Best Paper Awards
The conference will have the following awards, which will be announced and bestowed at the conference closing session.
- Student paper
Recipients of past RAAD Awards
RAAD 2022 Conference, Klagenfurt, Austria, June 8 – 10, 2022
Best Research Paper Award 2022:
Recipients: Tobias Marauli, Hubert Gattringer, Andreas Mueller, from Austria.
Paper Title: Singularity Robust Inverse Kinematics of Serial Manipulators by means of a Joint Arc Length Parameterization.
Abstract: The inverse kinematics problem is ill-posed near kinematic singularities leading to extremely large joint velocities. This classical problem is addressed from a different perspective; instead of prescribing the end-effector (EE) motion in terms of a path parameter, the motion is parameterized in terms of the arc length in joint space. This allows tackling the inverse kinematics problem when approaching kinematic sin- gularities. Thereupon a singularity consistent sampling scheme can easily be devised. A sampling of the arc length gives direct control over the joint motion for prescribed EE motion. The arc length parameterization can be used for solving the (time) optimal path following problem, avoiding the ill-conditioning upfront
Best Application Paper Award 2022:
Recipients: Ferdaws Ennaiem, Abdelbadia Chaker, Juan Sandoval, Sami Bennour, Abdelfattah Mlika, Lotfi Romdhane, Said Zeghloul, Med Amine Laribi, from France.
Paper Title: Cable-driven Parallel Robot Accuracy Improving Using Visual Servoing.
Abstract: A visual based control method based on coupling a camera with a cable-driven parallel robot (CDPR) is proposed in this paper. This work is motivated by the need of overcoming the robot uncertainties resulting from cable vibrations or inaccurate initial configurations. The poses taken by the end-effector are recorded in real time and used as feedback for the control loop to enhance the robot accuracy. Experimental tests were conducted on a planar CDPR dedicated to rehabilitation and allowing to assist the patient’s upper limb along a preselected path. The reference path of the prescribed exercise was recorded, for a healthy volunteer, using a motion capture system. The implementation results show a remarkable increase in the robot accuracy. In addition, thanks to the proposed correction, the initial pose of the end-effector has no longer an impact on the robot behavior. The prescribed task can be performed independently of the starting pose.
Best Student Paper Award 2022:
Recipients: Giovanni Colucci, Lorenzo Baglieri, Andrea Botta, Paride Cavallone, Giuseppe Quaglia, from Italy.
Paper Title: Optimal Positioning of Mobile Manipulators Using Closed Form Inverse Kinematics.
Abstract: Mobile manipulators have recently been subject to studies and researches thanks to their augmented mobility and interaction capability. In the precision agriculture field, the development and implementation of such systems can be advantageous in every aspect of the farm activities, e.g. harvesting, pruning, or trimming. This paper presents the implementation of a 7 degree of freedom manipulator upon a mobile rover prototype, designed for precision agriculture, in order to perform grape sampling tasks. While the redundancy of the arm is used to perform offline collision avoidance with the environment and the mobile base itself, thanks to sampling based path planning methods, a closed form inverse kinematics solution allows to select the posture which maximizes the manipulability index of the manipulator. To do so, base mobility is used to reach the target and properly position the arm. The overall architecture was implemented on the real system and successfully validated through experimental tests.
RAAD 2021 Conference, Poitiers, France, June 21-23, 2021
Best Research Paper Award 2021:
Recipients: Tilen Brecelj and Tadej Petric, from Slovenia.
Paper Title: Angular Dependency of the Zero Moment Point.
Abstract: In this paper, the standard definition of the zero moment point as a location on the ground is extended to its angular definition around the center of mass of a humanoid robot. This new definition provides a more general way of expressing this stability parameter and enables its wider use, as this way it can be located anywhere on a specific line passing through the system’s center of mass. The angular expression of the zero moment point is examined and compared with the zero moment point of the linear inverted pendulum model, which can be obtained with some simplifica- tions of its angular definition. For a better understanding of the angular dependence of the zero moment point with respect to the accelerations of the humanoid’s center of mass in the horizontal and vertical directions, some computer simulations are presented. Finally, a real scenario of human- oid postural stability is presented and discussed, in which the advantages of the angular definition of the zero moment point can be seen.
Best Application Paper Award 2021:
Recipients: Alessandro Denarda, Andrea Manuello Bertetto, Doina Pisla and Giuseppe Carbone,
from Italy and Romania.
