Khelifa Baizid | Brno University of Technology (original) (raw)

Papers by Khelifa Baizid

IFAC Proceedings Volumes, 2014

In this paper a Control software Architecture for Cooperative multiple unmanned aerial VehIcle-ma... more In this paper a Control software Architecture for Cooperative multiple unmanned aerial VehIcle-manipulator Systems (CAVIS) is presented. The core of the architecture is a set of software components, communicating each other through a set of defined messages. To handle multiple control objectives simultaneously, a library of elementary behaviors is defined; then, multiple elementary behaviors are combined, in a given priority order, into tasks (compound behaviors); to this aim the Null-Space-based Behavioral (NSB) approach has been adopted. An application example, involving a cooperative transportation of a bar by two aerial vehiclemanipulator systems, is developed to assess the performance of the proposed architecture.

The main goal of tele-operation is to allow human users to achieve safe and effective physical in... more The main goal of tele-operation is to allow human users to achieve safe and effective physical interactions within remote environments. Inherently, humans and robots must co-operate to reach the assigned objectives. By co-operation, one intends that the human must provide clear, feasible and quantitatively measurable controls to the robot(s) and the later, to execute as accurately as possible the received controls and to send back understandable information concerning its status. Unfortunately, this ideal scheme is not possible: human intentions are not quantifiable in the general case and the robot is not so perfect in executing commands nor in informing the human exactly about his status. The previous situation is even worst when considering to operate more than one robot. Indeed, on top of the individual difficulties (one-to-one tele-operation scheme), one adds the complexity of handling several robots and their coordination. This complexity increases when considering heterogeneo...

Stroke is a debilitating disease that has afflicted millions of people throughout the world. Assi... more Stroke is a debilitating disease that has afflicted millions of people throughout the world. Assisting physiotherapists in post-stroke activities to conduct rehabilitation therapies, scientific community has presented a new type of man-machine intelligent systems i.e. exoskeleton based exercisers. These devices help the patients having neurological disabilities to partially or fully regain their motor performance by applying forces to the affected finger phalanx and preventing unsuitable motion patterns. The exoskeletons because of their wide range of sensory capabilities have replaced traditional assessment of stroke patients. This article reviews developments in robotic prosthetics and exoskeletons. The primary design requirements of these devices are identified. Highlighting the authors' research achievements in this domain, a collection of exoskeleton-based hand rehabilitation devices has been then presented with a brief description about their mechanical designs. Finally, a...

This paper treats the safety issues in coordinated transportation of an object via multiple Unman... more This paper treats the safety issues in coordinated transportation of an object via multiple Unmanned Aerial Vehicles with Manipulator Systems (UAVMS); in particular, the case of obstacle avoidance is considered. The proposed paradigm is based on the so-called Null-Space-based Behavioral (NSB) control approach, that allows to achieve multiple tasks simultaneously. Two different scenarios of bar transportation using multi-UAVMSs have been developed, tested and compared in simulation: in the first scenario, the obstacle avoidance is achieved at the coordination level, where the controller allows the whole system (UAVMSs and bar) to circumnavigate the obstacle; while in the second scenario only the UAVMS closest to the obstacle modifies its trajectory to overcome the obstacle by keeping the desired trajectory of the bar unchanged.

2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2012

In this paper we present the architecture of ViRAT (Virtual Reality for Advanced Tele-operation),... more In this paper we present the architecture of ViRAT (Virtual Reality for Advanced Tele-operation), the hardwaresoftware platform we developed to support researches and studies dealing with multi-robotics. The achieved architecture is multi-purposes and as such, allows a wide spectrum of operation modes ranging from full tele-operated controls to full autonomous exploitation. From the hardware point of view, the platform offers the possibility to integrate heterogeneous robots having different mobility (wheeled, Humanoids, etc) as well as embedded sensing capabilities (video, laser-scanner, IMU, etc.). From the software side, the developed architecture is modular for more flexibility and adaptability: it includes human-robots interfaces (HRI) bricks, together with supervision and low/high level controls. After presenting the architecture of the ViRAT platform, we give some examples and some use cases to illustrate the performances of ViRAT and the easiness of developing around it.

