Mario Di Castro

A Multi-Sensor RSS Spatial Sensing-Based Robust Stochastic Optimization Algorithm for Enhanced Wireless Tethering

The reliability of wireless communication in a network of mobile wireless robot nodes depends on the received radio signal strength (RSS). When the robot nodes are deployed in hostile environments with ionizing radiations (such as in some scientific facilities), there is a possibility that some electronic components may fail randomly (due to radiation effects), which causes problems in wireless connectivity. The objective of this paper is to maximize robot mission capabilities by maximizing the wireless network capacity and to reduce the risk of communication failure. Thus, in this paper, we consider a multi-node wireless tethering structure called the “server-relay-client” framework that uses (multiple) relay nodes in between a server and a client node. We propose a robust stochastic optimization (RSO) algorithm using a multi-sensor-based RSS sampling method at the relay nodes to efficiently improve and balance the RSS between the source and client nodes to improve the network capacity and to provide redundant networking abilities. We use pre-processing techniques, such as exponential moving averaging and spatial averaging filters on the RSS data for smoothing. We apply a receiver spatial diversity concept and employ a position controller on the relay node using a stochastic gradient ascent method for self-positioning the relay node to achieve the RSS balancing task. The effectiveness of the proposed solution is validated by extensive simulations and field experiments in CERN facilities. For the field trials, we used a youBot mobile robot platform as the relay node, and two stand-alone Raspberry Pi computers as the client and server nodes. The algorithm has been proven to be robust to noise in the radio signals and to work effectively even under non-line-of-sight conditions.

A framework of teleoperated and stereo vision guided mobile manipulation for industrial automation

Smart and flexible manufacturing requests the adoption of industrial mobile manipulators in factory. The goal of autonomous mobile manipulation is the execution of complex manipulation tasks in unstructured and dynamic environments. It is significant that a mobile manipulator is able to detect and grasp the object in a fast and accurate manner. In this research, we developed a stereo vision system providing qualified point cloud data of the object. A modified and improved iterative closest point algorithm is applied to recognize the targeted object greatly avoiding the local minimum in template matching. Moreover, a stereo vision guided teleoperation control algorithm using virtual fixtures technology is adopted to enhance robot teaching ability. Combining these two functions, the mobile manipulator is able to learn semi-autonomously and work autonomously. The key components and the system performance are then tested and proved in both simulation and experiments.

CERNTAURO: A Modular Architecture for Robotic Inspection and Telemanipulation in Harsh and Semi-Structured Environments

Intelligent robotic systems are becoming essential for industries, nuclear plants, and for harsh environments in general, such as the European Organization for Nuclear Research (CERN) particles accelerator complex and experiments. In order to increase safety and machine availability, robots can perform repetitive, unplanned, and dangerous tasks, which humans either prefer to avoid or are unable to carry out due to hazards, size constraints, or the extreme environments in which they take place. A novel robotic framework for autonomous inspections and supervised teleoperations in harsh environments is presented. The proposed framework covers all aspects of a robotic intervention, from the specification and operator training, the choice of the robot and its material in accordance with possible radiological contamination risks, to the realization of the intervention, including procedures and recovery scenarios. The robotic solution proposed in this paper is able to navigate autonomously, inspecting unknown environments in a safe way. A new real-time control system was implemented in order to guarantee a fast response to environmental changes and adaptation to different type of scenarios the robot may find in a semi-structured and hazardous environment. Components of the presented framework are: a novel bilateral master-slave control, a new robotic platform named CERNbot, and an advanced user-friendly multimodal human-robot interface, also used for the operators’ offline training, allowing technicians not expert in robot operation to perform inspection/maintenance tasks. The proposed system has been tested and validated with real robotic interventions in the CERN hazardous particle accelerator complex.

Image mosaicing of tunnel wall images using high level features

This paper proposes a novel approach for position offset correction of images taken from a moving robotic platform in tunnel environments using image mosaicing. An image mosaic is formed by combining multiple images which capture overlapping components of a scene into a larger image. Unlike current image mosaicing methods, which use low-level features such as corners, our method uses binary edges as high-level features for image registration via template matching. This is necessary since such low-level features are absent or rare in tunnel environments. A shading correction algorithm is applied as a pre-processing step to adjust the uneven illumination present in this environment. This technique is simple and efficient while being robust to small camera rotations and small variations in camera distance from the wall. Experimental results show that our method contributes to good image mosaicing results with a low computational complexity, which is attractive for real-time image-based inspection applications.

