A survey on coverage path planning for robotics

Coverage Path Planning (CPP) is the task of determining a path that passes over all points of an area or volume of interest while avoiding obstacles. This task is integral to many robotic applications, such as vacuum cleaning robots, painter robots, autonomous underwater vehicles creating image mosaics, demining robots, lawn mowers, automated harvesters, window cleaners and inspection of complex structures, just to name a few. A considerable body of research has addressed the CPP problem. However, no updated surveys on CPP reflecting recent advances in the field have been presented in the past ten years. In this paper, we present a review of the most successful CPP methods, focusing on the achievements made in the past decade. Furthermore, we discuss reported field applications of the described CPP methods. This work aims to become a starting point for researchers who are initiating their endeavors in CPP. Likewise, this work aims to present a comprehensive review of the recent breakthroughs in the field, providing links to the most interesting and successful works

Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking

This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV

Autonomous underwater vehicle control using reinforcement learning policy search methods

Autonomous underwater vehicles (AUV) represent a challenging control problem with complex, noisy, dynamics. Nowadays, not only the continuous scientific advances in underwater robotics but the increasing number of subsea missions and its complexity ask for an automatization of submarine processes. This paper proposes a high-level control system for solving the action selection problem of an autonomous robot. The system is characterized by the use of reinforcement learning direct policy search methods (RLDPS) for learning the internal state/action mapping of some behaviors. We demonstrate its feasibility with simulated experiments using the model of our underwater robot URIS in a target following task

Model-based objects recognition in industrial environments for autonomous vehicles control

Behavior-based navigation of autonomous vehicles requires the recognition of the navigable areas and the potential obstacles. In this paper we describe a model-based objects recognition system which is part of an image interpretation system intended to assist the navigation of autonomous vehicles that operate in industrial environments. The recognition system integrates color, shape and texture information together with the location of the vanishing point. The recognition process starts from some prior scene knowledge, that is, a generic model of the expected scene and the potential objects. The recognition system constitutes an approach where different low-level vision techniques extract a multitude of image descriptors which are then analyzed using a rule-based reasoning system to interpret the image content. This system has been implemented using a rule-based cooperative expert system

Gradient-based reinforcement learning techniques for underwater robotics behavior learning

Darrerament, l'interès pel desenvolupament d'aplicacions amb robots submarins autònoms (AUV) ha crescut de forma considerable. Els AUVs són atractius gràcies al seu tamany i el fet que no necessiten un operador humà per pilotar-los. Tot i això, és impossible comparar, en termes d'eficiència i flexibilitat, l'habilitat d'un pilot humà amb les escasses capacitats operatives que ofereixen els AUVs actuals. L'utilització de AUVs per cobrir grans àrees implica resoldre problemes complexos, especialment si es desitja que el nostre robot reaccioni en temps real a canvis sobtats en les condicions de treball. Per aquestes raons, el desenvolupament de sistemes de control autònom amb l'objectiu de millorar aquestes capacitats ha esdevingut una prioritat. Aquesta tesi tracta sobre el problema de la presa de decisions utilizant AUVs. El treball presentat es centra en l'estudi, disseny i aplicació de comportaments per a AUVs utilitzant tècniques d'aprenentatge per reforç (RL). La contribució principal d'aquesta tesi consisteix en l'aplicació de diverses tècniques de RL per tal de millorar l'autonomia dels robots submarins, amb l'objectiu final de demostrar la viabilitat d'aquests algoritmes per aprendre tasques submarines autònomes en temps real. En RL, el robot intenta maximitzar un reforç escalar obtingut com a conseqüència de la seva interacció amb l'entorn. L'objectiu és trobar una política òptima que relaciona tots els estats possibles amb les accions a executar per a cada estat que maximitzen la suma de reforços totals. Així, aquesta tesi investiga principalment dues tipologies d'algoritmes basats en RL: mètodes basats en funcions de valor (VF) i mètodes basats en el gradient (PG). Els resultats experimentals finals mostren el robot submarí Ictineu en una tasca autònoma real de seguiment de cables submarins. Per portar-la a terme, s'ha dissenyat un algoritme anomenat mètode d'Actor i Crític (AC), fruit de la fusió de mètodes VF amb tècniques de PG.

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.

Robots with a gentle touch: advances in assistive robotics and prosthetics

As healthcare costs rise and an aging population makes an increased demand on services, so new techniques must be introduced to promote an individuals independence and provide these services. Robots can now be designed so they can alter their dynamic properties changing from stiff to flaccid, or from giving no resistance to movement, to damping any large and sudden movements. This has some strong implications in health care in particular for rehabilitation where a robot must work in conjunction with an individual, and might guiding or assist a persons arm movements, or might be commanded to perform some set of autonomous actions. This paper presents the state-of-the-art of rehabilitation robots with examples from prosthetics, aids for daily living and physiotherapy. In all these situations there is the potential for the interaction to be non-passive with a resulting potential for the human/machine/environment combination to become unstable. To understand this instability we must develop better models of the human motor system and fit these models with realistic parameters. This paper concludes with a discussion of this problem and overviews some human models that can be used to facilitate the design of the human/machine interfaces.

Towards a modular robotics standard for AGV design and programming

Across the world there are many bodies currently involved in researching into the design of autonomous guided vehicles (AGVs). One of the greatest problems at present however, is that much of the research work is being conducted in isolated groups, with the resulting AGVs sensor/control/command systems being almost completely nontransferable to other AGV designs. This paper describes a new modular method for robot design which when applied to AGVs overcomes the above problems. The method is explained here with respect to all forms of robotics but the examples have been specifically chosen to reflect typical AGV systems.

