Probabilistic vs linear blending approaches to shared control for wheelchair driving

Abstract

Abstract-Some people with severe mobility impairments are unable to operate powered wheelchairs reliably and effectively, using commercially available interfaces. This has sparked a body of research into "smart wheelchairs", which assist users to drive safely and create opportunities for them to use alternative interfaces. Various "shared control" techniques have been proposed to provide an appropriate level of assistance that is satisfactory and acceptable to the user. Most shared control techniques employ a traditional strategy called linear blending (LB), where the user's commands and wheelchair's autonomous commands are combined in some proportion. In this paper, however, we implement a more generalised form of shared control called probabilistic shared control (PSC). This probabilistic formulation improves the accuracy of modelling the interaction between the user and the wheelchair by taking into account uncertainty in the interaction. In this paper, we demonstrate the practical success of PSC over LB in terms of safety, particularly for novice users.

Assisting power wheelchair driving on a sidewalk: A proof of concept

“…We developed and tested our solution on a commercially available Typhoon II power wheelchair from Invacare. We had previously modified Invacare's DX controller to intercept the user input and adjust the control signals before sending them to the motors, allowing us to implement and test various shared control algorithms on the platform [5]. The algorithm itself runs on an embedded Beagle-Bone Black.…”

“…In this context, many research teams are involved in the development of solutions to assist in the driving of electric wheelchairs. Indeed, driving assistance can be provided in the form of autonomous [2][3] or semi-autonomous [4][5] assistance but are so far restricted to indoor use because they do not provide assistance with respect to negative obstacles.…”

Comparing shared control approaches for alternative interfaces: A wheelchair simulator experiment

“…This implementation was an improvement on our first implementation detailed in [16]. In particular, we improved the autonomy performance by focussing on testing its parameters in a simulation and modifying our algorithm to perform better for driving in reverse.…”

“…In this paper, we employ a probabilistic approach to blending similar to [16]. However, we include probabilistic models for alternative interfaces: head-array and sip-puff switch.…”

“…To account for uncertainty in user's intentions and inability to perform certain manoeuvres, probabilistic models of the user's intention have been employed [13]- [15]. Probability distributions have been used to model the actual blending of the human's intended velocity taken from a joystick and the path planner's velocity [16].…”