Variable Stiffness Control for Sequential Contact Tasks

This paper presents a hierarchical reinforcement learning framework for efficient robotic manipulation in sequential contact tasks. We leverage this hierarchical structure to sequentially execute behavior primitives with variable stiffness control capabilities for contact tasks. Our proposed approach relies on three key components: an action...

Specialised Hook Gripper For Robotic Grasping of Vine Tomato Trusses

In this master thesis, the development of an innovative gripper specifically designed for grasping the delicate peduncles of vine tomato trusses is presented. This research addresses a critical challenge in agricultural automation: efficiently and safely manipulating high-value crops without causing damage. The thesis begins with a comprehensive...

Augmented Reality Interfaces in Robotic Manipulation: Assessing the effects of autonomy levels and environmental complexity

This study investigated the human-robot interaction of three different augmented reality interfaces that enabled an operator to control a robot arm. The first control methods gives the operator complete manual control by moving a holographic object which the robot arm copies (Direct control). The second control method allows the operator to...

Manipulation of Deformable Linear Objects Using Dynamic Affine Curvature Modelling

In robotic manipulation of deformable objects, the continuum nature of the object state leads to prohibitively high degrees of freedom when traditional modelling techniques are applied, leading to much research focusing on approaches that avoid an explicit object model. However, without such a model the opportunities for long horizon planning...

Dynamically feasible data-driven trajectory generation for high performance control of robot manipulators

Robot manipulators are significantly more accurate than their human counterparts and enhance the repeatability of various tasks. However, manufactures still provide reduced information regarding the robot controller functions, typically affecting robots' predictability. Additionally, industrial examples show that system transparency could be...

Structural Design and Experiments of a Dynamically Balanced Inverted Four-Bar Linkage as Manipulator Arm for High Acceleration Applications

Industrial robotic manipulators in pick-and-place applications require short settling times to achieve high productivity. The fluctuating reaction forces and moments on the base of a dynamically unbalanced manipulator, however, cause base vibrations, leading to increased settling times. These base vibrations can be eliminated with dynamic...

Synthesis and Control of a 3 Degrees of Freedom Inherently Dynamically Balanced Manipulator for an Unmanned Aerial Vehicle

In aerial manipulation, Unmanned Aerial Vehicles (UAVs) are equipped with manipulators to perform a variety of tasks such as inspections of critical infrastructure at heights. A fundamental issue is that the shaking forces and moments of the manipulator cause the UAV to tip-over and become unstable. Control based methods have been applied in...

Fault-tolerant Control of Robot Manipulators with Sensory Faults using Unbiased Active Inference

This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of probabilistically robust thresholds for fault-tolerant control of robotic systems using the free-energy. The...

Active inference for fault tolerant control of robot manipulators with sensory faults

We present a fault tolerant control scheme for robot manipulators based on active inference. The proposed solution makes use of the sensory prediction errors in the free-energy to simplify the residuals and thresholds generation for fault detection and isolation and does not require additional controllers for fault recovery. Results...

A classification and performance comparison of force-generators for application in exoskeletons and robotic manipulators

In Chapter 1, the focus is on the classification of force generators, which is the family of mechanisms to which balancers belong to. The goal of this chapter is to introduce a bottom-up classification method to identify the complete solutions space of transmissions in force generators based on their transfer function. Using this method, spring...

Guided Stochastic Optimization for Motion Planning

Learning from Demonstration (LfD) is a family of methods used to teach robots specific tasks. It is used to assist them with the increasing difficulty of performing manipulation tasks in a scalable manner. The state-of-the-art in collaborative robots allows for simple LfD approaches that can handle limited parameter changes of a task. These...

Robot manipulator control under the Active Inference framework

The Active Inference framework is a neuroscience theory based on the Free Energy Principle by Karl Friston that has gained considerable prominence as a general theory to explain action and perception. Despite its promising future and use in different fields, its applicability for robot control has been barely investigated in the literature so...

Real-time Collision Avoidance for Robot Manipulators by Braking Trajectory Prediction

The thesis contributes to the pre-collision strategies of robot manipulators by proposing a real-time implementable collision avoidance scheme. The collision is avoided by a braking controller that is activated by a braking trajectory predictor. The predictor provides distances of the end-effector to the object/human in the environment and...

Reinforcement Learning for Tracking Control in Robotics

For a robot manipulator, an accurate reference tracking capability is one of the most important performance factor. This is especially the case for a robot which is deployed for an industrial use such as welding and laser cutting. Recently, an emerging application of 3D printing also attracts researchers to use robotic manipulators in hope of...

Cooperative Sequential Composition Control for Compliant Manipulation: An Approach via "Robot Contact Language"

A convoluted manipulation task involves extensive planning and the use of a supervisory controller to execute the desired task. One controller specification is generally unsuitable to perform the complete manipulation task. Manipulation involves contact of the object being manipulated with robots, surfaces and other objects in the scenario. The...