Yvan R. Petillot

• PhD, Université de Bretagne
• Heriot-Watt University

This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of RL compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated h...

Simulations are highly valuable in marine robotics, offering a cost-effective and controlled environment for testing in the challenging conditions of underwater and surface operations. Given the high costs and logistical difficulties of real-world trials, simulators capable of capturing the operational conditions of subsea environments have become...

Introduction This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, contributing to the Industry 4.0 paradigm. Industry 4.0, emphasizing data-driven processes, connectivity, and robotics, enhances accessibility and sustainability across the value chain....

This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm. Industry 4.0, driven by data, connectivity, analytics, and robotics, promises enhanced accessibility and sustainability throughout the value chain. The integ...

The aim of this study is to design an adaptive controller for the hard contact interaction problem of underwater vehicle-manipulator systems to realize asset inspection through physical interaction. The proposed approach consists of a force and position controller in the operational space of the end-effector of the robot manipulator mounted on an u...

Robotic systems may frequently come across similar manipulation planning problems that result in similar motion plans. Instead of planning each problem from scratch, it is preferable to leverage from previously computed motion plans, i.e., experiences, to ease the planning. Different approaches have been proposed to exploit prior information on nov...

Underwater acoustic sensor networks (UWASNs) can revolutionize the subsea domain by enabling low-cost monitoring of subsea assets and the marine environment. Accurate localization of the UWASNs is essential for these applications. In general, range-based localization techniques are preferred for their high accuracy in estimated locations. However,...

Unforeseen events are frequent in the real-world environments where robots are expected to assist, raising the need for fast replanning of the policy in execution to guarantee the system and environment safety. Inspired by human behavioural studies of obstacle avoidance and route selection, this paper presents a hierarchical framework which generat...

The following paper presents an adaptive path planning algorithm for cooperative localisation in the maritime environment. It considers the scenario where an Autonomous Surface Vehicle (ASV) acts as a Communication and Naviga- tion Aid (CNA) to support Autonomous Underwater Vehicles (AUVs) with range measurements. As AUVs have no access to GPS whil...

Autonomous vehicles and robots are increasingly being deployed to remote, dangerous environments in the energy sector, search and rescue and the military. As a result, there is a need for humans to interact with these robots to monitor their tasks, such as inspecting and repairing offshore wind-turbines. Conversational Agents can improve situation...

Remotely operated vehicles (ROVs) revolutionized the subsea industry when they were introduced in the 1960s. They were more powerful and inherently safer, and they could go deeper than divers. However, they require a tether and a support ship, which makes their use complex and expensive. Autonomous marine vehicles (AMVs) have long been seen as a ga...

Autonomous underwater vehicles (AUVs) are being tasked with increasingly complex missions. The acoustic communications required for AUVs are, by the nature of the medium, low bandwidth while adverse environmental conditions underwater often mean they are also intermittent. This has motivated development of highly autonomous systems, which can opera...

Autonomous interaction with the underwater environment has increased the interest of scientists in the study of control structures for lightweight underwater vehicle-manipulator systems. This paper presents an essential comparison between two different strategies of designing control laws for a lightweight underwater vehicle-manipulator system. The...

Low-level control of autonomous underwater vehicles (AUVs) has been extensively addressed by classical control techniques. However, the variable operating conditions and hostile environments faced by AUVs have driven researchers towards the formulation of adaptive control approaches. The reinforcement learning (RL) paradigm is a powerful framework...

Nowadays, research in autonomous underwater manipulation has demonstrated simple applications like picking an object from the sea floor, turning a valve or plugging and unplugging a connector. These are fairly simple tasks compared with those already demonstrated by the mobile robotics community, which include, among others, safe arm motion within...

To have a significant and fair competition an adequate scoring system is necessary. Different scoring systems exist, each one directly related to the nature and goals of the competition, e.g. student/educational, focused on benchmarking, Grand Challenge style, etc. However, the design of such systems is not an easy task. It is mandatory to design a...

