No abstract

This paper presents a novel approach to infer navigational intent of the user of a walker, based on measuring forces and moments applied to the walker's handles. While there are many types of "intent" that could be inferred for a given user action, the experiments conducted here focused on the determining user's navigational intent, i.e. their desired heading. Our experiments used two 6-DOF force/ moment sensors on the walker's handles and a digital motion capture system to correlate applied force with actual motion. Preliminary results revealed that the intent to turn, represented by changes in the heading angle, highly correlates with the overall turning moment around the vertical axis as well as the side forces applied by the user. Other force/moment components reveal additional information, such as support needs. The inferred user intent will be incorporated into a passive shared steering control system for the walker.

The goal of this project is to develop a pedestrian mobility aid for the elderly. In order for this type of assistive technology to be useful and accepted by its intended user community, it must enhance the abilities of users, not replace them. This leads to an agent architecture in which the agent must operate without hindering the user's ability to take direct action when they choose. In other words, the agent cannot simply be a proxy for the user's actions. The agent must select its own goals based on observations of its user's actions. This is crucial not only because users may have diminished capacity to explain their actions to an agent, but because the ability of the agent to correctly interpret the user's goals is tied to its ability to act while still allowing the user to "feel in control". We present a mobility aid, i.e. a wheeled walker, which varies its goals and level of activity based on an estimation of its user's intentions. The assistive agent often takes no action, allowing the user to be fully in control. When the ease or safety of the user's travel is threatened, the agent attempts to influence the user's motion based on its belief in the user's goal. By varying the degree of autonomy, the walker can adjust to the user as their abilities change from day to day, or hour to hour. This prevents the walker from "trying to do too much", allowing the user to feel as if they are in control and not being "lead".

-This paper presents a characterization study of the HOKUYO PBS-03JN Infrared range-finder and compares it to the characterization of the SICK LMS-200 laser rangefinder for use in indoor 2-D mapping. Many parameters that could affect the performance of the sensor including warm-up time, divergence of the detection beam, usable detection range in the azimuth, target surface, color, and size properties, incidence angle at the target, and the mixed pixels problem have been studied. This characterization, quantification of errors, and 3-D confidence in the distance readings of the sensor is vital for practical applications. These characteristics are compared to the counterpart characteristics of the laser range-finder. The PBS-03JN is a cost effective alternative to laser range-finders in indoor environments. The sensor is attractive due to lower power consumption, and its lightweight.

No abstract