Paper Title: Design and Preliminary Testing of a Novel Semi-Automatic Saffron Harvesting Device.
Abstract: This paper addresses the procedure for designing a novel mechatronic device for a semi-automatic saffron harvesting. The design process includes the kinematic analysis and synthesis of the proposed mechanism to fulfill a grasping and harvesting of saffron flower with a specific two- finger gripper design. Then, a cam mechanism and elastic spring elements are designed to provide a shaking movement that achieves the splitting of the flower from its steam and a consequent flower harvesting. This is followed by a suction system for collecting and storing the harvested flowers. A 3D printed prototype is reported and preliminarily tested for validating the engineering feasibility and effectiveness of the proposed design solution.
Best Student Paper Award 2021:
Recipients: Stefania Magnetti Gisolo, Giovanni Gerardo Muscolo, Maria Paterna, Carlo De Benedictis and Carlo Ferraresi, from Italy.
Paper Title: Feasibility study of a passive pneumatic exoskeleton for upper limbs based on a McKibben artificial muscle.
Abstract: Exoskeletons are wearable structures or systems designed to enhance human movement and to improve the wearer’s strength or agility, providing auxiliary support aimed at reducing efforts on muscles and joints of the human body. The aim of this work is to discuss on the feasibility of a new passive upper limb exoskeleton, based on the use of pneumatic artificial muscles, and characterized by extreme lightness, cheapness, and ease of use. A broad overview of the state of the art on current exoskeletons is introduced. Then the concept of the new device is presented, and different transmission architectures between pneumatic muscle and limb are discussed. The study demonstrates the potential effectiveness of such a device for supporting an operator in heavy work condition.
RAAD 2019 Conference, Kaiserslautern, Germany, June 19–21, 2019
Best Research Paper Award 2019:
Recipients:Ioannis H. Misios, Panagiotis N. Koustoumpardis and Nikos A. Aspragathos, from Greece.
Paper Title: Gain Scheduled PID Force Control of a Robotic Arm for Sewing Fabrics.
Abstract: In this paper, a manipulator’s gain scheduled PID force feedback controller is designed and implemented for the robotized sewing of fabrics, using a commercial sewing machine. The proposed manipulator controller should keep a constant tension of the fabric, to achieve high quality of cloth’s seams, as the length of the fabric is shortened along the sewing process. For the controller design, a nonlinear model of the fabric is considered, varying with the actual length between the grasping and sewing points. The model is based on a simplified Kelvin-Voigt model with non-linear spring and damper coefficients, which also depend on the type and the length of the fabric and are estimated experimentally. The Model-based PID tuning process from Simulink is used, for tuning and scheduling the gains of the PID controller corresponding to fabric’s different actual lengths. The determined sets of gains are used for controlling on-line an Adept Cobra s800 robot to manipulate a woven piece of fabric during the sewing process, where the proposed approach is tested. The proposed manipulator’s force control approach maintains a stable tensional force on the fabric and therefore the quality of the seam and hence of the cloth could be enhanced. Finally, it is compared with a PID controller with constant gains.
Best Application Paper Award 2019:
Recipients:, Marko Jovanović, Marko Vučić, Bojan Tepavčević, Mirko Raković and Jovica Tasevski, from Serbia.
Paper Title: Robotic Knitting in String Art as a Tool for Creative Design Processes.
Abstract: The application of industrial robots in creative industries has shown great potential in the last decade. The interpretation of images as tangible and artistic works of art is depicted with various elements and techniques. The usage of a continuous piece of string allows for the design process to explore dierent methods of achieving comprehensible images in the form of string art. With dierent computational tools and design techniques it becomes possible to explore design thinking coupled with automated fabrication. In this paper, the emphasis is placed on generating a large scale string art pieces out of smaller tiles, that can be used as wall art. By using an integrated work ow it is possible to generate the program for robotic knitting of the string art piece, by adjusting the parameters that govern the entire process.
Best Student Paper Award 2019:
Recipients: Branko Lukić, Tadej Petrič, Leon Žlajpah, and Kosta Jovanović, from Serbia and Slovenia.
Paper Title: KUKA LWR Robot Cartesian Stiffness Control Based on Kinematic Redundancy.
