Browsing by Author "Valencia, David"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Absolute position calculation for a desktop mobile rehabilitation robot based on three optical mouse sensors(2011) Zabaleta, Haritz; Valencia, David; Perry, Joel; Veneman, Jan; Keller, Thierry; Tecnalia Research & InnovationArmAssist is a wireless robot for after stroke upper limb rehabilitation. In this paper, we describe a method based on artificial landmark navigation system. The navigation system is only based in three optical mouse sensors. This enables to build a cheap but reliable position sensor. Two of the sensors are the data source for odometry calculations, and the third optical mouse sensor takes very low resolution pictures of a custom designed mat. These pictures are processed by an optical symbol recognition algorithm which will estimate the orientation of the robot and recognize the landmarks placed on the mat. The data fusion strategy is described to detect the misclassifications of the landmarks in order to fuse only the reliable information. The orientation given by the OSR algorithm is used to improve significantly the odometry and the recognition of the landmarks is used to reference the odometry to a absolute coordinate systemItem Feasibility of Using Neuro-Fuzzy Subject-Specific Models for Functional Electrical Stimulation Induced Hand Movements(2015-09-01) Imatz-Ojanguren, Eukene; Irigoyen, Eloy; Valencia, David; Keller, Thierry; Tecnalia Research & Innovation; Medical TechnologiesFunctional Electrical Stimulation (FES) is a technique that artificially elicits muscle contractions and it is used to restore motor/sensory functions in both assistive and therapeutic applications. The use of multi-field surface electrodes is a novel popular approach in transcutaneous FES applications. Lately, hybrid systems that combine artificial neural networks and fuzzy logic have also been proposed for many applications in different areas. This paper presents the possibility of combining both approaches for obtaining subject-specific models of FES induced hand movements for grasping applications. Data of the hand and finger motion from two subjects affected by acquired brain injury were used to train two different approaches: coactive neuro-fuzzy inference system and recurrent fuzzy neural network. Preliminary results show that these approaches can be considered in modelling applications for their ability to learn and predict main characteristics of the system, as well as providing useful information from the original system that could be interpreted as subject-specific knowledge.