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.

Modelling, control and supervision for a class of hybrid systems

The aim of this thesis is to narrow the gap between two different control techniques: the continuous control and the discrete event control techniques DES. This gap can be reduced by the study of Hybrid systems, and by interpreting as Hybrid systems the majority of large-scale systems. In particular, when looking deeply into a process, it is often possible to identify interaction between discrete and continuous signals. Hybrid systems are systems that have both continuous, and discrete signals. Continuous signals are generally supposed continuous and differentiable in time, since discrete signals are neither continuous nor differentiable in time due to their abrupt changes in time. Continuous signals often represent the measure of natural physical magnitudes such as temperature, pressure etc. The discrete signals are normally artificial signals, operated by human artefacts as current, voltage, light etc. Typical processes modelled as Hybrid systems are production systems, chemical process, or continuos production when time and continuous measures interacts with the transport, and stock inventory system. Complex systems as manufacturing lines are hybrid in a global sense. They can be decomposed into several subsystems, and their links. Another motivation for the study of Hybrid systems is the tools developed by other research domains. These tools benefit from the use of temporal logic for the analysis of several properties of Hybrid systems model, and use it to design systems and controllers, which satisfies physical or imposed restrictions. This thesis is focused in particular types of systems with discrete and continuous signals in interaction. That can be modelled hard non-linealities, such as hysteresis, jumps in the state, limit cycles, etc. and their possible non-deterministic future behaviour expressed by an interpretable model description. The Hybrid systems treated in this work are systems with several discrete states, always less than thirty states (it can arrive to NP hard problem), and continuous dynamics evolving with expression: with Ki ¡ Rn constant vectors or matrices for X components vector. In several states the continuous evolution can be several of them Ki = 0. In this formulation, the mathematics can express Time invariant linear system. By the use of this expression for a local part, the combination of several local linear models is possible to represent non-linear systems. And with the interaction with discrete events of the system the model can compose non-linear Hybrid systems. Especially multistage processes with high continuous dynamics are well represented by the proposed methodology. Sate vectors with more than two components, as third order models or higher is well approximated by the proposed approximation. Flexible belt transmission, chemical reactions with initial start-up and mobile robots with important friction are several physical systems, which profits from the benefits of proposed methodology (accuracy). The motivation of this thesis is to obtain a solution that can control and drive the Hybrid systems from the origin or starting point to the goal. How to obtain this solution, and which is the best solution in terms of one cost function subject to the physical restrictions and control actions is analysed. Hybrid systems that have several possible states, different ways to drive the system to the goal and different continuous control signals are problems that motivate this research. The requirements of the system on which we work is: a model that can represent the behaviour of the non-linear systems, and that possibilities the prediction of possible future behaviour for the model, in order to apply an supervisor which decides the optimal and secure action to drive the system toward the goal. Specific problems can be determined by the use of this kind of hybrid models are: - The unity of order. - Control the system along a reachable path. - Control the system in a safe path. - Optimise the cost function. - Modularity of control The proposed model solves the specified problems in the switching models problem, the initial condition calculus and the unity of the order models. Continuous and discrete phenomena are represented in Linear hybrid models, defined with defined eighth-tuple parameters to model different types of hybrid phenomena. Applying a transformation over the state