Abstract: This paper is dealing with one important topic for physical human-robot interaction, and that is achieving and/or optimizing of an arbitrary Cartesian stiffness of robot’s end-effector (EE). The focus is given on redundant compliant robots with serial elastic actuators with fixed joint stiffness, but can reconfigure without changing the EE position. The work presented in this paper is an approach where the robot redundancy is exploited to achieve the desired or at least some optimal Cartesian stiffness of robots EE. Robot tasks can be divided into primary and secondary tasks. In our case, the primary task is to track the Cartesian position reference and the secondary task is to optimize EE Cartesian stiffness behavior while keeping the desired EE position. This means that the EE position is a constraint in the robot Cartesian stiffness optimization. The algorithm for the Cartesian stiffness optimization has been initially tested using the simulation, and then evaluated on the 7-DOFs KUKA light weight robot.
RAAD 2018 Conference, Patras, Greece, June 6–8, 2018
Best Research Paper Award 2018:
Recipients: Leon Žlajpah, Tadej Petrič from Slovenia.
Paper Title: Virtual Guides for Redundant Robots Using Admittance Control for Path Tracking Tasks.
Abstract: Virtual guides are used in human-robot cooperation to support a human performing manipulation tasks. They can act as guidance constrains to assist the user to move in the preferred direction or along desired path, or as forbidden-region constraint which prevent him to move into restricted region of the robot workspace. In this paper we proposed a novel framework that unifies virtual guides using virtual robot approach, which is represented with the admittance control, where a broad class of virtual guides and constraints can be implemented. The dynamic properties and the constraints of the virtual robot can be defined using three sets of parameters and variables: desired motion variables, dynamic parameters (stiffness, damping and inertia) and dead-zones. To validate the approach, we implemented it on a KUKA LWR robot for the Buzz-Wire tasks, where the goal is to move a ring along a curved wire.
Best Application Paper Award 2018:
Recipients: Giuseppe Quaglia, Walter Franco, and Matteo Nisi, from Italy.
Paper Title: Stair-Climbing Wheelchair.q05: from the concept to the prototype.
Abstract: In this paper, an electric stair-climbing wheelchair, named wheelchair.q05, able to move on flat ground and to climb stairs, is presented. The proposed solution has been developed through a series of studies and designs, all based on a smart hybrid triple leg-wheel locomotion unit. The stability of the device is guaranteed by a rear support of a pair of pivoting wheels during motion on flat ground, and by the support of an idle track, when climbing on or going down stairs. By means of mechanisms and actuators, it is possible to change the configuration of the wheelchair, from the flat ground motion to the stair climbing configuration.
Best Student Paper Award 2018:
Recipients: Florian Pucher, Hubert Gattringer, Christoph Stöger, Andreas Mueller, and Ulrich Single, from Austria and Germany.
Paper Title: Modeling and Analysis of a Novel Passively Steered 4WD Mobile Platform Concept.
Abstract: Applications in the field of mobile robotics have high demands on flexibility and maneuverability of mobile platform s. Especially in logistics, vehicles have limited space for the movement. This paper presents the analysis and control of a mobile platform which uses a novel steering principle. The considered vehicle is able to perform a steered forward movement, lateral motion or pure rotation without t he need of steering motors. The kinematics is analyzed and a kinematic model is derived. For simulation a dynamic model formulated in terms of redundant coordinates is used. A control scenario where reference values are commanded by a joystick is presented. For feedforward control design, a reduced dynamic model based on minimal velocities and the kinematic model are used. For feedback control, a cascaded structure with an in-ner velocity loop for the wheels and a superimposed steering control is used. The efficiency of the presented control approach is demonstrated by simulation results.
RAAD 2017 Conference, Turin, Italy, June 21–23, 2017
Best Research Paper Award 2017:
Recipients: Carbone Giuseppe, Bogdan Gherman, Ionut Ulinici, Calin Vaida, and Doina Pisla, from Italy and Romania.
Paper Title: Design Issues for an Inherently Safe Robotic Rehabilitation Device.
Abstract: This paper outlines the main design issues for an upper limb rehabilitation device. In particular, human motions have been measured and analysed in order to identify a safe workspace required for a rehabilitation device. A preliminary design solution is proposed based on a cable-driven parallel architecture, which can provide the required operation workspace and significantly improve the safety of the rehabilitation procedure as compared with exoskeletons or traditional robotic devices.
