In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

The research on autonomous miniature flying robots has intensified considerably thanks to the recent growth of civil and military interest in unmanned aerial vehicles (UAV). This paper summarizes the final results of the modeling and control parts of OS4 project, which focused on design and control of a quadrotor. It introduces a simulation model which takes into account the variation of the aerodynamical coefficients due to vehicle motion. The control parameters found with this model are successfully used on the helicopter without re-tuning. The last part of this paper describes the control approach (integral backstepping) and the scheme we propose for full control of quadrotors (attitude, altitude and position). Finally, the results of autonomous take-off, hover, landing and collision avoidance are presented.

Full control of a quadrotor

Machining difficult-to-machine materials such as alloys used in aerospace, nuclear and medical industries are usually accompanied with low productivity, poor surface quality and short tool life. Despite the broad use of the term difficult-to-machine or hard-to-cut materials, the area of these types of materials and their properties are not clear yet. On the other hand, using cutting fluids is a common technique for improving machinability and has been acknowledged since early 20th. However, the environmental and health hazards associated with the use of conventional cutting fluids together with developing governmental regulations have resulted in increasing machining costs. The aim of this paper is to review and identify the materials known as difficult-to-machine and their properties. In addition, different cutting fluids are reviewed and major health and environmental concerns about their usage in material cutting industries are defined. Finally, advances in reducing and/or eliminating the use of conventional cutting fluids are reviewed and discussed.

/pdf/environmentally-conscious-machining-of-difficult-to-machine-32ov2j8z58.pdf

Environmentally conscious machining of difficult-to-machine materials with regard to cutting fluids

Motion planning is a fundamental research area in robotics. Sampling-based methods offer an efficient solution for what is otherwise a rather challenging dilemma of path planning. Consequently, these methods have been extended further away from basic robot planning into further difficult scenarios and diverse applications. A comprehensive survey of the growing body of work in sampling-based planning is given here. Simulations are executed to evaluate some of the proposed planners and highlight some of the implementation details that are often left unspecified. An emphasis is placed on contemporary research directions in this field. We address planners that tackle current issues in robotics. For instance, real-life kinodynamic planning, optimal planning, replanning in dynamic environments, and planning under uncertainty are discussed. The aim of this paper is to survey the state of the art in motion planning and to assess selected planners, examine implementation details and above all shed a light on the current challenges in motion planning and the promising approaches that will potentially overcome those problems.

Sampling-Based Robot Motion Planning: A Review

Currently autonomous or self-driving vehicles are at the heart of academia and industry research because of its multi-faceted advantages that includes improved safety, reduced congestion, lower emissions and greater mobility. Software is the key driving factor underpinning autonomy within which planning algorithms that are responsible for mission-critical decision making hold a significant position. While transporting passengers or goods from a given origin to a given destination, motion planning methods incorporate searching for a path to follow, avoiding obstacles and generating the best trajectory that ensures safety, comfort and efficiency. A range of different planning approaches have been proposed in the literature. The purpose of this paper is to review existing approaches and then compare and contrast different methods employed for the motion planning of autonomous on-road driving that consists of (1) finding a path, (2) searching for the safest manoeuvre and (3) determining the most feasible trajectory. Methods developed by researchers in each of these three levels exhibit varying levels of complexity and performance accuracy. This paper presents a critical evaluation of each of these methods, in terms of their advantages/disadvantages, inherent limitations, feasibility, optimality, handling of obstacles and testing operational environments. Based on a critical review of existing methods, research challenges to address current limitations are identified and future research directions are suggested so as to enhance the performance of planning algorithms at all three levels. Some promising areas of future focus have been identified as the use of vehicular communications (V2V and V2I) and the incorporation of transport engineering aspects in order to improve the look-ahead horizon of current sensing technologies that are essential for planning with the aim of reducing the total cost of driverless vehicles. This critical review on planning techniques presented in this paper, along with the associated discussions on their constraints and limitations, seek to assist researchers in accelerating development in the emerging field of autonomous vehicle research.

Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions

The exponential growth of the interest and investigations in UAVs is strongly pushing the emergence of autonomous MFRs. This article presented some developments in the ASL-MFR project. A new design methodology was introduced and applied to a quadrotor and a coaxial helicopter enhancing appreciably the robots characteristics by allowing 100% thrust margin and 30 min autonomy (respectively, 40% and 20 min for CoaX). An original concept of hybrid active and passive control is introduced for CoaX. A simulation software permitting rapid MFR reconfiguration and various testing conditions was shown. Finally, a simulation of an obstacle avoidance controller was presented. The numerous developments presented in this article reinforce our conviction in the emergence of autonomous MFRs.

Autonomous miniature flying robots: coming soon! - Research, Development, and Results

Under canopy light detection and ranging-based autonomous navigation

A fundamental problem in the management of an automated guided vehicle system (AGVS) is the determination of the load to be transported and the vehicle to transport it. The time for the loading and unloading of pallets must be specified as soon as possible. Typical objectives are minimization of travel times and costs by the reduction of the number of vehicles required to fulfill a given transportation order. This article presents a methodology for the estimation the minimum number of AGVs (considering all the available ones at the shop floor level) required to execute a given transportation order within a specific time-window. A comparison is made between the algorithms Shortest Job First and meta-heuristic Tabu Search (applied to an initial solution) for a task assignment. An enhanced Dijkstra algorithm is used for the conflict-free routing task. The number of vehicles is estimated so as to provide an efficient distribution of tasks and reduce the operational costs of the materials handling system. Simulation results of two typical industrial warehouse shop floor scenarios are provided. Although the study focuses on pre-planning of order fulfillment of materials handling, the proposed methodology can also be utilized as an important tool for investment analysis of the warehouse layout design and for estimating the ideal number of AGVs.

Integrated tasks assignment and routing for the estimation of the optimal number of AGVS

he evolution of autonomous miniature flying robots (MFRs) is considerably intensified thanks to the recent growth of military and civil interest in unmanned aerial robotics that are able to perform different tasks such as surveillance and rescue. This article presents some of the research undertaken for the Automous Systems Lab (ASL) MFR project. It introduces a new design methodology adapted to rotorcraft MFRs and presents two different application examples: a mini quadrotor named OS4 and a compact coaxial rotor helicopter called CoaX. In addition to this, an original concept of hybrid active and passive control for CoaX is addressed. Finally, a simulation tool based on MATLAB and Simulink is described. This tool

Autonomous Miniature Flying Robots: COMING SOON!

Today, robotic systems are bridging the gaps between global economy, social needs, and logistics focusing on sustainable development solutions. Everyday new robotic applications can be found in literature and media. Some of them are basically entertainment toys. Nevertheless, the great majority of them is used inside industries, performing several tasks (painting, welding, moving materials, etc.). In a scenario of global economy growth, any sustainable solution that can reduce the product final cost is welcome. This article presents researches on robotic forklifts for intelligent warehouses developed at the Mechatronics Lab at USP-EESC in Brazil. We show three keyroutines that determine the Automated Guided Vehicle (AGV) behavior: the routing algorithm (that computes the overall task execution time and the minimum global path of each AGV using a topological map of the warehouse), the local path planning algorithm (based on A∗ it searches for the local minimum path between two nodes of the warehouse topological map), and an auto-localization algorithm (that applies an Extended Kalman Filter — EKF — to estimate the AGVs actual positions). In order to validate the algorithms developed, several tests were carried out using the simulation software Player/Stage. The results obtained were encouraging and the router developed was able to solve traffic jams and collisions, before sending the final paths to the robots. In a near future all algorithms will be implemented using mini- robotic forklifts and a scaled environment built in our lab.

Marcelo Becker

Papers

Autonomous miniature flying robots: coming soon! - Research, Development, and Results

Under canopy light detection and ranging-based autonomous navigation

Integrated tasks assignment and routing for the estimation of the optimal number of AGVS

Autonomous Miniature Flying Robots: COMING SOON!

Robotic forklifts for intelligent warehouses: Routing, path planning, and auto-localization