vector : for LTI system we obtain from a two-dimensional SS a single parameter, alpha, which still maintains the dynamical information. Combining this parameter with the system output, a complete description of the system is obtained in a form of a graph in polar representation. Using Tagaki-Sugeno type III is a fuzzy model which include linear time invariant LTI models for each local model, the fuzzyfication of different LTI local model gives as a result a non-linear time invariant model. In our case the output and the alpha measure govern the membership function. Hybrid systems control is a huge task, the processes need to be guided from the Starting point to the desired End point, passing a through of different specific states and points in the trajectory. The system can be structured in different levels of abstraction and the control in three layers for the Hybrid systems from planning the process to produce the actions, these are the planning, the process and control layer. In this case the algorithms will be applied to robotics ¡V a domain where improvements are well accepted ¡V it is expected to find a simple repetitive processes for which the extra effort in complexity can be compensated by some cost reductions. It may be also interesting to implement some control optimisation to processes such as fuel injection, DC-DC converters etc. In order to apply the RW theory of discrete event systems on a Hybrid system, we must abstract the continuous signals and to project the events generated for these signals, to obtain new sets of observable and controllable events. Ramadge & Wonham¡¦s theory along with the TCT software give a Controllable Sublanguage of the legal language generated for a Discrete Event System (DES). Continuous abstraction transforms predicates over continuous variables into controllable or uncontrollable events, and modifies the set of uncontrollable, controllable observable and unobservable events. Continuous signals produce into the system virtual events, when this crosses the bound limits. If this event is deterministic, they can be projected. It is necessary to determine the controllability of this event, in order to assign this to the corresponding set, , controllable, uncontrollable, observable and unobservable set of events. Find optimal trajectories in order to minimise some cost function is the goal of the modelling procedure. Mathematical model for the system allows the user to apply mathematical techniques over this expression. These possibilities are, to minimise a specific cost function, to obtain optimal controllers and to approximate a specific trajectory. The combination of the Dynamic Programming with Bellman Principle of optimality, give us the procedure to solve the minimum time trajectory for Hybrid systems. The problem is greater when there exists interaction between adjacent states. In Hybrid systems the problem is to determine the partial set points to be applied at the local models. Optimal controller can be implemented in each local model in order to assure the minimisation of the local costs. The solution of this problem needs to give us the trajectory to follow the system. Trajectory marked by a set of set points to force the system to passing over them. Several ways are possible to drive the system from the Starting point Xi to the End point Xf. Different ways are interesting in: dynamic sense, minimum states, approximation at set points, etc. These ways need to be safe and viable and RchW. And only one of them must to be applied, normally the best, which minimises the proposed cost function. A Reachable Way, this means the controllable way and safe, will be evaluated in order to obtain which one minimises the cost function. Contribution of this work is a complete framework to work with the majority Hybrid systems, the procedures to model, control and supervise are defined and explained and its use is demonstrated. Also explained is the procedure to model the systems to be analysed for automatic verification. Great improvements were obtained by using this methodology in comparison to using other piecewise linear approximations. It is demonstrated in particular cases this methodology can provide best approximation. The most important contribution of this work, is the Alpha approximation for non-linear systems with high dynamics While this kind of process is not typical, but in this case the Alpha approximation is the best linear approximation to use, and give a compact representation.

