Virtual Model Control of a Hexapod Walking Robot

Since robots are typically designed with an individual actuator at each joint, the control of these systems is often difficult and non-intuitive. This thesis explains a more intuitive control scheme called Virtual Model Control. This thesis also demonstrates the simplicity and ease of this control method by using it to control a simulated walking hexapod. Virtual Model Control uses imagined mechanical components to create virtual forces, which are applied through the joint torques of real actuators. This method produces a straightforward means of controlling joint torques to produce a desired robot behavior. Due to the intuitive nature of this control scheme, the design of a virtual model controller is similar to the design of a controller with basic mechanical components. The ease of this control scheme facilitates the use of a high level control system which can be used above the low level virtual model controllers to modulate the parameters of the imaginary mechanical components. In order to apply Virtual Model Control to parallel mechanisms, a solution to the force distribution problem is required. This thesis uses an extension of Gardner`s Partitioned Force Control method which allows for the specification of constrained degrees of freedom. This virtual model control technique was applied to a simulated hexapod robot. Although the hexapod is a highly non-linear, parallel mechanism, the virtual models allowed text-book control solutions to be used while the robot was walking. Using a simple linear control law, the robot walked while simultaneously balancing a pendulum and tracking an object.

Model of Competencies for Decomposition of Human Behavior: Application to Control System of Robots

Humans and machines have shared the same physical space for many years. To share the same space, we want the robots to behave like human beings. This will facilitate their social integration, their interaction with humans and create an intelligent behavior. To achieve this goal, we need to understand how human behavior is generated, analyze tasks running our nerves and how they relate to them. Then and only then can we implement these mechanisms in robotic beings. In this study, we propose a model of competencies based on human neuroregulator system for analysis and decomposition of behavior into functional modules. Using this model allow separate and locate the tasks to be implemented in a robot that displays human-like behavior. As an example, we show the application of model to the autonomous movement behavior on unfamiliar environments and its implementation in various simulated and real robots with different physical configurations and physical devices of different nature. The main result of this study has been to build a model of competencies that is being used to build robotic systems capable of displaying behaviors similar to humans and consider the specific characteristics of robots.

A proposal of a behavior-based control architecture with reinforcement learning for an autonomous underwater robot

Aquesta tesi proposa l'ús d'un seguit de tècniques pel control a alt nivell d'un robot autònom i també per l'aprenentatge automàtic de comportaments. L'objectiu principal de la tesis fou el de dotar d'intel·ligència als robots autònoms que han d'acomplir unes missions determinades en entorns desconeguts i no estructurats. Una de les premisses tingudes en compte en tots els passos d'aquesta tesis va ser la selecció d'aquelles tècniques que poguessin ésser aplicades en temps real, i demostrar-ne el seu funcionament amb experiments reals. El camp d'aplicació de tots els experiments es la robòtica submarina. En una primera part, la tesis es centra en el disseny d'una arquitectura de control que ha de permetre l'assoliment d'una missió prèviament definida. En particular, la tesis proposa l'ús de les arquitectures de control basades en comportaments per a l'assoliment de cada una de les tasques que composen la totalitat de la missió. Una arquitectura d'aquest tipus està formada per un conjunt independent de comportaments, els quals representen diferents intencions del robot (ex.: "anar a una posició", "evitar obstacles",...). Es presenta una recerca bibliogràfica sobre aquest camp i alhora es mostren els resultats d'aplicar quatre de les arquitectures basades en comportaments més representatives a una tasca concreta. De l'anàlisi dels resultats se'n deriva que un dels factors que més influeixen en el rendiment d'aquestes arquitectures, és la metodologia emprada per coordinar les respostes dels comportaments. Per una banda, la coordinació competitiva és aquella en que només un dels comportaments controla el robot. Per altra banda, en la coordinació cooperativa el control del robot és realitza a partir d'una fusió de totes les respostes dels comportaments actius. La tesis, proposa un esquema híbrid d'arquitectura capaç de beneficiar-se dels principals avantatges d'ambdues metodologies. En una segona part, la tesis proposa la utilització de l'aprenentatge per reforç per aprendre l'estructura interna dels comportaments. Aquest tipus d'aprenentatge és adequat per entorns desconeguts i el procés d'aprenentatge es realitza al mateix temps que el robot està explorant l'entorn. La tesis presenta també un estat de l'art d'aquest camp, en el que es detallen els principals problemes que apareixen en utilitzar els algoritmes d'aprenentatge per reforç en aplicacions reals, com la robòtica. El problema de la generalització és un dels que més influeix i consisteix en permetre l'ús de variables continues sense augmentar substancialment el temps de convergència. Després de descriure breument les principals metodologies per generalitzar, la tesis proposa l'ús d'una xarxa neural combinada amb l'algoritme d'aprenentatge per reforç Q_learning. Aquesta combinació proporciona una gran capacitat de generalització i una molt bona disposició per aprendre en tasques de robòtica amb exigències de temps real. No obstant, les xarxes neurals són aproximadors de funcions no-locals, el que significa que en treballar amb un conjunt de dades no homogeni es produeix una interferència: aprendre en un subconjunt de l'espai significa desaprendre en la resta de l'espai. El problema de la interferència afecta de manera directa en robòtica, ja que l'exploració de l'espai es realitza sempre localment. L'algoritme proposat en la tesi té en compte aquest problema i manté una base de dades representativa de totes les zones explorades. Així doncs, totes les mostres de la base de dades s'utilitzen per actualitzar la xarxa neural, i per tant, l'aprenentatge és homogeni. Finalment, la tesi presenta els resultats obtinguts amb la arquitectura de control basada en comportaments i l'algoritme d'aprenentatge per reforç. Els experiments es realitzen amb el robot URIS, desenvolupat a la Universitat de Girona, i el comportament après és el seguiment d'un objecte mitjançant visió per computador. La tesi detalla tots els dispositius desenvolupats pels experiments així com les característiques del propi robot submarí. Els resultats obtinguts demostren la idoneïtat de les propostes en permetre l'aprenentatge del comportament en temps real. En un segon apartat de resultats es demostra la capacitat de generalització de l'algoritme d'aprenentatge mitjançant el "benchmark" del "cotxe i la muntanya". Els resultats obtinguts en aquest problema milloren els resultats d'altres metodologies, demostrant la millor capacitat de generalització de les xarxes neurals.