A Real-Time Reconfigurable Collision Avoidance System for Robot Manipulation

Intelligent robotic systems are becoming fundamental actors in industrial and hazardous facilities scenarios. Aiming to increase personnel safety and machine availability, robots can help perform repetitive and dangerous tasks which humans either prefer to avoid or are unable to do because of hazards, space constraints or the extreme environments in which they take place, such as outer space or radioactive experimental areas. Teleoperated robots need user friendly and safety tools to be safely operated in harsh environments where the intervention scenarios are unstructured and most of the time dangerous for human intervention. In many robotic interventions in harsh environments, a dual arms robotic system is needed to perform difficult task such as cutting, drilling etc. To ensure the safety of the robotic system and the machines to be tele-manipulated, as well as increasing the uptime of the plants, a real-time reconfigurable self-collision avoidance system coupled to a virtual augmented reality scenario is fundamental to help the operator during the intervention. In addition, it is important to provide to the operator a uniform control system, in order to not create confusion when several operations are performed using different robotic platforms. For this reason, it is vital that the self-collision avoidance system is adaptable to the current robot hardware and software configurations. In this paper, a novel reconfigurable collision avoidance system for robot manipulation running in real time is presented. The novelty of the proposed solution is the capability to be adaptable to different robots configuration and installation taking into account different parameters like the type and the number of robotic arms, as well as their orientation. The novel system is able to avoid collision not only within the robot itself, but it can avoid collision also with external unexpected objects. The structure of the novel solution is presented, as well as its validation in the CERN accelerators facilities.

An RGB-D based Augmented Reality 3D Reconstruction System for Robotic Environmental Inspection of Radioactive Areas.

Preparing human intervention in hazardous, unknown and unstructured environments is a difficult task. The intervention should focus on the optimization of the operations in order to reduce the personnel exposure to hazards. Optimizing these operations is not always possible, due to a lack of information about the intervention environment: such information can be collected through a robotic inspection before the preparation of the intervention. The data collected during this inspection, such as radiation, temperature and oxygen level, must be accurate and precisely positioned in the environment in order to optimize the humans approaching path and their stay in the intervention area. In this paper we present a robotic system for collecting physical quantities, precisely positioned in the environment, which is easy to use by the robot operator and it is seamlessly integrated in the robot control. The operator is helped by the system in finding the most dangerous zones, which collects all the sensor readings while building a 3D model of the environment. Preliminary results are presented using CERN’s accelerators facilities as testing area.

Novel Pose Estimation System for Precise Robotic Manipulation in Unstructured Environment.

Intelligent robotic systems are becoming essential for industry and harsh environments, such as the CERN accelerator complex. Aiming to increase safety and machine availability, robots can help perform repetitive and dangerous tasks, which humans either prefer to avoid or are unable to do because of hazards, size constraints, or the extreme environments in which they take place, such as outer space or radioactive experimental areas. A fundamental part of intelligent robots is the perception of the environment that is possible to obtain only knowing the 6D pose of the objects around the robotic system. In this paper, we present a novel algorithm to estimate the 6D pose of an object that can be manipulated by a robot. The proposed algorithms works consistently in unstructured and harsh environments presenting several constraints like variable luminosity, difficult accessibility and light reflections. The algorithm detects the position and rotation of an object using 3D cameras. The procedure has been developed using Point Cloud Library to manage the point cloud created with an RGBD Camera. The position and rotation of an object is useful in augmented reality systems to help the tele-operator and for the realization of autonomous or semi-autonomous tasks.

An Advanced, Adaptive and Multimodal Graphical User Interface for Human-robot Teleoperation in Radioactive Scenarios

In this paper we present the user interface of a tele-robotic system, which allows CERN users to perform visual inspections and tele-manipulation tasks inside the CERN accelerator complex. This graphical user interface has been designed to be simple to use, in order to provide the operator with a comfortable system. Moreover, the user interface is robot independent and it adapts itself to the robot configuration, in order to provide a general way for controlling any kind of robot used at CERN. Furthermore it allows the operator to choose between different kinds of input (e.g. keyboard, joypad, haptic device, etc), in order to provide the most easy human-robot interaction interface, which is a fundamental requirement for safe operations.