A Floating-point Extended Kalman Filter Implementation for Autonomous Mobile Robots

Localization and Mapping are two of the most important capabilities for autonomous mobile robots and have been receiving considerable attention from the scientific computing community over the last 10 years. One of the most efficient methods to address these problems is based on the use of the Extended Kalman Filter (EKF). The EKF simultaneously estimates a model of the environment (map) and the position of the robot based on odometric and exteroceptive sensor information. As this algorithm demands a considerable amount of computation, it is usually executed on high end PCs coupled to the robot. In this work we present an FPGA-based architecture for the EKF algorithm that is capable of processing two-dimensional maps containing up to 1.8 k features at real time (14 Hz), a three-fold improvement over a Pentium M 1.6 GHz, and a 13-fold improvement over an ARM920T 200 MHz. The proposed architecture also consumes only 1.3% of the Pentium and 12.3% of the ARM energy per feature.

Paraconsistent Autonomous Mobile Robot Emmy III

This work presents some improvements regarding to the autonomous mobile robot Emmy based on Paraconsistent Annotated Evidential Logic ET. A discussion on navigation system is presented.

Autonomous mobile robots designing for the medical trash collector task

This paper describes the UNESP robotic team in the medical trash collector task, proposed on the 5 rd IEEE Latin American Robots Competition in the LEGO category. We present our understanding of the task and discuss the proposed solution, focusing on the mechanical and computational issues of the robots. The mechanics is based on rigid body capability of transforming rotational into curvilinear movement. With respect to the computational control, the system is modeled as a reactive system with sequential transition of behaviors. A state-machine is proposed to allow this transition, and the synchronization of robotic states is guaranteed by the communication system. The proposed approach has shown itself capable of dealing with the high difficulty degree of this cooperative task. ©2006 IEEE.

Development of an Autonomous Robot for Gas Storage Spheres Inspection

Inspection for corrosion of gas storage spheres at the welding seam lines must be done periodically. Until now this inspection is being done manually and has a high cost associated to it and a high risk of inspection personel injuries. The Brazilian Petroleum Company, Petrobras, is seeking cost reduction and personel safety by the use of autonomous robot technology. This paper presents the development of a robot capable of autonomously follow a welding line and transporting corrosion measurement sensors. The robot uses a pair of sensors each composed of a laser source and a video camera that allows the estimation of the center of the welding line. The mechanical robot uses four magnetic wheels to adhere to the sphere's surface and was constructed in a way that always three wheels are in contact with the sphere's metallic surface which guarantees enough magnetic atraction to hold the robot in the sphere's surface all the time. Additionally, an independently actuated table for attaching the corrosion inspection sensors was included for small position corrections. Tests were conducted at the laboratory and in a real sphere showing the validity of the proposed approach and implementation.

Virtual sensing technology applied to a swarm of autonomous robots.

This thesis proposes a novel technology in the field of swarm robotics that allows a swarm of robots to sense a virtual environment through virtual sensors. Virtual sensing is a desirable and helpful technology in swarm robotics research activity, because it allows the researchers to efficiently and quickly perform experiments otherwise more expensive and time consuming, or even impossible. In particular, we envision two useful applications for virtual sensing technology. On the one hand, it is possible to prototype and foresee the effects of a new sensor on a robot swarm, before producing it. On the other hand, thanks to this technology it is possible to study the behaviour of robots operating in environments that are not easily reproducible inside a lab for safety reasons or just because physically infeasible. The use of virtual sensing technology for sensor prototyping aims to foresee the behaviour of the swarm enhanced with new or more powerful sensors, without producing the hardware. Sensor prototyping can be used to tune a new sensor or perform performance comparison tests between alternative types of sensors. This kind of prototyping experiments can be performed through the presented tool, that allows to rapidly develop and test software virtual sensors of different typologies and quality, emulating the behaviour of several hardware real sensors. By investigating on which sensors is better to invest, a researcher can minimize the sensors’ production cost while achieving a given swarm performance. Through augmented reality, it is possible to test the performance of the swarm in a desired virtual environment that cannot be set into the lab for physical, logistic or economical reasons. The virtual environment is sensed by the robots through properly designed virtual sensors. Virtual sensing technology allows a researcher to quickly carry out real robots experiment in challenging scenarios without all the required hardware and environment.

A vision-based strategy for autonomous aerial refueling tasks

Autonomous aerial refueling is a key enabling technology for both manned and unmanned aircraft where extended flight duration or range are required. The results presented within this paper offer one potential vision-based sensing solution, together with a unique test environment. A hierarchical visual tracking algorithm based on direct methods is proposed and developed for the purposes of tracking a drogue during the capture stage of autonomous aerial refueling, and of estimating its 3D position. Intended to be applied in real time to a video stream from a single monocular camera mounted on the receiver aircraft, the algorithm is shown to be highly robust, and capable of tracking large, rapid drogue motions within the frame of reference. The proposed strategy has been tested using a complex robotic testbed and with actual flight hardware consisting of a full size probe and drogue. Results show that the vision tracking algorithm can detect and track the drogue at real-time frame rates of more than thirty frames per second, obtaining a robust position estimation even with strong motions and multiple occlusions of the drogue.