Skip to content

Ways to assist powered wheelchair users

Project: Innovation

Description

Research has resulted in new features for powered wheelchairs that included: effort-reduction, predictive and interactive Artificial Intelligence, so that children could drive for longer and in some cases for the first time. Research was based on many years of work by the Systems Engineering Research Group into climbing and walking robots and automated guided vehicles.

The systems have been used in six special schools and institutions (including RNIB and NHS) and many private homes. There has been economic impact in reducing the need for carers and the devices have also changed some professional services.

The research has investigated perception of motion-lag compared with actual phase-lag for a powered wheelchair system and changes to user learning behaviour of powered wheelchair drivers depending on the level of sensor support. The results were used to improve steering of a powered wheelchair using an expert system to interpret hand tremor.

A new prototype intelligent mobility system to assist powered wheelchair user was created that used low cost ultrasonic sensors. That led to the creation of new powered wheelchair systems for the rehabilitation of some severely disabled users.

Virtual reality systems were investigated and new systems were created to train powered wheelchair users and to test new wheelchair systems.

Veer corrections systems were created to control wheel-chair direction on slopes and these were combined with sensor systems to improve wheelchair-driving.

Variable switches were designed (mainly by M Langner) as an alternative to digital-switches or joysticks. These were integrated with the other systems using task programming methods.

New navigational assistance systems were created for wheelchair users with expert system to interpret hand tremor and provide joystick position signals and new systems to detect failure in a powered wheelchair using artificial neural networks.

Some simple gesture recognition systems were created to assist in controlling a powered wheelchair and combined with an adaptive fuzzy control algorithm for a powered wheelchair. These systems were adapted to Interpret hand tremor using an expert system to assist with steering.

Finally, a rule-based system was created to assist a powered wheelchair driver and that was further developed into a proposed new system that uses self-reliance factors to decide how to share control between human powered wheelchair drivers and ultrasonic sensors. Non-model-based control was applied to a wheelchair and a train pulling two trailers.

As part of this project, Martin Langner copleted his PhD in 2012 / 2013 after studying effort reduction and collision avoidance for powered wheelchairs; SCAD Mobility System. The PhD was directd by DA Sanders.

Layman's description

Research at the University of Portsmouth has created new user-friendly control, navigation and communication systems for powered-wheelchairs that have made a significant and positive impact on the lives of users. These have given many disabled children and adults an opportunity for independent mobility, some for the first time.

Key findings

Investigated:

- Perception of motion-lag compared with actual phase-lag for a powered wheelchair system.
- Changes to user learning behaviour of powered wheelchair drivers depending on the level of sensor support.
- Improving steering of a powered wheelchair using an expert system to interpret hand tremor.

Created:
- A new prototype intelligent mobility system to assist powered wheelchair user.
- Low cost ultrasonic sensors for tele-operated vehicles.
- New powered wheelchair systems for the rehabilitation of some severely disabled users.
- Virtual reality systems to train powered wheelchair users and test new wheelchair systems.
- Veer corrections systems to control wheel-chair direction on slopes.
- Sensor systems to improve wheelchair-driving.
- Variable switches as an alternative to digital-switches or joysticks.
- Task programming methods for powered wheelchairs.
- Navigational assistance systems for wheelchair users.
- Expert system to interpret hand tremor and provide joystick position signals.
- Systems to detect failure in a powered wheelchair sensor system using artificial neural networks.
- Simple gesture recognition systems to assist in controlling a powered wheelchair.
- An adaptive fuzzy control algorithm for a powered wheelchair.
- Systems to Interpret hand tremor using an expert system to assist with steering.
- Rule-based system to assist a powered wheelchair driver.
- A new system that uses self-reliance factors to decide how to share control between human powered wheelchair drivers and ultrasonic sensors.
- Non-model-based control of a wheeled vehicle pulling two trailers to provide early powered mobility and driving experiences.
Short titleWheelchair research
StatusFinished
Effective start/end date8/02/999/07/16

Collaborative partners

  • University of Portsmouth (lead)
  • University of Plymouth
  • Chailey Heritage Clinical Services
  • Quest Enabling Designs
  • NHS England
Relations

ID: 9575373