In this paper we present novel methods and algorithms for augmenting a foot 3D model in real-time... more In this paper we present novel methods and algorithms for augmenting a foot 3D model in real-time. By overlaying reconstructed anatomical contents onto user's field of view via an augmented reality visualization platform, the virtual Biomedical Computer Aid Design (BioCAD) objects, appear geo-referenced to the real environment, help physicians and/or students to improve the overall image of the bone condition and anatomical structures of patients. Moreover, we explain the principle of marker and markerless Augmented Reality (AR) and interactive integration of virtual objects in the actual scene by development of a PC and mobile AR applications. In particular, this should be a powerful tool to understand the complex 3D nature and structure of 3D foot bones, joints and assemblies.

The need to validate and define the industrial tasks has lead to develop tools that help to provi... more The need to validate and define the industrial tasks has lead to develop tools that help to provide aid to the user, e.g. the optimum placement of the robot in its working site, the robot trajectory to accomplish a specific task, etc. Additionally, the placement of the robots in the robotized sites carries potential benefits in terms of task execution time as well as overall cost in industrial and automation industries. In this paper, we propose a general approach based on SolidWorks Application Programming Interface to provide a virtual simulated representation of the site allowing robot optimal placement of the performed task.

The implementation of robots in workshops has raised requirements related with the use and manage... more The implementation of robots in workshops has raised requirements related with the use and management of robotized sites. These requirements take place throughout the definition phases of the robotized site. The need to simulate and control the industrial tasks has lead to develop tools that aim to provide aid to the user, e.g. the optimum robot trajectory to accomplish a specific task, the placement of the robot in its working environment etc. Additionally, the simulation of robotized sites carries potential benefits in terms of cost as well as time management in industrial and automation projects. In this work, we propose a general approach based on SolidWorks Application Programming Interface (API) to simulate a serial robot’s task. The approach is mainly based on 3D models of the robotized site and time optimization ensuring accessibility and collision avoidance. To demonstrate the approach, a number of points representing a frequent and an important task (spot welding) by an industrial robot has been presented. The proposed simulation strategy gives collision free trajectory of robot motion which can be directly mapped to a real robot. Moreover, the approach provides the possibility to cope almost all problems related to the real implementation of serial robots.

Several requirements have been addressed in the robots working in workshops related to the use an... more Several requirements have been addressed in the
robots working in workshops related to the use and
management of robotized sites. These requirements take
place within the definition and design stages of the robotized
site. The need to validate and define the industrial tasks has
lead to develop tools that provide aid to the user, e.g. the
optimum placement (position and orientation) of the robot
in its working site, the robot trajectory to accomplish the
task etc. Additionally, the placement of the robot in the
robotized sites carries potential benefits in terms of task
accomplishment time as well as the overall cost in industries
and automation. In this paper, we propose a general
approach based on SolidWorks Application Programming
Interface (API) to provide a virtual representation of the
site allowing the determination of the robot placement and
orientation zone and the optimization of the task time based
on this zone. To validate the developed approach, an
important and frequent industrial robotics task (spotwelding)
is considered. The proposed modelling and
simulation strategy show the effectiveness of the method.
Namely, we show how the optimum robot placement and
orientation is achieved with consideration of minimum time
criterion. As well, we present how the designers deal with
the definition of the robotised tasks and their feasibility.
Moreover, our API-based scheme facilitates handling of
commonly encountered problems related to the real
implementation of serial robots.