In this paper we outline the euRathlon 2015 and the ERL Emergency 2017 Grand Challenge robotics competitions, and the results and lessons learned from euRathlon 2015. Staged at Piombino, Italy in September 2015, euRathlon 2015 was the world’s first multi-domain (air, land and sea) multi-robot search and rescue competition. In a mock disaster scenar...

An underwater manipulator is a complex system, highly non-linear and subject to disturbances caused by underwater effects. To obtain a reliable system, robust control strategies have to be designed for the manipulator. The main contribution of this paper is the development of the low-level position/force control structure for an underwater manipula...

The introduction of SAS (Synthetic Aperture Sonar) systems has been a game changer for underwater surveys. The gain in resolution, compared to traditional sidescan systems, created a paradigm shift as the information contained in a SAS image switches from shadows to highlights. SAS systems traditionally perform lawnmower type surveys, but the need...

A warping operator consists of an invertible axis deformation applied either in the signal domain or in the corresponding Fourier domain. Additionally, a warping transformation is usually required to preserve the signal energy, thus preserving orthogonality and being invertible by its adjoint. Initially, the design of such operators has been motiva...

Synthetic aperture imaging systems achieve constant azimuth resolution by coherently summating the observations acquired along the aperture path. At this aim, their locations have to be known with subwavelength accuracy. In underwater Synthetic Aperture Sonar (SAS), the nature of propagation and navigation in water makes the retrieval of this infor...

Depth profile measurements are performed in highly scattering underwater environments at stand-off distances equivalent to nine attenuation lengths. The optical system used a scanning transceiver and single-photon detection to produce high-resolution images with milli-watt average powers.

The introduction of SAS (Synthetic Aperture Sonar) systems has been a game changer for underwater surveys. The gain in resolution, compared to traditional sidescan systems, created a paradigm shift as the information contained in a SAS image switches from shadows to highlights. SAS systems traditionally perform lawnmower type surveys, but the need...

Circular Synthetic Aperture Sonar (CSAS) processing computes coherently Synthetic Aperture Sonar (SAS) data acquired along a circular trajectory. This approach has a number of advantages, in particular it maximises the aperture length of a SAS system, producing very high resolution sonar images. CSAS image reconstruction using back-projection algor...

This paper presents an optical depth imaging system optimized for highly scattering environments such as underwater. The system is based on the time-correlated single-photon counting (TCSPC) technique and the time-of-flight approach. Laboratory-based measurements demonstrate the potential of underwater depth imaging, with specific attention given t...

Resolution comes from the Latin word resolvo, which literally means “untie a knot.” The meaning evolved, in optics, toward the capability to distinguish two scattering points. For the MCM (Mine Counter Measure) problem, the introduction of synthetic aperture systems, and the resulting drastic increase in resolution, has been a game changer, as the...

Multiple-input–multiple-output (MIMO) sonar systems offer new perspectives for target detection and area surveillance. This paper introduces a unified formulation for sonar MIMO systems and focuses on the target detection and recognition capability of these systems. The multiplication of the number of transmitters and receivers not only provides a...

Synthetic aperture systems rely on accurate knowledge of Transmitter (Tx) and Receiver (Rx) positions at each ping. In Synthetic Aperture Sonar (SAS), due to the nature of propagation and navigation in water, they have to be estimated by either physical sensors or raw data or a combination of these and employed to compensate motion errors. Hence, m...

Multiple-input multiple-output (MIMO) sonar systems offer new perspectives for area surveillance especially in complex environments where strong multipath and dense clutter can become very challenging. This study proposes a MIMO sonar system based scheme to tackle the difficult problem of harbour surveillance. An emphasis is put on recognition and...

The euRathlon project was an FP7-funded Coordination and Support Action (2013–2015). Itsmain aim was to organize outdoor robotics competitions in realistic search and rescue response scenarios for cooperative land, sea, and air robots. Participant teams were requested to test the intelligence and autonomy of their robots in scenarios inspired by th...

