Dirk Vanhooydonck

Asynchronous non-invasive brain-actuated control of an intelligent wheelchair

In this paper we present further results of our asynchronous and non-invasive BMI for the continuous control of an intelligent wheelchair. Three subjects participated in two experiments where they steered the wheelchair spontaneously, without any external cue. To do so the users learn to voluntary modulate EEG oscillatory rhythms by executing three mental tasks (i.e., mental imagery) that are associated to different steering commands. Importantly, we implement shared control techniques between the BMI and the intelligent wheelchair to assist the subject in the driving task. The results show that the three subjects could achieve a significant level of mental control, even if far from optimal, to drive an intelligent wheelchair.

User-adapted plan recognition and user-adapted shared control: A Bayesian approach to semi-autonomous wheelchair driving

Abstract Many elderly and physically impaired people experience difficulties when maneuvering a powered wheelchair. In order to ease maneuvering, powered wheelchairs have been equipped with sensors, additional computing power and intelligence by various research groups. This paper presents a Bayesian approach to maneuvering assistance for wheelchair driving, which can be adapted to a specific user. The proposed framework is able to model and estimate even complex user intents, i.e. wheelchair maneuvers that the driver has in mind. Furthermore, it explicitly takes the uncertainty on the user’s intent into account. Besides during intent estimation, user-specific properties and uncertainty on the user’s intent are incorporated when taking assistive actions, such that assistance is tailored to the user’s driving skills. This decision making is modeled as a greedy Partially Observable Markov Decision Process (POMDP). Benefits of this approach are shown using experimental results in simulation and on our wheelchair platform Sharioto.

Bayesian Estimation of Wheelchair Driver Intents: Modeling Intents as Geometric Paths Tracked by the Driver

Many elderly and disabled people today experience difficulties when manoeuvring an electric wheelchair. In order to help these people, several robotic assistance platforms have been devised in the past. In most cases, these platforms consist of separate assistance modes, and heuristic rules are used to automatically decide which assistance mode should be selected in each time step. As these decision rules are often hard-coded and do not take uncertainty regarding the users intent into account, assistive actions may lead to confusion or even irritation if the users actual plans do not correspond to the assistive systems behavior. In contrast to previous approaches, this paper presents a more user-centered approach for recognizing the intent of wheelchair drivers, which explicitly estimates the uncertainty on the users intent. The paper shows the benefit of estimating this uncertainty using experimental results with our wheelchair platform Sharioto

Iso efficiency contour measurement results for variable speed drives

The efficiency of variable speed drives with induction motors and permanent magnet synchronous motors has received little attention so far in international standards. However the number of such applications is increasing rapidly and the potential energy savings are large. This paper is based on a measurement campaign of three collaborating research institutes and reports on the efficiency of motors up to 15 kW. The efficiency values are represented by means of iso efficiency contours. From these contours, the efficiency for IE1, IE2 and IE3 induction motors is compared with that of a permanent magnet machine for the entire torque - speed operation region. Also the impact of flux optimization with induction motors is analyzed. The required number of measurement points to construct accurate iso efficiency contours with minimum measurement effort is also discussed.

Iso efficiency contours as a concept to characterize variable speed drive efficiency

Despite recent revisions and harmonization efforts of international motor efficiency standards which has lead to the revised IEC Std 60034-2-1 and the efficiency classification of IEC Std 60034-30, there remains a lacuna in the context of motor systems efficiency. Although IEC is preparing a “Guide for the selection and application of energy-efficient motors including variable-speed applications” labeled IEC Std 60034-31, to date, there is no internationally accepted test protocol that allows the determination of drive system efficiency at different load points. As the first in a set of three by a joint research project of three research institutes, this paper introduces iso efficiency contours as a useful tool in this context. The concept of these contours as well as their mutual interaction with system specifications and losses are discussed. A first testing protocol for all types of motor drives is proposed. The concept is illustrated by first results of an extensive testing campaign.

Calculating energy consumption of motor systems with varying load using iso efficiency contours

Increasing awareness of ecological problems forces machine manufacturers to design greener machines. This implies amongst other things the selection of the most efficient electric motor system for their specific application. On the other hand, machine building applications evolve more and more from constant speed and load characteristics to varying speed and load applications. Therefore, the motor system that is used evolves more and more from direct online (DOL) to motors fed by a variable speed drive (VSD). However, current efficiency standardization focuses on DOL applications, and can by consequence not offer assistance to the machine builder to select the most efficient motor-VSD combination for his particular varying load application. The goal of this paper is to present a methodology that allows to predict the energy consumption for a specific motor-VSD combination and a specific varying speed-load application, using the fairly new concept of iso efficiency contours. By comparing the predicted energy consumption for a number of selected combinations, the most efficient one is revealed.

Bayesian plan recognition and shared control under uncertainty: assisting wheelchair drivers by tracking fine motion paths

The last years have witnessed a significant increase in the percentage of old and disabled people. Members of this population group very often require extensive help for performing daily tasks like moving around or grasping objects. Unfortunately, assistive technology is not always available to people needing it. For instance, steering a wheelchair can represent an extremely fatiguing or simply impossible task to many elderly or disabled users. Most of the existing assistance platforms try to help users without considering their specific needs. However, driving performance may vary considerably across users due to different pathologies or just due to temporary effects like fatigue. Therefore, we propose in this paper a user adapted shared control approach aimed at helping users in driving a power wheelchair. Adaption to the user is achieved by estimating the users true intent out of potentially noisy steering signals before assisting him/her. The users driving performance is explicitly modeled in order to recognize the users intention or plan together with the uncertainty on it. Safe navigation is achieved by merging the potentially noisy input of the user with fine motion trajectories computed online by a 3D planner. Encouraging results on assisting a user who cannot steer to the left are reported on K.U.Leuvens intelligent wheelchair Sharioto.

Selection of suitable human-robot interaction techniques for intelligent wheelchairs

There are many user interfaces already available to drive electric wheelchairs. These enable users to convey their intention explicitly to the wheelchair control system. However, we have observed users who find it nonetheless extremely difficult to do so. For some severely disabled users it is almost impossible to drive a conventional electric wheelchair in a safe way. This paper explores several ways of implicit communication to assist the user to perform daily manoeuvres. Some initial user trials have been performed at a hospital. The results are evaluated and conclusions are drawn on the selection of suitable human-robot interaction techniques.

Global dynamic window approach for holonomic and non-holonomic mobile robots with arbitrary cross-section

This paper presents an extension of current global dynamic window approaches to holonomic and nonholonomic mobile robots with an arbitrary cross-section. The algorithm proceeds in two stages. In order to account for an arbitrary robot footprint, the first stage takes the robots orientation explicitly into account by constructing a navigation function in the (x, y, /spl theta/) configuration space. In a second stage, an admissible velocity is chosen from a window around the robots current velocity, which contains all velocities that can be reached under the acceleration constraints. Fast computation over large areas is achieved by adopting multi-resolution (x, y) and (x, y, /spl theta/) planning. Several measures are taken to obtain safe and robust robot behaviour. Experimental results on our wheelchair test platform show the feasibility of the approach.

Shared Autonomy for Wheel Chair Control: Attempts to Assess the User's Autonomy

People who suffer from paresis, tremor, spasticity etc. may experience considerable difficulties when driving electric wheel chairs. A sensor-based wheel chair may assist these users in their daily driving manoeuvres. There are two extreme cases: on the one hand, the wheel chair can be fully in control and on the other, the user can be fully in control. It is however difficult to determine a suitable level of shared autonomy situated in between these two extreme cases. This paper presents a framework for shared autonomy and addresses the issue of assessing the user’s autonomy.