In this paper we address the problem of coverage area with multi-robot system by giving an autono... more In this paper we address the problem of coverage area with multi-robot system by giving an autonomy level to single robot as well as the team. The coverage concept is based on Voronoi algorithm and it applied to extract the minimum number of views from the supervised environment. Human Robot Interface was developed to allow user to selects minimum points’ locations where robots have to achieve the supervision task. Moreover, user can access at any time through the interface watching video streams feedback coming from robots and semi-autonomous robots can locally correct their paths if probability collusion, with the environment, is predicted based on new adapted Active Counter Model. However, failed robots can easily request help from user, where, this last acts overcoming the robot from its unlikely situation. The coverage strategy that we proposed combines the real robot motion (by consideration motion error and process the correction method) and the human robot interaction as well as the supervision paradigms.

When exploring environments remotely, the knowledge of the tele-operated vehicle location is a ke... more When exploring environments remotely, the knowledge of the tele-operated vehicle location is a key element for operators’ situational awareness. Given visual information provided by the ROV, we aimed at finding the best combination between the maps used by operators, visual feedbacks provided by the ROV and the displays to show the previous information. In our system, tele-operators use 2D top-view or 3D immersive representation of the remote world as maps. From the remote site, they receive a live video stream provided by a remotely controlled pan-tilt camera. Maps and video streams are displayed on PC screens or HMD’s. We give and we discuss here, the results of the performed experiments. As expected, the 3D maps give more accurate estimation but are time consuming. On the other hand, we found that the use of simple PC-screens leads to better results than HMDs.

Effective control of autonomous robots evolving in dynamic and unpredictable environments is a ha... more Effective control of autonomous robots evolving in dynamic and unpredictable environments is a hard problem. The challenging issue is to achieve this control while the robot is performing a constrained and an interactive task. Namely, our aim is endow a mobile manipulator by controllers allowing safe and effective interactions with humans. This multi criteria optimization problem includes the coordination of two or more behaviors, in order to reach global goal. We propose in this paper a new concept to achieve multi-behaviors of catching objects and avoiding moving obstacles simultaneously for autonomous mobile robot arm. The mobile robot is equipped with an arm of 7 DOF. The robot's learns to avoid obstacles by moving (translation and rotation) its base while its arm tries to catch a given target.

Industrial implementation of robots is to perform the assigned tasks in the minimum possible time... more Industrial implementation of robots is to perform the assigned tasks in the minimum possible time in the cycle comes up to increase productivity and reduce the cost. The cycle time is strongly linked to the robot trajectory cycle to the task. However, the optimization of the robot trajectory cycle the robot visited a set of points which represent the robotics task. Similar to persons in traveling the robot execute the task into shorter time if has a shorter path. However the trajectory cycle of the robot is strongly related to the displacement in coordinate space rather than operational space. In fact, the shorter distance between two task points is the shorter distance between two configurations. Since robot has different configurations in each task point the minimum trajectory should be chosen between each successive configuration. However the order of visiting the task point also affects the trajectory distance. Moreover the relative robot position to the task also has a trivial effect on the task time. In this work we develop a method to optimize the order of visiting the task point taking into consideration the robot configuration and the placement of the robot in the robotized site. Mainly, this method is based on Genetic Algorithms and it takes into consideration the multiplicity solutions of the robot Inverse Kinematics Model (IKM), the task point visit order and the placement of robot at the same time.

Tele-operating robots’ team is a way to increase tasks type and complexity, the working space siz... more Tele-operating robots’ team is a way to increase tasks type and complexity, the working space size and to improve the remote interactions robustness. These interesting potentialities have a counterpart in terms of human robots interface. Indeed, we increase the complexity of the system and users must handle heterogeneous entities with different intrinsic mobility and sensing capabilities: tele-operators make integration and prediction efforts, firstly to built the remote world status and secondly to generate the right commands to be sent to the robots. In this paper, we present the platform we are developing to allow multi-robots tele-operation based tasks. The main aim of this platform is to support investigations about Human Multi-robots interfaces. Namely, to conduct studies concerning the integration of virtual and augmented reality technologies to reduce operators mental efforts. A description of this system is given. We present preliminary results in executing a simple scenario allowing to a single operator to supervise a given area.

IFAC Proceedings Volumes, 2014

2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2012