Best Application Paper Award 2017:
Recipients: Katiuscia Sacco, Guido Belforte, Gabriella Eula, Terenziano Raparelli, Silvia Sirolli, Elisabetta Geda, Giuliano Carlo Geminiani, Roberta Virgilio, and Marina Zettin, from Italy.
Paper Title: P.I.G.R.O.: An Active Exoskeleton for Robotic Neurorehabilitation Training Driven by an Electro-Pneumatic Control.
Abstract: This paper presents the structure and the main innovations of P.I.G.R.O. (Pneumatic Interactive Gait Rehabilitation Orthosis). It is an active exoskeleton electro-pneumatically controlled with 6 DoF (Degree of Freedom) in the sagittal plane. Robotic neurorehabilitation trainings are its main field of application. Some preliminary tests are carrying on with brain stroke and ictus patients.
Best Student Paper Award 2017:
Recipients: Yu-Hsun Chen, Marco Ceccarelli, and Hong-Sen Yan, from Taiwan and Italy.
Paper Title: Performance Analysis of the Automata in a Blossoming Flower Clock in the 18th Century.
Abstract: This paper presents a performance evaluation of an automaton mechanism in a Blossoming Flower Clock that is preserved in Beijing palace museum. Even though the mechanical structure inside this clock is uncertain, the feasible mechanisms for these automata are synthesized through a systematically design procedure in a previous study. In this paper, the historical background of this clock is introduced first, and then the dimension design, kinematic and dynamic analysis are proposed to provide the numeral results for a performance characterisation. The proposed procedure can also be applied to other automata for reconstructing and analysing the mechanical performance.
RAAD 2016 Conference, Belgrade, Serbia, June 30 – July 2, 2016
Best Research Paper Award 2016:
Recipients: Leon Žlajpah, from Slovenia.
Paper Title: Kinematic Control of Redundant Robots in Changing Task Space.
Abstract: In the paper we propose a task-space kinematic velocity controller for tasks where the task does not require motion in all spatial directions and these directions also change over time. For that, the controller is mapped from the world space to the task space which may change during the task execution. To simplify the mapping we propose that the desired task location is the origin of the task frame. Effectiveness of the proposed control approach is illustrated by an experiment on a dual arm robot system performing a ring task.
Best Application Paper Award 2016:
Recipients: Mohammad M. Aref, Reza Ghabcheloo, Antii Kolu and Jouni Mattila, from Finland.
Paper Title: Vision-Guided Autonomous Forklift.
Abstract: This paper tackles the problem of integrating Visual Servoing Control (VSC) into the functionalities of an Articulated-Frame-Steering (AFS) hydraulic forklift. The controller is capable of breaking down high-level messages into piecewise commands for the different software modules of the vehicle. It also preserves seamless cooperation of the modules for a successful pallet-picking mission. The proposed architecture has been verified on a real machine. Videos of the test runs are available on YouTube.
Best Student Paper Award 2016:
Recipients: M. Jovanović, J. Tasevski, B. Tepavčević, M. Raković, D. Mitov, B. Borovac, from Serbia.
Paper Title: Fabrication of Digital Anamorphic Sculptures with Industrial Robot.
Abstract: The fabrication process of complex architectural designs in the real world requires precise and complex movements in the workspace. The robotic arms can fulfil this requirement, which makes them an excellent choice for a set of digital fabrication tasks. This paper presents a design methodology for the generation of anamorphic sculptures based on input gray scale image. To represent pixels in real world, wooden sticks are used. The colour of a gray scale image is represented by setting the appropriate orientation of the wooden sticks with respect to the initial vertical position. To achieve good results a large number of sticks is required to be placed and oriented precisely. In order to do this, the holes are drilled at a specified angle in a wooden base. Drilling is carried out with a driller mounted on ABB IRB140 robot arm. After the drilling is finished, wooden sticks are manually placed in each hole.
RAAD 2015 Conference, Bucharest, Romania, May 25-27, 2015
Best Research Paper Award 2015:
Recipients: Viorel Stoian, Ionel Cristian Vladu and Ileana Vladu, from Romania.
Paper Title: A New Hyper-Redundant Arm and its Control System.