Quantified real constraint solving using modal intervals with applications to control

Les restriccions reals quantificades (QRC) formen un formalisme matemàtic utilitzat per modelar un gran nombre de problemes físics dins els quals intervenen sistemes d'equacions no-lineals sobre variables reals, algunes de les quals podent ésser quantificades. Els QRCs apareixen en nombrosos contextos, com l'Enginyeria de Control o la Biologia. La resolució de QRCs és un domini de recerca molt actiu dins el qual es proposen dos enfocaments diferents: l'eliminació simbòlica de quantificadors i els mètodes aproximatius. Tot i això, la resolució de problemes de grans dimensions i del cas general, resten encara problemes oberts. Aquesta tesi proposa una nova metodologia aproximativa basada en l'Anàlisi Intervalar Modal, una teoria matemàtica que permet resoldre problemes en els quals intervenen quantificadors lògics sobre variables reals. Finalment, dues aplicacions a l'Enginyeria de Control són presentades. La primera fa referència al problema de detecció de fallades i la segona consisteix en un controlador per a un vaixell a vela.

Representació qualitativa asíncrona de senyals per a la supervisió de sistemes dinàmics

L'objectiu general d'aquest treball és trobar i mostrar una eina que permeti obtenir una representació dels senyals procedents de sistemes dinàmics adequada a les necessitats dels sistemes de Supervisió Experta de processos. Aquest objectiu general es pot subdividir en diverses parts, que són tractades en els diferents capítols que composen el treball i que es poden resumir en els següents punts: En primer lloc, cal conèixer les necessitats dels sistemes de Supervisió: La gran quantitat de dades que provenen dels processos fa necessari el tractament d'aquestes dades per obtenir-ne d'altres, més elaborades, amb un nivell més elevat de representació. La utilització de raonament qualitatiu, pròpia dels éssers humans, comporta la necessitat de representar simbòlicament els senyals, de traduir les dades numèriques en símbols. La Supervisió de sistemes dinàmics comporta que el temps sigui una variable fonamental, la asincronia dels esdeveniments significatius per a la Supervisió fa que les representacions més adequades i útils dels senyals siguin asíncrones. Finalment,l'ús dels coneixements experimentals en la Supervisió dels processos comporta que les representacions més naturals siguin les més útils. Aquestes necessitats fan de la representació dels senyals mitjançant episodis l'eina amb més possibilitats per assolir els objectius que es volen assolir. Per això, es presenta un formalisme que permet descriure i incloure-hi la formalització i les diferents aproximacions a aquest tipus de representació ja existents i, al mateix temps, augmentar-ne la significació a través de característiques dels senyals que no es tenen en compte en les aproximacions ja existents. El següent pas és aprofitar el nou formalisme per obtenir una nova representació amb un grau més gran de significació, cosa que s'aconsegueix representant explícitament les discontinuïtats i els períodes estacionaris o d'estabilitat, molt significatius en Supervisió de processos. Un problema sempre present en el tractament de senyals és el soroll que els afecta. Per aquest motiu es presenta un mètode que permet filtrar el soroll de manera que les representacions resultants quedin afectades el mínim possible per aquest tractament. Finalment, es presenta l'aplicació en línia de les eines descrites. La representació en línia dels senyals comporta el tractament de la incertesa inherent al coneixement parcial del senyal (un episodi no pot ser determinat i caracteritzat completament fins que no s'acaba). L'obtenció de resultats amb determinats graus de certesa és perfectament coherent amb la seva utilització posterior mitjançant Sistemes Experts o altres eines de la IA. Totes les aportacions del treball vénen acompanyades d'exemples i/o aplicacions que permeten observar-ne la utilitat i les limitacions.

Oriented vehicles travelling in spherical space

This paper tackles the path planning problem for oriented vehicles travelling in the non-Euclidean 3-Dimensional space; spherical space S3. For such problem, the orientation of the vehicle is naturally represented by orthonormal frame bundle; the rotation group SO(4). Orthonormal frame bundles of space forms coincide with their isometry groups and therefore the focus shifts to control systems defined on Lie groups. The oriented vehicles, in this case, are constrained to travel at constant speed in a forward direction and their angular velocities directly controlled. In this paper we identify controls that induce steady motions of these oriented vehicles and yield closed form parametric expressions for these motions. The paths these vehicles trace are defined explicitly in terms of the controls and therefore invariant with respect to the coordinate system used to describe the motion.

Singularities of optimal control problems on some 6-D lie groups

This paper considers the motion planning problem for oriented vehicles travelling at unit speed in a 3-D space. A Lie group formulation arises naturally and the vehicles are modeled as kinematic control systems with drift defined on the orthonormal frame bundles of particular Riemannian manifolds, specifically, the 3-D space forms Euclidean space E-3, the sphere S-3, and the hyperboloid H'. The corresponding frame bundles are equal to the Euclidean group of motions SE(3), the rotation group SO(4), and the Lorentz group SO (1, 3). The maximum principle of optimal control shifts the emphasis for these systems to the associated Hamiltonian formalism. For an integrable case, the extremal curves are explicitly expressed in terms of elliptic functions. In this paper, a study at the singularities of the extremal curves are given, which correspond to critical points of these elliptic functions. The extremal curves are characterized as the intersections of invariant surfaces and are illustrated graphically at the singular points. It. is then shown that the projections, of the extremals onto the base space, called elastica, at these singular points, are curves of constant curvature and torsion, which in turn implies that the oriented vehicles trace helices.

