Control using Center of Mass Height Variation

This research considers using center of mass (CoM) height variation as an input for balance control on a humanoid robot. Traditional balance strategies for humanoid robots are taking a step, control of the center of pressure (CoP) location, a result of the ‘ankle strategy’, and changing the angular momentum about the CoM, for example by a ‘hip...

Inverse Optimal Control for robot arm motions: Improving human-robot collaboration by incorporating human characteristics into optimal motion generation

Human-robot collaboration can be improved if the motions of the robot are more legible and predictable. This can be achieved by making the motions more human-like. It is assumed that humans move optimal with respect to a certain objective or cost function. To find this function an inverse optimal control approach is developed. It uses a bilevel...

Generative CoLearn: steering and cost prediction with generative adversarial nets in kinodynamic RRT

Kinodynamic planning is motion planning in state space and aims to satisfy kinematic and dynamic constraints. To reduce its computational cost, a popular approach is to use sampling based methods such as RRT with off-line machine learning for estimating the steering cost and inputs. However, scalability and robustness are still open challenges...

Forward dynamic model for rowing performance; driven by rower specific data and variable rigging setup

In this research the influence of the rower behavior and rigging setup on the boat performance is investigated in a data-driven model. There are different rowing styles and techniques between rowers. Making rowers row in synchrony, while important for the boat performance, is not easy. Rowers have their own signature rowing curve, of which only...

Benchmarking gait models for simulating the influence of body weight unloading on human gait

Deep Reinforcement Learning for Bipedal Robots

Reinforcement Learning (RL) is a general purpose framework for designing controllers for non-linear systems. It tries to learn a controller (policy) by trial and error. This makes it highly suitable for systems which are difficult to control using conventional control methodologies, such as walking robots. Traditionally, RL has only been...

Exploring animation in the design of a mobile intra-logistics robot: Project Mo

The focus of this project is two-fold: first it explores how animation can be used to make functional robots more intuitively understandable. A framework for functional robot developers, to apply animations in the designed behaviours of their products, is proposed. Second, it demonstrates the value of the incorporation of animated behaviours, as...