Abstract: This paper presents a new hyper-redundant robotic arm structure and its sensorial, driving and control systems. A system of cables actuated by DC motors is used for bending. The position of the robot can be obtained by bending it with the cables and by blocking the position of the needed elements using an electro pneumatic system. The major advantage of this type of actuator consists in the fact that the robot can be moved using a boundary control by cables with a single actuating unit, the position blocking system for any element being relatively simple. The main features and advantages of the sensorial system and global robot system are presented. The dynamic model of the arm is developed using Lagrange’s formalism; the motion control system is based on the adaptive computed-torque method. Finally, experimental results are described.
Best Application Paper Award 2015:
Recipients: Aleksandar Rodić, Ilija Stevanović, Miloš D. Jovanović and Đorđe Urukalo, from Serbia.
Paper Title: On building remotely operated underwater robot-explorer with bi-manual poly-articular system.
Abstract: The paper addresses the mechanical design of a river underwater robot (remotely operated vehicle – ROV) suitable for implementation in delicate and risky underwater tasks. The main factors that determine the mechanical design of the robot are hydrodynamic drags and low underwater visibility. The robot body is inspired by biological models of fishes as well as by the “golden ratio” a natural geometry proportion that commonly appears in nature. The underwater ROV presented in the paper has two redundant, poly-articular, tendon-driven robot arms, suitable for use in submarine tasks due to their flexibility and light mechanical structure. The paper explains how robot propulsion is determined and which kind of thruster motors are chosen for this purpose. The designed mechanical structure is evaluated by corresponding simulation tests and the results of which are analysed. The paper finally presents concluding remarks and objectives of future work.
Best Student Paper Award 2015:
Recipients: Pauline Chevalier, Brice Isableu, Jean-Claude Martin and Adriana Tapus, from France.
Paper Title: Individuals with Autism: Analysis of the First Interaction with Nao Robot based on their Proprioceptive and Kinematic Profiles.
Abstract: The research aims to develop a new personalized social interaction model between a humanoid robot and an individual suffering of Autistic Spectrum Disorder (ASD), so as to enhance his/her social and communication skills. In order to define individual’s profile, we posit that the individual’s reliance to proprioceptive and kinematic visual cues will affect the way an individual suffering of ASD interacts with a social agent. We describe a first experiment that defines each participant’s perceptive-cognitive and sensorimotor profile with respect to the integration of visual inputs, thanks to the Sensory Profile questionnaire and an experimental set-up. We succeeded to form 3 groups with significant different behavioural responses inside our subject pool formed by 7 adults and 6 children with ASD. In a second experiment, we presented the Nao robot to all of our participants. We video-analysed their behaviours and compared them to the profiles we defined. In view of our results, this first interaction confirmed our hypothesis: participants with a weak proprioceptive integration and strong visual dependency had more successful interaction than participants with an overreliance on proprioceptive input and hypo-reactivity to visual cues.
RAAD 2014 Conference, Smolenice, Slovakia, September 3–5, 2014
Best Research Paper Award 2014:
Recipients: Andrej Gams and Tadej Petrič, from Slovenia.
Paper Title: Adapting periodic motion primitives to external feedback: modulating and changing the motion.
Abstract: This paper evaluates the means of adapting periodic motions using either force or position feedback in order to permanently modify the motion, i.e. learn a new trajectory in order to comply with the conditions of the external environment. We evaluate three different approaches: a modulation approach using repetitive control, and two learning approaches of changing the motion. Simulation results have shown that all three approaches can be used with minor differences amongst them. Tests on a 7 degree-of-freedom Kuka LWR robot have shown that the approaches can be used in the real-world.
Best Application Paper Award 2014:
Recipients: Mirko Rakovic, Marko Jovanovic, Branislav Borovac, Bojan Tepavlevic, Milutin Nikolic and Mladen Papovic, from Serbia.
Paper Title: Design and Fabrication with Industrial Robot as Brick-laying tool and with Custom Script Utilisation.
Abstract: The paper presents methodology and implementation of parametric architectural design of brick-laying walls fabricated by industrial robotic arm. As a design tool Grasshopper is used, a visual programming editor that runs within the Rhinoceros 3D CAD application. Grasshopper offers a range of objects for creating parametric models including brick-laying walls. However it lacks the ability of integration with fabrication tools. To overcome this problem, a custom C# script has been developed. As the fabrication tool, the ABB-IRB 140 robotic arm is used. Thus the C# script is written in such a way to obtain the RAPID code for controlling ABB industrial robots. The C# script enabled automated generation of RAPID code in accordance to the Grasshopper generated geometries of walls.