Cancellation of siren noise from two way voice communications inside emergency vehicles

Sirens used by police, fire and paramedic vehicles have been designed so that they can be heard over large distances, but unfortunately the siren noise enters the vehicle and corrupts intelligibility of voice communications from the emergency vehicle to the control room. Often the siren needs to be turned off to enable the control room to hear what is being said. This paper discusses a siren noise filter system that is capable of removing the siren noise picked up by the two-way radio microphone inside the vehicle. The removal of the siren noise improves the response time for emergency vehicles and thus save lives. To date, the system has been trialed within a fire tender in a non-emergency situation, with good results.

Cancellation of siren noise from two-way voice communication inside emergency vehicles

The development of an adaptive filter system, capable of reducing significantly the effect of siren noise within the cab of an emergency vehicle, is described. The system is capable of removing the siren noise picked up by the radio microphone inside the vehicle, without degrading the wanted voice signal, thus allowing the siren to be used at all times.

Planning autonomous vehicles in the absence of speed lanes using lateral potentials

Chaotic traffic, prevalent in many countries, is marked by a large number of vehicles driving with different speeds without following any predefined speed lanes. Such traffic rules out using any planning algorithm for these vehicles which is based upon the maintenance of speed lanes and lane changes. The absence of speed lanes may imply more bandwidth and easier overtaking in cases where vehicles vary considerably in both their size and speed. Inspired by the performance of artificial potential fields in the planning of mobile robots, we propose here lateral potentials as measures to enable vehicles to decide about their lateral positions on the road. Each vehicle is subjected to a potential from obstacles and vehicles in front, road boundaries, obstacles and vehicles to the side and higher speed vehicles to the rear. All these potentials are lateral and only govern steering the vehicle. A speed control mechanism is also used for longitudinal control of vehicle. The proposed system is shown to perform well for obstacle avoidance, vehicle following and overtaking behaviors.

Optimal steady motions for oriented vehicles

Motivated by the motion planning problem for oriented vehicles travelling in a 3-Dimensional space; Euclidean space E3, the sphere S3 and Hyperboloid H3. For such problems the orientation of the vehicle is naturally represented by an orthonormal frame over a point in the underlying manifold. The orthonormal frame bundles of the space forms R3,S3 and H3 correspond with their isometry groups and are the Euclidean group of motion SE(3), the rotation group SO(4) and the Lorentzian group SO(1; 3) respectively. Orthonormal frame bundles of space forms coincide with their isometry groups and therefore the focus shifts to left-invariant control systems defined on Lie groups. In this paper a method for integrating these systems is given where the controls are time-independent. For constant twist motions or helical motions, the corresponding curves g(t) 2 SE(3) are given in closed form by using the well known Rodrigues’ formula. However, this formula is only applicable to the Euclidean case. This paper gives a method for computing the non-Euclidean screw/helical motions in closed form. This involves decoupling the system into two lower dimensional systems using the double cover properties of Lie groups, then the lower dimensional systems are solved explicitly in closed form.

Control methodologies: Peak reduction algorithms for DNO owned storage devices on the Low Voltage network

The Distribution Network Operators (DNOs) role is becoming more difficult as electric vehicles and electric heating penetrate the network, increasing the demand. As a result it becomes harder for the distribution networks infrastructure to remain within its operating constraints. Energy storage is a potential alternative to conventional network reinforcement such as upgrading cables and transformers. The research presented here in this paper shows that due to the volatile nature of the LV network, the control approach used for energy storage has a significant impact on performance. This paper presents and compares control methodologies for energy storage where the objective is to get the greatest possible peak demand reduction across the day from a pre-specified storage device. The results presented show the benefits and detriments of specific types of control on a storage device connected to a single phase of an LV network, using aggregated demand profiles based on real smart meter data from individual homes. The research demonstrates an important relationship between how predictable an aggregation is and the best control methodology required to achieve the objective.

