Case-based reasoning emulation of persons for wheelchair navigation

OBJECTIVE

Testing is a key stage in system development, particularly in systems such as a wheelchair, in which the final user is typically a disabled person. These systems have stringent safety requirements, requiring major testing with many different individuals. The best would be to have the wheelchair tested by many different end users, as each disability affects driving skills in a different way. Unfortunately, from a practical point of view it is difficult to engage end users as beta testers. Hence, testing often relies on simulations. Naturally, these simulations need to be as realistic as possible to make the system robust and safe before real tests can be accomplished. This work presents a tool to automatically test wheelchairs through realistic emulation of different wheelchair users.

METHODS AND MATERIALS

Our approach is based on extracting meaningful data from real users driving a power wheelchair autonomously. This data is then used to train a case-based reasoning (CBR) system that captures the specifics of the driver via learning. The resulting case-base is then used to emulate the driving behavior of that specific person in more complex situations or when a new assistive algorithm needs to be tested. CBR returns user's motion commands appropriate for each specific situation to add the human component to shared control systems.

RESULTS

The proposed system has been used to emulate several power wheelchair users presenting different disabilities. Data to create this emulation was obtained from previous wheelchair navigation experiments with 35 volunteer in-patients presenting different degrees of disability. CBR was trained with a limited number of scenarios for each volunteer. Results proved that: (i) emulated and real users returned similar paths in the same scenario (maximum and mean path deviations are equal to 23 and 10cm, respectively) and similar efficiency; (ii) we established the generality of our approach taking a new path not present in the training traces; (iii) the emulated user is more realistic - path and efficiency are less homogeneous and smooth - than potential field approaches; and (iv) the system adequately emulates in-patients - maximum and mean path deviations are equal to 19 and 8.3cm approximately and efficiencies are similar - with specific disabilities (apraxia and dementia) obtaining different behaviors during emulation for each of the in-patients, as expected.

CONCLUSIONS

The proposed system adequately emulates the driving behavior of people with different disabilities in indoor scenarios. This approach is suitable to emulate real users' driving behaviors for early testing stages of assistive navigation systems.

A comparative study of optical techniques applied to particle-enhanced assays of C-reactive protein

This work is based on the well-established immunoassay principle of agglutination of latex particles covered by immunoproteins. In our experiments, positively charged particles act as carriers for the F(ab')2 fragment, obtained from rabbit polyclonal IgG, active against C-reactive protein (CRP). The presence of the antigen CRP in the immunolatex system causes agglutination and the aim of the present study was to compare different optical techniques (turbidimetry, nephelometry, angular anisotropy and photon correlation spectroscopy) capable of detecting the agglutination. The sensitivity and detection limit largely depend on the optical method. We have analyzed for each optical technique the following aspects: sensitivity, reproducibility, detection limit, reaction time, amount of sample wasted and availability of the required detection device. The results presented in this paper show that both angular anisotropy and photon correlation spectroscopy offer lower detection limits, and use little reagent, but have longer assay times than the classical optical techniques of turbidimetry and nephelometry.

Coadsorption of IgG and BSA onto sulfonated polystyrene latex: I. Sequential and competitive coadsorption isotherms

In this work the sequential and competitive coadsorption of IgG and BSA proteins on a sulfonate polystyrene latex with high surface charge density have been studied. For sequential coadsorption the IgG/a-CRP was first adsorbed and then the free surface of the particle was saturated by redispersion of the pellet in a solution with a high concentration of monomeric BSA (m-BSA). The competitive coadsorption experiments were carried out in two separate experiments by changing the initial concentration of one protein when the concentration of other protein was high and constant. During the incubation the pH was 5 or 6, and the ionic strength 2 mM, as in previous studies the adsorption of BSA was very low at neutral or basic pH regardless of the amount of adsorbed IgG. From these coadsorption experiments it was possible to obtain latex-protein complexes with a similar degree of coverage by each protein, high adsorption of IgG and different amounts of BSA, or high adsorption of BSA and a low, but significant, amount of IgG. The latex-protein complexes were electrokinetically characterized by measuring the electrophoretic mobility of each complex vs the pH of redispersion. In that way we can detect the i.e.p. of the complexes and the pH range in which the electrostatic repulsion can make them colloidally stable.

Coadsorption of IgG and BSA onto sulfonated polystyrene latex: II. Colloidal stability and immunoreactivity

The present work deals with the study of the colloidal stability and immunoreactivity of sulfonated polystyrene latex particles covered by different amounts of m-BSA and IgG/a-CRP. These proteins have been previously adsorbed onto a sulfonated latex by sequential and competitive coadsorption experiments and it was possible to obtain latex-protein particles with different degrees of coverage by each protein. The latex particles, fully or partially covered by each protein (termed latex-protein complexes), were resuspended under several conditions (different pH and ionic strength values) and their colloidal stability, vs the addition of the electrolyte was studied using turbidity measurements. This stability appeared at a high degree of coverage by BSA and at a pH in which the BSA was negatively charged. At a high degree of coverage by IgG, the latex particles were unstable at all pHs. As a final part of this work, the immunoreactivity of several complexes was studied following the changes in the turbidity after the addition of CRP antigen. Only the complexes which were colloidally stable gave detectable reactivity. However, the complexes with a relatively low degree of coverage by IgG/a-CRP gave good immunoreactivity. Therefore, the latex-protein complex properties depended on the percentage of BSA or IgG adsorbed and on the electric state of the proteins at the redispersion pH. Under specific incubation conditions, sulfonated latex covered by significant IgG/BSA percentages was obtained, which showed a high colloidal stability and good immunoreactivity.