Detection,localisation and tracking of pallets using machine learning techniques and 2D range data

The problem of autonomous transportation in industrial scenarios is receiving a renewed interest due to the way it can revolutionise internal logistics, especially in unstructured environments. This paper presents a novel architecture allowing a robot to detect, localise, and track (possibly multiple) pallets using machine learning techniques based on an on-board 2D laser rangefinder only. The architecture is composed of two main components: the first stage is a pallet detector employing a Faster Region-Based Convolutional Neural Network (Faster R-CNN) detector cascaded with a CNN-based classifier; the second stage is a Kalman filter for localising and tracking detected pallets, which we also use to defer commitment to a pallet detected in the first stage until sufficient confidence has been acquired via a sequential data acquisition process. For fine-tuning the CNNs, the architecture has been systematically evaluated using a real-world dataset containing 340 labelled 2D scans, which have been made freely available in an online repository. Detection performance has been assessed on the basis of the average accuracy over k-fold cross-validation, and it scored 99.58% in our tests. Concerning pallet localisation and tracking, experiments have been performed in a scenario where the robot is approaching the pallet to fork. Although data have been originally acquired by considering only one pallet as per specification of the use case we consider, artificial data have been generated as well to mimic the presence of multiple pallets in the robot workspace. Our experimental results confirm that the system is capable of identifying, localising and tracking pallets with a high success rate while being robust to false positives.

     

Plasmomechanical Systems: Principles and Applications

Extreme confinement of electromagnetic waves and mechanical displacement fields to nanometer dimensions through plasmonic nanostructures offers unprecedented opportunities for greatly enhanced interaction strength, increased bandwidth, lower power consumption, chip-scale fabrication, and efficient actuation of mechanical systems at the nanoscale. Conversely, coupling mechanical oscillators to plasmonic nanostructures introduces mechanical degrees of freedom to otherwise static plasmonic structures thus giving rise to the generation of extremely large resonance shifts even for minor position changes. This nanoscale marriage of plasmonics and mechanics has led to the emergence of a new field of study called plasmomechanics that explores the fundamental principles underneath the coupling between light and plasmomechanical nanoresonators. In this review, both the fundamental concepts and applications of plasmomechanics as an emerging field of study are discussed. After an overview of the basic principles of plasmomechanics, the active tuning mechanisms of plasmonic nano-mechanical systems are extensively analyzed. Moreover, the recent developments on the practical implications of plasmomechanic systems for such applications as biosensing and infrared detection are highlighted. Finally, an outlook on the implications of the plasmomechanical nanosystems for development of point-of-care diagnostic devices that can help early and rapid detection of fatal diseases are forwarded.     

Pre-emptive versus non-pre-emptive real time scheduling in intelligent mobile robotics

Autonomous and semi-autonomous mobile robots have to perform a multiplicity of concurrent activities in order to carry out useful tasks in unstructured human-populated environments. Even if it is commonly accepted that a successful accomplishment of assigned tasks requires some sort of real time capability to quickly react and adapt to environmental changes, it is not clear which operating system support is best suited for the scheduling and synchronizing of concurrent activities with different timing requirements. This paper discusses this problem, comparing two different real time scheduling policies for autonomous robot applications: pre-emptive rate monotonic and non pre-emptive Earliest Deadline First (EDF). Experimental results are presented and evaluated.     

Efficiency measurement and uncertainty discussion of an electric engine powered by a "self-breathing" and "self-humidified" proton exchange membrane fuel cell

The efficiency of an automotive engine based on a "self-breathing" and "self-humidified" proton exchange membrane fuel cell stack (PEM FC) connected to a dc brushless electrical motor was measured under variable power load conditions. Experiments have been carried out on a small scale 150 W engine model. After determining the fuel cell static polarization curve and the time response to power steps, the system was driven to copy on the test bench a "standard urban load cycle" and its instantaneous efficiencies were measured at an acquisition rate of 5 Hz. The integral system efficiency over the entire urban load cycle, comprising the losses of the unavoidable auxiliary components of the engine, was then calculated. The fuel cell stack was operated mainly in "partial" dead-end mode, with a periodic anode flow channel purging, and one test was carried out in "pure" dead-end mode, with no anode channel purging. An uncertainty analysis of the efficiencies was carried out, taking into account either type A and type B evaluation methods, strengthening the discussion about the outcomes obtained for a system based on this novel simplified FC type. For our small scale engine we measured over the standard urban cycle, on the basis of the H(2) high heating value (HHV), a tank-to-wheel integral efficiency of (18.2+/-0.8)%, when the fuel cell was operated with periodic flow channel purging, and of (21.5+/-1.3)% in complete dead-end operation mode.     

Progress in the MITICA beam source design

In the framework of the development of the ITER neutral beam (NB) system, a test facility is planned to be built in Padova. A full size prototype of the ITER heating NB injector (MITICA) shall be built and tested at full beam power (17 MW) as per ITER requirements. The design of the MITICA beam source has further progressed following updated optimization and overall integration criteria. In the paper, the major design choices and revisions are presented, together with some results of numerical analyses carried out in order to assess the electrostatic and thermo-mechanical behaviour of the source.     

A Sensitivity-Based Design Space Exploration Methodology for Embedded Systems

In this paper, we propose a system-level design methodology for the efficient exploration of the architectural parameters of the memory sub-systems, from the energy-delay joint perspective. The aim is to find the best configuration of the memory hierarchy without performing the exhaustive analysis of the parameters space. The target system architecture includes the processor, separated instruction and data caches, the main memory, and the system buses. To achieve a fast convergence toward the near-optimal configuration, the proposed methodology adopts an iterative local-search algorithm based on the sensitivity analysis of the cost function with respect to the tuning parameters of the memory sub-system architecture. The exploration strategy is based on the Energy-Delay Product (EDP) metric taking into consideration both performance and energy constraints. The effectiveness of the proposed methodology has been demonstrated through the design space exploration of a real-world case study: the optimization of the memory hierarchy of a MicroSPARC2-based system executing the set of Mediabench benchmarks for multimedia applications. Experimental results have shown an optimization speedup of 2 orders of magnitude with respect to the full search approach, while the near-optimal system-level configuration is characterized by a distance from the optimal full search configuration in the range of 2%.     

The evaluation of a color-naming test for color blindness.

A simple color-naming test for color blindness was developed using the Eastman Color Temperature Meter, and compared with three other color-vision tests: the Farnsworth-Munsell 100-Hue Test, AO Pseudo-Isochromatic Plates, and Freeman Illuminant-Stable Color Vision Test on a sample of 100 Ss. "The data indicated that there was fairly high agreement among the American Optical, Eastman and Freeman tests… . The correlations of the Farnsworth with the other three tests were somewhat lower, indicating that the Farnsworth is apparently measuring factors not measured by the other tests… . It is significant that high correlations were obtained between naming and color competence." (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

UGUS, a reporter for use with destabilizing N-termini

Due to constraints in vector construction, reporter polypeptides often carry N-terminal sequences of extraneous origin. Since protein half-life can be influenced by small determinants in the N-terminus, such foreign sequences can destabilize proteins and compromise results of reporter-based studies. We provide a real-life example of this problem (destabilizing sequences derived from a ribosomal protein) and show that it can be solved with the ubiquitin fusion technique, in which ubiquitin sequences are placed upstream of the reporter, in our case beta-glucuronidase. Post-translational processing by characterized pathways removes the ubiquitin together with destabilizing sequences, generating a stable reporter whose N-terminus is constant.