Bio-inspired autonomous visual vertical control of a quadrotor UAV

Near ground maneuvers, such as hover, approach and landing, are key elements of autonomy in unmanned aerial vehicles. Such maneuvers have been tackled conventionally by measuring or estimating the velocity and the height above the ground often using ultrasonic or laser range finders. Near ground maneuvers are naturally mastered by flying birds and insects as objects below may be of interest for food or shelter. These animals perform such maneuvers efficiently using only the available vision and vestibular sensory information. In this paper, the time-to-contact (Tau) theory, which conceptualizes the visual strategy with which many species are believed to approach objects, is presented as a solution for Unmanned Aerial Vehicles (UAV) relative ground distance control. The paper shows how such an approach can be visually guided without knowledge of height and velocity relative to the ground. A control scheme that implements the Tau strategy is developed employing only visual information from a monocular camera and an inertial measurement unit. To achieve reliable visual information at a high rate, a novel filtering system is proposed to complement the control system. The proposed system is implemented on-board an experimental quadrotor UAV and shown not only to successfully land and approach ground, but also to enable the user to choose the dynamic characteristics of the approach. The methods presented in this paper are applicable to both aerial and space autonomous vehicles.

Bioinspired autonomous visual vertical control of a quadrotor unmanned aerial vehicle

Near-ground maneuvers, such as hover, approach, and landing, are key elements of autonomy in unmanned aerial vehicles. Such maneuvers have been tackled conventionally by measuring or estimating the velocity and the height above the ground, often using ultrasonic or laser range finders. Near-ground maneuvers are naturally mastered by flying birds and insects because objects below may be of interest for food or shelter. These animals perform such maneuvers efficiently using only the available vision and vestibular sensory information. In this paper, the time-tocontact (tau) theory, which conceptualizes the visual strategy with which many species are believed to approach objects, is presented as a solution for relative ground distance control for unmanned aerial vehicles. The paper shows how such an approach can be visually guided without knowledge of height and velocity relative to the ground. A control scheme that implements the tau strategy is developed employing only visual information from a monocular camera and an inertial measurement unit. To achieve reliable visual information at a high rate, a novel filtering system is proposed to complement the control system. The proposed system is implemented onboard an experimental quadrotor unmannedaerial vehicle and is shown to not only successfully land and approach ground, but also to enable the user to choose the dynamic characteristics of the approach. The methods presented in this paper are applicable to both aerial and space autonomous vehicles.

Implementation of a DC-DC converter with variable structure control of switched systems

This paper presents a control method for a class of continuous-time switched systems, using state feedback variable structure controllers. The method is applied to the control of a two-cell dc-dc buck converter and a control circuit design using the software PSpice is proposed. The design is based on Lyapunov-Metzler-SPR systems and the performance of the resulting control system is superior to that afforded by a recently-proposed alternative sliding-mode control technique. The dc-dc power converters are very used in industrial applications, for instance, in power systems of hybrid electric vehicles and aircrafts. Good results were obtained and the proposed design is also inexpensive because it uses electric components that can be easily found for the hardware implementation. Future researches on the subject include the hardware validation of the dc-dc converter controller and the robust control design of switched systems, with structural failures. © 2011 IEEE.

Networked control system for the guidance of a four-wheel steering agricultural robotic platform

A current trend in the agricultural area is the development of mobile robots and autonomous vehicles for precision agriculture (PA). One of the major challenges in the design of these robots is the development of the electronic architecture for the control of the devices. In a joint project among research institutions and a private company in Brazil a multifunctional robotic platform for information acquisition in PA is being designed. This platform has as main characteristics four-wheel propulsion and independent steering, adjustable width, span of 1,80m in height, diesel engine, hydraulic system, and a CAN-based networked control system (NCS). This paper presents a NCS solution for the platform guidance by the four-wheel hydraulic steering distributed control. The control strategy, centered on the robot manipulators control theory, is based on the difference between the desired and actual position and considering the angular speed of the wheels. The results demonstrate that the NCS was simple and efficient, providing suitable steering performance for the platform guidance. Even though the simplicity of the NCS solution developed, it also overcame some verified control challenges in the robot guidance system design such as the hydraulic system delay, nonlinearities in the steering actuators, and inertia in the steering system due the friction of different terrains. Copyright © 2012 Eduardo Pacincia Godoy et al.