Best Student Paper Award 2014:
Recipients: Sromona Chatterjee, Timo Nachstedt, Florentin Wlirgotter, Minija Tamosiunaite, Poramate Manoonpong, Yoshihide Enomoto, Ryo Ariizumi and Fumitoshi Matsuno, from Germany, Denmark and Japan.
Paper Title: Reinforcement Learning Approach to Generate Goal-directed Locomotion of a Snake-Like Robot with Screw-Drive Units.
Abstract: In this paper the authors apply a policy improvement algorithm called Policy Improvement with Path Integrals (PI) to generate goal-directed locomotion of a complex snake-like robot with screw-drive units. PI is numerically simple and has an ability to deal with high dimensional systems. Here, this approach is used as a model-free learning mechanism to find proper locomotion control parameters, like joint angles and screw drive velocities, of the robot for moving toward a given goal in a given time. Proper control parameters were also found when the robot was configured with different shapes and for different starting positions of the robot. The learning process was achieved using a simulated robot and the learned parameters were successfully transferred to the real one.
RAAD 2013 Workshop, Portorož, Slovenia, September 11–13, 2013
Best Research Paper Award 2013:
Recipients: Emre Ugur, Yukie Nagai and Erhan Oztop, from Austria, Japan and Turkey.
Paper Title: Parental scaffolding as a bootstrapping mechanism for learning grasp affordances and imitation skills.
Abstract: Parental scaffolding is an important mechanism utilized by infants during their development. Infants, for example, pay stronger attention to the features of objects highlighted by parents and learn the way of manipulating an object while being supported by parents. Parents are known to make modifications in infant-directed actions, i.e. use “motionese”. Motionese is characterized by higher range and simplicity of motion, more pauses between motion segments, higher repetitiveness of demonstration, and more frequent social signals to an infant. In this paper, we extend our previously developed affordances framework to enable the robot to benefit from parental scaffolding and motionese. First, we present our results on how parental scaffolding can be used to guide the robot and modify robot’s crude action execution to speed up learning of complex actions such as grasping. For this purpose, we realize the interactive nature of a human caregiver-infant skill transfer scenario on the robot. During reach and grasp attempts the movement of the robot hand is modified by the human caregiver’s physical interaction to enable successful grasping. Next, we discuss how parental scaffolding can be used in speeding up imitation learning. The system describes how our robot, by using previously learned affordance prediction mechanisms, can go beyond simple goal-level imitation and become a better imitator using infant-directed modifications of parents.
Best Application Paper Award 2013:
Recipients: Michael Sfakiotakis, Manolis Arapis, Nektarios Spyridakis and John Fasoulas, from Greece.
Paper Title: Development and Experimental Evaluation of an Undulatory Fin Prototype.
Abstract: Bio-inspired thruster designs encompass significant potential for developing a new generation of underwater vehicles with enhanced propulsion and manoeuvring abilities, to address the needs of a growing number of underwater applications. Undulatory fin propulsion, inspired by the locomotion of cuttlefish and of certain electric eel species, is one such approach currently under investigation. Within this framework, we present the design and experimental evaluation of an undulatory fin prototype, comprised of eight actively-controlled fin rays, which are interconnected by a flexible membrane. A control architecture, based on an artificial Central Pattern Generator (CPG), is used to produce the rays’ motion pattern associated with the undulatory movement of the fin. Experimental results from a parametric study indicate that the prototype can achieve speeds up to 1.45 fin lengths per second, and highlight the effect of the various kinematic parameters on the attained velocity and wave efficiency.
Best Student Paper Award 2013:
Recipients: Igor Cvišić and Ivan Petrović, from Croatia.
Paper Title: Inertial aided sensor platform stabilization on multirotor aerial vehicles.
Abstract: Multiple rotor Unmanned Aerial Vehicles (UAVs) are becoming ubiquitous because of their construction simplicity and ease of maintenance. Such UAVs are able to hover, take off and land vertically. In addition, it is straightforward to design an on-board attitude autopilot. In comparison with classical helicopters, multi-rotor aircrafts provide less dangerous testbed in urban and cluttered environments due to their small-size and light-weight blades. In this paper, we present our prototype of aerial vehicle with eight rotors, which carries a unique platform for exteroceptive sensors. We designed inertial aided stabilization of the movement of the platform, decoupling the motion of exteroceptive sensors from the vehicle motion. This directly contributes to improved position and attitude estimation in visual navigation and smoother perception of the environment, and indirectly to achievement of the vehicle autonomy in urban and cluttered environments. The functionalities of the prototype aerial vehicle and the stabilizing platform are tested in simulation and experimentally.