Staged at Piombino, Italy in September 2015, euRathlon 2015 was the world’s first multi-domain (air, land and sea) multi-robot search and rescue competition. In a mock-disaster scenario inspired by the 2011 Fukushima NPP accident, the euRathlon 2015 Grand Challenge required teams of robots to cooperate to map the area, find missing workers and stem...

Technologies for oceans engineering are being based in autonomous solutions (mainly adaptation capabilities) able to tackle more complex maritime missions. This paper presents how an Intelligent Vehicle Control Architecture (IVCA) for marine robots deals with fault-tolerant capabilities in order to build a robust approach. The IVCA moves away from...

This paper proposes a control strategy for station keeping of an underwater vehicle- manipulator system when the manipulator is asked to perform a certain task. The control structure consists of an inverse dynamic feedforward controller, the interaction forces between subsystems and a PILIM feedback controller for pitch control of the vehicle. The...

Sea robotics competitions have been happening for almost twenty years. Teams have been improving and performing better and better each year. Therefore, the need of assessing their performance through means of fair comparison and rigorous metrics arises. Benchmarking the results is important to understand how teams performed compared to each other b...

We investigate the potential of a depth imaging system for underwater environments. This system is based on the timeof-flight approach and the time correlated single-photon counting (TCSPC) technique. We report laboratory-based measurements and explore the potential of achieving sub-centimeter xyz resolution at 10’s meters stand-off distances. In...

A depth imaging system, based on the time-of-flight approach and the time-correlated single-photon counting (TCSPC) technique, was investigated for use in highly scattering underwater environments. The system comprised a pulsed supercontinuum laser source, a monostatic scanning transceiver, with a silicon single-photon avalanche diode (SPAD) used f...

Stereo vision and structured light are compared in a common underwater environment with known dimensions and objects. Two different sensors are mounted on top of a Cartesian robot that moves with a known and programmed trajectory. The resulting point clouds from each sensor are compared in terms of distance from point to point, and measurements in...

Multiple Input Multiple Output sonar systems offer new perspectives for target detection and area surveillance. This paper introduces MIMO sonar systems and focuses on its capabilities. The multiplication of the number of transmitters and receivers not only provides a greater variety in terms of target view angles but provides also in meaningful st...

This paper presents a study of the interaction effects between a lightweight underwater vehicle and the attached manipulator. Based on a tree representation of the system, the dynamic and hydrodynamic model of the UVMS is computed and the coupling effects are analysed. Simulations show that having a manipulator with considerable mass compared with...

Vehicle operations in underwater environments are often compromised by poor visibility conditions. For instance, the perception range of optical devices is heavily constrained in turbid waters, thus complicating navigation and mapping tasks in environments such as harbors, bays, or rivers. A new generation of high-definition forward-looking sonars...

Time-of-flight single-photon depth imaging measurements made under a variety of free-space and underwater conditions are presented. We will include discussion of future system performance and the effect of environmental conditions such as scattering and turbulence.

Advanced ocean systems are increasing their capabilities and the degree of autonomy more and more in order to perform more sophisticated maritime missions. Remotely operated vehicles are no longer cost-effective since they are limited by economic support costs, and the presence and skills of the human operator. Alternatively, autonomous surface and...

MIMO stands for Multiple Inputs Multiple Outputs. Such systems have received a lot of interests in the radar community during the last decade. One of the main reason behind this is the greater variety in terms of target view angles compared with traditional monostatic systems. With several independent views one can hope to reduce the speckle effect...

Multiple Input Multiple Output sonar systems offer new perspectives for target detection and underwater surveillance. In this paper we present an unified formulation for sonar MIMO systems and study their properties in terms of target recognition and imaging. Here we are interested in large MIMO systems. The multiplication of the number of transmit...

This paper describes the use of local sea-floor characteristics to train a neural network to remove false alarms from an Automatic Target Recognition (ATR) algorithm. We demonstrate that this reduces the Probability of False Alarm (PFA) in difficult areas without impacting the Probability of Detection (PD) in flat areas. The sea-floor characteristi...