Generating timed trajectories foran autonomous robot

Tese de Doutoramento Programa Doutoral em Engenharia Electrónica e Computadores

Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

Towards Direct Policy Search Reinforcement Learning for Robot Control

This paper proposes a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, when using RL, has been to apply value function based algorithms, the system here detailed is characterized by the use of direct policy search methods. Rather than approximating a value function, these methodologies approximate a policy using an independent function approximator with its own parameters, trying to maximize the future expected reward. The policy based algorithm presented in this paper is used for learning the internal state/action mapping of a behavior. In this preliminary work, we demonstrate its feasibility with simulated experiments using the underwater robot GARBI in a target reaching task

Designing pheromone communication in swarm robotics: Group foraging behavior mediated by chemical substance

In swarm robotics, communication among the robots is essential. Inspired by biological swarms using pheromones, we propose the use of chemical compounds to realize group foraging behavior in robot swarms. We designed a fully autonomous robot, and then created a swarm using ethanol as the trail pheromone allowing the robots to communicate with one another indirectly via pheromone trails. Our group recruitment and cooperative transport algorithms provide the robots with the required swarm behavior. We conducted both simulations and experiments with real robot swarms, and analyzed the data statistically to investigate any changes caused by pheromone communication in the performance of the swarm in solving foraging recruitment and cooperative transport tasks. The results show that the robots can communicate using pheromone trails, and that the improvement due to pheromone communication may be non-linear, depending on the size of the robot swarm.

Learning Robot Motions from Visual Sensing

Learning from demonstration becomes increasingly popular as an efficient way of robot programming. Not only a scientific interest acts as an inspiration in this case but also the possibility of producing the machines that would find application in different areas of life: robots helping with daily routine at home, high performance automata in industries or friendly toys for children. One way to teach a robot to fulfill complex tasks is to start with simple training exercises, combining them to form more difficult behavior. The objective of the Master’s thesis work was to study robot programming with visual input. Dynamic movement primitives (DMPs) were chosen as a tool for motion learning and generation. Assuming a movement to be a spring system influenced by an external force, making this system move, DMPs represent the motion as a set of non-linear differential equations. During the experiments the properties of DMP, such as temporal and spacial invariance, were examined. The effect of the DMP parameters, including spring coefficient, damping factor, temporal scaling, on the trajectory generated were studied.

Modeling, optimizing and simulating robot calibration with accuracy improvement

This work describes techniques for modeling, optimizing and simulating calibration processes of robots using off-line programming. The identification of geometric parameters of the nominal kinematic model is optimized using techniques of numerical optimization of the mathematical model. The simulation of the actual robot and the measurement system is achieved by introducing random errors representing their physical behavior and its statistical repeatability. An evaluation of the corrected nominal kinematic model brings about a clear perception of the influence of distinct variables involved in the process for a suitable planning, and indicates a considerable accuracy improvement when the optimized model is compared to the non-optimized one.

