A decision-theoretic approach for the collaborative control of a smart wheelchair.

While assistive robot technology is quickly progressing, several challenges remain to make this technology truly usable and useful for humans. One of the aspects that is particularly important is in defining control protocols that allow both the human and the robot technology to contribute to the best of their abilities. In this paper we propose a framework for the collaborative control of a smart wheelchair designed for individuals with mobility impairments. Our approach is based on a decision-theoretic model of control, and accepts commands from both the human user and robot controller. We use a Partially Observable Markov Decision Process to optimize the collaborative action choice, which allows the system to take into account uncertainty in the user intent, in the command and in the environment. The system is deployed and validated on the SmartWheeler platform, and experiments with 8 users show the improvement in usability and navigation efficiency that are achieved with this form of collaborative control.

The potential impact of intelligent power wheelchair use on social participation: perspectives of users, caregivers and clinicians.

PURPOSE: To explore power wheelchair users', caregivers' and clinicians' perspectives regarding the potential impact of intelligent power wheelchair use on social participation. METHODS: Semi-structured interviews were conducted with power wheelchair users (n = 12), caregivers (n = 4) and clinicians (n = 12). An illustrative video was used to facilitate discussion. The transcribed interviews were analyzed using thematic analysis. RESULTS: Three main themes were identified based on the experiences of the power wheelchair users, caregivers and clinicians: (1) increased social participation opportunities, (2) changing how social participation is experienced and (3) decreased risk of accidents during social participation. CONCLUSION: Findings from this study suggest that an intelligent power wheelchair would enhance social participation in a variety of important ways, thereby providing support for continued design and development of this assistive technology. IMPLICATIONS FOR REHABILITATION: An intelligent power wheelchair has the potential to: Increase social participation opportunities by overcoming challenges associated with navigating through crowds and small spaces. Change how social participation is experienced through "normalizing" social interactions and decreasing the effort required to drive a power wheelchair. Decrease the risk of accidents during social participation by reducing the need for dangerous compensatory strategies and minimizing the impact of the physical environment.

Exploring powered wheelchair users and their caregivers' perspectives on potential intelligent power wheelchair use: a qualitative study.

Power wheelchairs (PWCs) can have a positive impact on user well-being, self-esteem, pain, activity and participation. Newly developed intelligent power wheelchairs (IPWs), allowing autonomous or collaboratively-controlled navigation, could enhance mobility of individuals not able to use, or having difficulty using, standard PWCs. The objective of this study was to explore the perspectives of PWC users (PWUs) and their caregivers regarding if and how IPWs could impact on current challenges faced by PWUs, as well as inform current development of IPWs. A qualitative exploratory study using individual interviews was conducted with PWUs (n = 12) and caregivers (n = 4). A semi-structured interview guide and video were used to facilitate informed discussion regarding IPWs. Thematic analysis revealed three main themes: (1) "challenging situations that may be overcome by an IPW" described how the IPW features of obstacle avoidance, path following, and target following could alleviate PWUs' identified mobility difficulties; (2) "cautious optimism concerning IPW use revealed participants" addresses concerns regarding using an IPW as well as technological suggestions; (3) "defining the potential IPW user" revealed characteristics of PWUs that would benefit from IPW use. Findings indicate how IPW use may help overcome PWC difficulties and confirm the importance of user input in the ongoing development of IPWs.

Real-time MRI-based control of a ferromagnetic core for endovascular navigation.

This paper shows that even a simple proportional-integral-derivative (PID) controller can be used in a clinical MRI system for real-time navigation of a ferromagnetic bead along a predefined trajectory. Although the PID controller has been validated in vivo in the artery of a living animal using a conventional clinical MRI platform, here the rectilinear navigation of a ferromagnetic bead is assessed experimentally along a two-dimensional (2D) path as well as the control of the bead in a pulsatile flow. The experimental results suggest the likelihood of controlling untethered microdevices or robots equipped with a ferromagnetic core inside complex pathways in the human body.

Bidimensional MRI-based navigation system using a PID controller.

The feasibility of using 2D real-time control to navigate ferromagnetic entities in an MRI bore for novel medical interventions is assessed. Preliminary experimental results confirm that a simple PID controller can be suitable for several applications where targeting out-of-reach locations within the cardiovascular system is essential.