The aim of euRathlon is to create real-world robotics challenges to test the intelligence and autonomy of outdoor robots in demanding mock disaster-response scenarios. Inspired by the Fukushima accident we are working toward a competition that requires autonomous flying, land and underwater robots acting together to survey the disaster, collect env...

The main advantages of MIMO (Multiple Input Multiple Output) sonar systems come from the assumption of independent observations between each transmitter/receiver pairs.The independence of the observations ensures a unbiased set of measurements and then provides true statistics on the target. In this paper we study the correlation between views in M...

Software engineering plays a key role in state-of-the-art robotics where more effective and efficient software development solutions are needed for implementation and integration of advanced robotics capabilities. Component-based software engineering and model-driven software development are two paradigms suitable to deal with such challenges. This...

We are interested in the coverage path planning problem with imperfect sensors, within the context of robotics for mine countermeasures. In the studied problem, an autonomous underwater vehicle (AUV) equipped with sonar surveys the bottom of the ocean searching for mines. We use a cellular decomposition to represent the ocean floor by a grid of uni...

This paper proposes a general framework to control underwater vehicle-manipulator systems from external sensors. The design of the control law follows several constraints and criteria to optimize the overall behavior. The task is defined in the sensor space, that is suited for visual servoing from camera or sonar images. The control input distribut...

Autonomous underwater vehicles (AUVs) have become a standard tool for data gathering and intervention in security, offshore and marine science applications. In these environments, mission effectiveness directly depends on vehicle's operability. Operability underlies the vehicle's ultimate availability. Two main vehicle characteristics can improve o...

Two-dimensional forward-looking sonars such as Blueview or DIDSON are becoming a standard sensor in both remotely-operated and autonomous underwater vehicles. Registration of imagery obtained from this sensors is of great interest since it constitutes a key step in several applications like the generation of acoustic mosaics or the extraction of ve...

The increasing demand for more self-governed assistance in maritime activities is leading ocean engineering research projects to combine diverse autonomous capabilities developed at geographically-dispersed locations. Availability of such capabilities as well as experiments in water is a critical issue that can seriously impact on the project miles...

Current research projects are developing technologies that require more and more the integration of different system capabilities placed at geographically-dispersed locations. The challenge when integrating system capabilities is to choose the right system components to be integrated in order to fulfill the deadline given by the project milestones....

Automatic detection of underwater objects is a critical task for a variety of underwater applications. Rapid detection approaches are needed to tackle the large amount of data produced using state-of-the-art sensors such as Synthetic Aperture Sonar. Accurate detection approaches are also required to reduce the number of false alarms and enable on t...

The use of autonomous underwater vehicles for a variety of purposes is set to increase in the future. A key issue is accurate navigation, especially for survey applications large cumulative error are introduced by the various position sensors: accelerometer; Doppler velocity log; compass; inertial navigation sensors. Algorithms such as simultaneous...

Autonomous underwater vehicles (AUVs) have become a standard tool for data gathering and intervention in security, offshore and marine science applications. In these environments, mission effectiveness directly depends on vehicle’s operability. Operability underlies the vehicle’s ultimate availability. Two main vehicle characteristics can improve o...

TRIDENT is the official acronym used for a funded European project entitled: 'Marine Robots and Dexterous Manipulation for Enabling Autonomous Underwater Multipurpose Intervention Missions'. This project has demonstrated a new approach for multipurpose underwater intervention tasks with diverse potential applications ranging from underwater archaeo...

This paper presents a model-based, filter response algorithm for Automatic Target Recognition (ATR) in Sidescan Sonar (SSS). The filters are created from the projection of a large set of generating boxes. The first and second-order statistics over the highlight and shadow regions of the projected boxes form a feature vector for each pixel in the im...

Current unmanned marine vehicles are increasing their autonomy so that more sophisticated maritime missions can be carried out. Remotely operated vehicles are no longer cost-effective since they are limited by economic support costs, and the presence and skills of the human operator. This paper proposes an Intelligent Control Architecture (ICA) to...