Flexible multibody dynamics and intelligent control of a hydraulically driven hybrid redundant robot machine

The assembly and maintenance of the International Thermonuclear Experimental Reactor (ITER) vacuum vessel (VV) is highly challenging since the tasks performed by the robot involve welding, material handling, and machine cutting from inside the VV. The VV is made of stainless steel, which has poor machinability and tends to work harden very rapidly, and all the machining operations need to be carried out from inside of the ITER VV. A general industrial robot cannot be used due to its poor stiffness in the heavy duty machining process, and this will cause many problems, such as poor surface quality, tool damage, low accuracy. Therefore, one of the most suitable options should be a light weight mobile robot which is able to move around inside of the VV and perform different machining tasks by replacing different cutting tools. Reducing the mass of the robot manipulators offers many advantages: reduced material costs, reduced power consumption, the possibility of using smaller actuators, and a higher payload-to-robot weight ratio. Offsetting these advantages, the lighter weight robot is more flexible, which makes it more difficult to control. To achieve good machining surface quality, the tracking of the end effector must be accurate, and an accurate model for a more flexible robot must be constructed. This thesis studies the dynamics and control of a 10 degree-of-freedom (DOF) redundant hybrid robot (4-DOF serial mechanism and 6-DOF 6-UPS hexapod parallel mechanisms) hydraulically driven with flexible rods under the influence of machining forces. Firstly, the flexibility of the bodies is described using the floating frame of reference method (FFRF). A finite element model (FEM) provided the Craig-Bampton (CB) modes needed for the FFRF. A dynamic model of the system of six closed loop mechanisms was assembled using the constrained Lagrange equations and the Lagrange multiplier method. Subsequently, the reaction forces between the parallel and serial parts were used to study the dynamics of the serial robot. A PID control based on position predictions was implemented independently to control the hydraulic cylinders of the robot. Secondly, in machining, to achieve greater end effector trajectory tracking accuracy for surface quality, a robust control of the actuators for the flexible link has to be deduced. This thesis investigates the intelligent control of a hydraulically driven parallel robot part based on the dynamic model and two schemes of intelligent control for a hydraulically driven parallel mechanism based on the dynamic model: (1) a fuzzy-PID self-tuning controller composed of the conventional PID control and with fuzzy logic, and (2) adaptive neuro-fuzzy inference system-PID (ANFIS-PID) self-tuning of the gains of the PID controller, which are implemented independently to control each hydraulic cylinder of the parallel mechanism based on rod length predictions. The serial component of the hybrid robot can be analyzed using the equilibrium of reaction forces at the universal joint connections of the hexa-element. To achieve precise positional control of the end effector for maximum precision machining, the hydraulic cylinder should be controlled to hold the hexa-element. Thirdly, a finite element approach of multibody systems using the Special Euclidean group SE(3) framework is presented for a parallel mechanism with flexible piston rods under the influence of machining forces. The flexibility of the bodies is described using the nonlinear interpolation method with an exponential map. The equations of motion take the form of a differential algebraic equation on a Lie group, which is solved using a Lie group time integration scheme. The method relies on the local description of motions, so that it provides a singularity-free formulation, and no parameterization of the nodal variables needs to be introduced. The flexible slider constraint is formulated using a Lie group and used for modeling a flexible rod sliding inside a cylinder. The dynamic model of the system of six closed loop mechanisms was assembled using Hamilton’s principle and the Lagrange multiplier method. A linearized hydraulic control system based on rod length predictions was implemented independently to control the hydraulic cylinders. Consequently, the results of the simulations demonstrating the behavior of the robot machine are presented for each case study. In conclusion, this thesis studies the dynamic analysis of a special hybrid (serialparallel) robot for the above-mentioned special task involving the ITER and investigates different control algorithms that can significantly improve machining performance. These analyses and results provide valuable insight into the design and control of the parallel robot with flexible rods.

Structural Dynamics Model of a Cartesian Robot

Methods are developed for predicting vibration response characteristics of systems which change configuration during operation. A cartesian robot, an example of such a position-dependent system, served as a test case for these methods and was studied in detail. The chosen system model was formulated using the technique of Component Mode Synthesis (CMS). The model assumes that he system is slowly varying, and connects the carriages to each other and to the robot structure at the slowly varying connection points. The modal data required for each component is obtained experimentally in order to get a realistic model. The analysis results in prediction of vibrations that are produced by the inertia forces as well as gravity and friction forces which arise when the robot carriages move with some prescribed motion. Computer simulations and experimental determinations are conducted in order to calculate the vibrations at the robot end-effector. Comparisons are shown to validate the model in two ways: for fixed configuration the mode shapes and natural frequencies are examined, and then for changing configuration the residual vibration at the end of the mode is evaluated. A preliminary study was done on a geometrically nonlinear system which also has position-dependency. The system consisted of a flexible four-bar linkage with elastic input and output shafts. The behavior of the rocker-beam is analyzed for different boundary conditions to show how some limiting cases are obtained. A dimensional analysis leads to an evaluation of the consequences of dynamic similarity on the resulting vibration.

Modeling Robot Dynamic Performance for Endpoint Force Control

This research aims to understand the fundamental dynamic behavior of servo-controlled machinery in response to various types of sensory feedback. As an example of such a system, we study robot force control, a scheme which promises to greatly expand the capabilities of industrial robots by allowing manipulators to interact with uncertain and dynamic tasks. Dynamic models are developed which allow the effects of actuator dynamics, structural flexibility, and workpiece interaction to be explored in the frequency and time domains. The models are used first to explain the causes of robot force control instability, and then to find methods of improving this performance.