RAAD 2012 Workshop, Naples, Italy, September 10–13, 2012
Best Research Paper Award 2012:
Recipients: Silvia Anton, Irina Mocanu, Florin Anton, Theodor Borangiu and Marco Ceccarelli, from Romania and Italy.
Paper Title: Gesture Recognition for Robot Assistance in Ambient Assisted Living Environments.
Abstract: The paper presents a model for pattern discovery of human body posture and gesture interpretation. The model will be used in an ambient intelligent system, called AmIHomCare. The AmIHomCare system is an intelligent ambient system which performs home medical assistance of elderly or disabled people. One component of the AmIHomCare system performs daily activity recognition and monitoring. Each activity is viewed as a sequence of sub-activities. Each sub-activity is composed of a pair of person context (location in the room) and person body posture. The posture of the person is then considered as a full body gesture. The body gesture is detected by using a model for pattern discovering using decision trees. The proposed model allows the detection and interpretation of human static and dynamic gestures. Next, the human gestures will be associated with response actions executed by an assistant robot which will improve the quality of life of the assisted person.
Best Application Paper Award 2012:
Recipients: M. Donnici, G. Lupinacci, P. Nudo, M. Perreli, S. Meduri, B. Sinopoli, D. Pulice, C. Pace and G. Danieli, from Italy.
Paper Title: Using Navi-Robot in conjunction with a CAT equipment to guide precision biopsies.
Abstract: This paper presents the first in vitro use of Navi-Robot to guide precision biopsies, after identification of the region to be sampled from the analysis of CT scan data. Before introducing the patient into the CT ring, three small plastic disks of a determined thickness are secured horizontally with tape on the patient’s skin, two on the shoulders and one in correspondence to the iliac crest prominence, since these points have minimal if no motion during breathing. Then, while the doctor examines the result, a software of which a first edition has been already developed, locates automatically the position of the disk in the CT coordinates system, thus establishing the base for a common frame of reference. Once the doctor decides the region to be sampled, eventually fixing also the disks coordinates in the CT coordinate systems. At this point, with the patient still on the CT stretcher, and Navi-Robot in navigation mode, the tip of the end effector is brought into contract with the centre of the three disks, and the new position to be assumed by the end effector is computed. Finally, passing to robot mode, the requested position is assumed, while the depth of penetration is also supplied.
Best Student Paper Award 2012:
Recipients: Luka Peternel and Jan Babič, from Slovenia.
Paper Title: Using Human Sensorimotor Ability to Control Robot Stability: Construction and Evaluation of Human-Robot Interface.
Abstract: Abstract. Humanoid robotics has been a subject of many studies in the past years. The humanoid robots are to imitate the human body, characteristics and behaviour. Humans are extremely adaptable and are able to learn many things throughout their life. Our motivation is to exploit this ability to teach robots. If we want to teach a robot how to perform a certain task we need to adapt to the robot dynamics by controlling it with our own body. It is crucial that the robot remains stable at all times. Therefore the human needs to maintain its stability. Robot stability is related to its centre-of-mass (COM) position. In order for human to be able to keep the robot stable while performing and teaching it a certain task, he needs effective feedback information. We decided to use tactile, vestibular and proprioceptive feedback by exerting a force on a human operator at the point of his COM position. To achieve this, we developed a special haptic interface and tested if it is possible to effectively use it to maintain robot stability.
RAAD 2010 Workshop, Budapest, Hungary, June 23–25, 2010
Best Research Paper Award 2010:
Recipients: Andrej Gams, Tadej Petrič, Leon Žlajpah and Aleš Ude, from Slovenia.
Paper Title: Optimizing parameters of trajectory representation for movement generalization: robotic throwing.