This paper presents a method to build large-scale mosaics adapted to underwater sonar imagery. By assuming a simplified imaging model, we propose to address the registrations between images using Fourier-based methods which, unlike feature-based methods, prove well suited to handle the characteristics of forward-looking sonar images, such as low re...

This paper presents some of the challenges related to multi-robot cooperation for the marine environment. Special attention is given to the world representation topic and to the communication challenges. Ontologies represent the tool to store and dynamically update world information. Due to the conditions of the underwater domain, communication amo...

It has been shown that time-reversal (TR), which was developed in the acoustics domain, can also improve the detection performance of a radar system. However, the TR technique is no longer a good choice when the noise level is high since the retransmitted signal contains significant noise components. We investigate a multiple-input multiple-output...

We describe a novel architecture for automotive vision organized on five levels of abstraction, i.e., sensor, data, semantic, reasoning, and resource allocation levels, respectively. Although we implement and evaluate processes to detect and classify other participants within the immediate environment of a moving vehicle, our main emphasis is on th...

Objective A fully automated and efficient method for segmenting ten major structures within the heart in Cardiac CT Angiography data for the purposes of display or cardiac functional analysis. Materials and methods A spatially varying Gaussian classifier is a flexible model for segmentation, combining the advantages of atlas-based frameworks, with...

The capability and cost effectiveness that unmanned underwater vehicles (UUVs) bring to underwater survey, target detection and identification operations has been widely demonstrated and accepted in recent years. However, these operations still rely mainly on pre-planned missions and require a high level of expert human interaction both at the plan...

The use of Remotely Operated Vehicles (ROVs) is ultimately limited by economic support costs, and the presence and skills of the human operator. Autonomous surface and underwater vehicles have the potential to operate with greatly reduced overhead costs and level of operator intervention. This paper proposes an Intelligent Control Architecture (ICA...

MIMO systems have raised a lot of interests in the recent years especially in the radar community. For MIMO systems with widely spaced antennas for example it has been shown that channel matrices are decorrelated from one another. The view diversity of an illuminated target is then increased. And as a consequence the detection probability of statis...

Multiple-input multiple-output (MIMO) radars have many advantages over their phased-array counterparts: improved spatial resolution; better parametric identifiably and greater flexibility to design the transmit beampattern. The design of the transmit beampatterns generally requires the waveforms to have arbitrary auto- and cross-correlation propert...

Detecting and selecting proper landmarks is a key issue to solve Simultaneous Localization and Mapping (SLAM). In this work, we present a novel approach to perform this landmark detection. Our approach is based on using three sources of information: 1) three-dimensional topological information from SLAM; 2) context information to characterize regio...

An overview of underwater SLAM implementations as well as submapping SLAM approaches is given in this paper. Besides, the implementation of the so called selective submap joining SLAM on the SPARUS AUV is presented. SPARUS carries a down-looking optical camera. The information gather by this camera is run through SLAM, together with on-board naviga...

This paper proposes a semantic world model framework for hierarchical distributed representation of knowledge in autonomous underwater systems. This framework aims to provide a more capable and holistic system, involving semantic interoperability among all involved information sources. This will enhance interoperability, independence of operation,...

�bstract— Simultaneous Localization and MappingSLAM) consists on building a map of an unknown environment, while simultaneously determining the location of the vehicle within this map. Building a map implies finding a proper representa- tion for its salient features, which are used as landmarks for the localization problem. These landmarks must be...

Multiple-input multiple-output (MIMO) radars have many advantages over their phased-array counterparts: improved spatial resolution; better parametric identifiably and greater flexibility to design the transmit beampattern. The design of the transmit beampatterns generally requires the waveforms to have arbitrary auto-and cross-correlation properti...

Marine mammals have developed highly effective sonar systems for detecting, identifying, and following underwater objects. In this paper we demonstrate that bio-inspired wideband sonar offers great capability for tracking cables on the seafloor. The analysis of biological signals, including dolphin clicks, suggests two approaches. The first is to u...