Glauco A. P. Caurin

Rehabilitation robotics and serious games: An initial architecture for simultaneous players

Traditional rehabilitation treatment includes repetitive and tedious exercises for the patient. The use of computer games can motivate and engage the patients attention, making the rehabilitation process more pleasant and attractive. In this context, this paper proposes an architecture that allows multiple users to take part simultaneously on a state of the art rehabilitation process using robots and computer games. The main components of this architecture are the impedance control system adopted by the therapy robots, the client-server communication structure (Telerehabilitation server) and the human machine interface based on a serious game. Preliminary experimental tests, involving a cooperative game with two users and individual robots, clearly demonstrate how the experience of the players may be influenced by impedance control.

Adaptive strategy for multi-user robotic rehabilitation games

In this paper, we discuss a strategy for the adaptation of the “difficulty level” in games intended to include motor planning during robotic rehabilitation. We consider concurrently the motivation of the user and his/her performance in a Pong game. User motivation is classified in three levels (not motivated, well motivated and overloaded). User performance is measured as a combination of knowledge of results-achieved goals and score points in the game — and knowledge of performance — joint displacement, speed, aiming, user work, etc. Initial results of a pilot test with unimpaired healthy young volunteers are also presented showing a tendency for individualization of the parameter values.

Increasing Students' Interest With Low-Cost CellBots

This paper introduces the use of a flexible and affordable educational robot specifically developed for the practical experimentation inherent to technological disciplines. The robot has been designed to be reconfigurable and extendible, serving as an experimental platform across several undergraduate courses. As most students have a mobile cell phone, this was used as the main control computer for the so-called CellBot, thus avoiding any need to deal with the details of microcontrollers or other embedded computing devices. Assessment results are also presented, based on a pre- and post-survey of student opinion administered to 204 science and engineering students from several universities. Among the conclusions are that 83% of the students prefer to use these low-cost robots as tools to improve their learning of the theory in several disciplines, and 71% of the students stated that they prefer to have their own robot to experiment with, instead of using a didactic kit loaned to them by the university.

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

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 key-routines 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.

Scara robot controller using real time linux

Real Time systems have several important characteristics and constraints that had always been related to enterprise-level solutions provided by well known software and hardware suppliers. Real Time Linux and Free Software are making success in this area through low cost and reliable solutions with high levels of flexibility. This paper explores Real Time Linux and other useful free open source tools for Real Time systems, applied to control an industrial SCARA Robot including a Web based Human Machine Interface that is also presented.

Robust control in 4×4 hybrid-converted touring vehicles during urban speed steering maneuvers

The present work is focused on the synthesis and the analysis of robust control techniques for rear electric traction control in 4×4 hybrid-converted CVs (Conventional Vehicles) at urban speed limits (lower than 60 Km/h). This set represents a practicable alternative for the automotive industry, improving vehicular performance and reducing considerably fossil fuel air pollution. Our goal is to design an electromechanical controlled system that can replace the conventional rear wheels in touring cars with a pair of electric wheels with a minimal level of adaptation, preserving the original combustion engine. We consider the synthesis of an H∞ robust controller and also the neurofuzzy approach. An optimized PID controller was also designed for the final analysis and evaluation. Based on Ackerman Geometry and the reading of the steering front angles, it was possible to estimate the maneuver radius from turning center. Thus, all three proposed control approaches must adjust the rear wheels individual angular speeds by means of the current control of the two electrical motors linked to them, so that the car presents an appropriate behavior during all possible maneuvers. Finally, computation models were run in order to compare the three controllers.

A Robotic System for Rehabilitation of Distal Radius Fracture Using Games

This work integrates robotics and electronic games with the objective of producing more motivating and attractive therapeutic activities in distal radius fracture rehabilitation (wrist region). The proposed robotic system allows the reliable measurement of all wrist angular motion amplitudes. To this end, a framework is proposed to allow the full integration of the designed game to the developed hardware. The framework stores data from the game and from the robot movements for further analysis. The prototype was tested in healthy subjects, and a questionnaire was used to produce qualitative impressions on the system.

A self-organizing state trajectory planner applied to an anthropomorphic robot hand

An incremental self-organizing map, called State Trajectory Generator (STRAGEN) is employed to plan state trajectories of a robot. STRAGEN can deal with different criteria to construct topological maps of the problem space, choosing neighbors that match these criteria and optimize different measures of the learned map. STRAGEN can also learn heterogeneous information, such as angles, torques and positions of a manipulator, preserving their characteristics. This algorithm was tested by generating trajectories for a robotic hand called Kanguera. Kanguera presents a new concept of anthropomorphic robot hand. The hand offers a suitable environment for experimental purposes due to its novel and more accurate transmission system. The implementation of adduction and abduction capacity for both the fingers and the thumb allows the execution of more complex movements. Simulations and experiments related to Kanguera hardware are also presented.

A comparison between flexible electrogoniometers, inclinometers and three-dimensional video analysis system for recording neck movement

This study compared neck range of movement recording using three different methods goniometers (EGM), inclinometers (INC) and a three-dimensional video analysis system (IMG) in simultaneous and synchronized data collection. Twelve females performed neck flexion-extension, lateral flexion, rotation and circumduction. The differences between EGM, INC, and IMG were calculated sample by sample. For flexion-extension movement, IMG underestimated the amplitude by 13%; moreover, EGM showed a crosstalk of about 20% for lateral flexion and rotation axes. In lateral flexion movement, all systems showed similar amplitude and the inter-system differences were moderate (4-7%). For rotation movement, EGM showed a high crosstalk (13%) for flexion-extension axis. During the circumduction movement, IMG underestimated the amplitude of flexion-extension movements by about 11%, and the inter-system differences were high (about 17%) except for INC-IMG regarding lateral flexion (7%) and EGM-INC regarding flexion-extension (10%). For application in workplace, INC presents good results compared to IMG and EGM though INC cannot record rotation. EGM should be improved in order to reduce its crosstalk errors and allow recording of the full neck range of movement. Due to non-optimal positioning of the cameras for recording flexion-extension, IMG underestimated the amplitude of these movements.

Learning how to grasp based on neural network retraining

Humans have an incredible capacity to manipulate objects using dextrous hands. A large number of studies indicate that robot learning by demonstration is a promising strategy to improve robotic manipulation and grasping performance. Concerning this subject we can ask: How does a robot learn how to grasp? This work presents a method that allows a robot to learn new grasps. The method is based on neural network retraining. With this approach we aim to enable a robot to learn new grasps through a supervisor. The proposed method can be applied for 2D and 3D cases. Extensive object databases were generated to evaluate the method performance in both 2D and 3D cases. A total of 8100 abstract shapes were generated for 2D cases and 11700 abstract shapes for 3D cases. Simulation results with a computational supervisor show that a robotic system can learn new grasps and improve its performance through the proposed HRH (Hopfield-RBF-Hopfield) grasp learning approach.