Abstract: For effective use of learning by imitation with a robot, it is necessary that the robot can adapt to the current state of the external world. This paper describes an optimization approach that enables the generation of a new motion trajectory, which accomplishes the task in a given situation, based on a library of example movements. New movements are generated by applying statistical methods, where the current state of the world is utilized as query into the library. Dynamic movement primitives are employed as the underlying motor representation. The main contribution of this paper is the optimization of dynamic movement primitives with respect to the kernel function positions and over the entire set of demonstrated movements. We applied the algorithm to a robotic throwing task, where the location of the target is determined by a stereo vision system, which can detect infrared markers. The vision system uses two Nintendo WIIMOTEs for cameras.
Best Application Paper Award 2010:
Recipients:Andrea Manuello Bertetto, Costantino Falchi, Rinaldo Pinna and Roberto Ricciu, from Italy.
Paper Title: An Integrated Device for Saffron Flowers Detaching and Harvesting.
Abstract:This work is concerned with a mechanical system designed to harvest Crocus Sativus (saffron) flowers. The system is conceived as a shoulder portable device with two mainparts: the first one is specifically designed to detach the flower containing three stigmas, which are the costly final product; the second one is aimed to collect the detached flower through a vacuum collector. This paper describes the operating principle of the detaching and of the harvesting devices. The former device imitates one of the procedures followed by the pickers but with the peculiarity that allows harvesting the flower without separating it from its leaves, which is a significant advantage since it simplifies the mechanical detachment of the flower. The paper also deals with some experimental tests in the laboratory carried out in order to highlight the dynamic behaviour of the detaching and of the harvesting devices.
Best Student Paper Award 2010:
Recipients: Stanislav Sula, Giuseppe Carbone and Doina Pisla, from Romania and Italy.
Paper Title:An Experimental Evaluation of Earthquake Effects on Mechanism Operation.
Abstract:The results of successful experiments for investigating the earthquake effects on mechanism operation by using Cassino Parallel Manipulator (CaPaMan) as an earthquake simulator are presented. The experimental tests have been carried on by using a slider-crank and a four bar linkage as representing machine operations. The mechanism behavior has been experienced as strongly influenced when the mechanism motion has low speed as compared to earthquake disturbances. But even at high speed mechanisms are affected by the variable earthquake frequency.
RAAD 2009 Workshop, Brasov, Romania, May 25-27, 2009
Best Research Paper Award 2009:
Recipients: Nicola Pio Belfiore, Matteo Verotti, Luciano Consorti, from Italy.
Paper Title: Comparative Analysis of Isotropy Indices in RR and RRP Arms.
Paper Abstract. In this paper isotropy and manipulability in RR dyads and RRP arms are analyzed and the solutions are obtained in algebraic symbolic forms. Such analysis is performed by means of two different methods: the classical approach based on the condition number and the Lie product. Although both the methods are known since decades, an accurate comparison of the two approaches has never been presented in literature. In particular, the geometrical interpretation of the Lie Product allows appreciating some interesting differences between the two methods.
Best Application Paper Award 2009:
Recipients: Peter Cepon, Roman Kamnik, Jernej Kuzelicki, Tadej Bajd, Marko Munih, from Slovenia.
Paper Title: Experimental Mobile Robotic Platform.
Paper Abstract. The paper presents an experimental mobile robotic platform aimed at user friendly development of new mobile robotics applications. The development system incorporates the mobile platform construction, the drive unit with traction and steering wheel, main controller, the drive controller and the software development environment. The embedded controller running under xPC Target real time operating system is implemented in mobile platform. The controller controls drive units via CAN communication. The system enables software development and robot control on a remote host supervisory computer. The development system is based on Mathworks Matlab tools Simulink, Stateflow and xPC Target. This configuration allows the development of control algorithm in graphical mode by building and connecting functional blocks. In this way the development system is built providing user friendly graphical software development environment, optimal tuning of parameters, acquisition and logging of signals, and easy incorporation of new devices.
Best Student Paper Award 2009:
Recipients: Alexandru Dumitrache, from Romania.
Paper Title: Calibration of wrist-mounted profile laser scanning probe using a tool transformation approach.
Paper Abstract. This paper describes a method for calibrating a 3D laser scanning device mounted on the wrist of a 6-DOF robot arm, by computing a tool transformation for the laser sensor reference frame. The calibration procedure involves scanning a spherical object fixed in the robot workspace, and it makes possible aligning many individual scans taken from different orientations. Another advantage of this approach is that further applications are made possible, such as using the laser sensor for accurate robot guidance and alignment.