Self-funded PhD opportunities

Collision avoidance and assistance for powered wheelchairs and guided vehicles

  • Application end date: Saturday 1 July 2017
  • Funding Availability: Self-funded PhD students only
  • Department: School of Engineering
  • PhD Supervisor: David Sanders and Giles Tewkesbury

Research will be based on years of work by the SERG into robots and automated guided vehicles.

Various analogue input devices and sensors have been created to safely detect the environment to assist children with different disabilities, including analogue veer-correction systems. These analogue systems have been featured on tv and radio and footage of the older systems and some of the latest systems can be seen at on our Facebook page.

The analogue systems have been used in schools and institutions and have made a significant and positive impact. Work is being hampered by the analogue nature of the systems and so this research will begin by digitising the analogue input devices and object proximity sensors.

Aims: Digitise systems, investigate novel AI, and create new digital systems to assist wheelchair users to steer their powered wheelchairs in cluttered environments.

Methodology: Analogue input devices will be digitised and digital veer-correction will be introduced. New digital switches will be interfaced to microcontrollers to improve mobility and manoeuvring and make wheelchairs easier for children to use. Further developments will attempt to tolerate involuntary movements and provide proportional-response controls. Collision avoidance devices will be redesigned as digital systems and connected to expert systems to interpret hand movements and tremors, and AI systems will be created to improve control. Infra-red optical detectors with background suppression will be investigated to see if they can help drivers lacking spatial awareness. Logical IF THEN programs will be written to interpret input and then Fuzzy Systems will be investigated to see if they can be successfully used to interpret useful hand movements among tremors to control a powered wheelchair. Finally a Rule Based System will generate revised instructions for veer-correction and compare possible outputs to suggest the best possible course of action for the wheelchair. Case Based Reasoning (CBR) will provide confidence weightings for the different outputs. The CBR will be revised to compare errors against search criteria and to then normalize those errors with weighting factors to investigate if that improves the result.

How to Apply:

To apply or make an enquiry, please visit postgraduate research: Engineering

Applications should use our standard application forms and follow the instructions given under the ‘Research Degrees’ heading on the following webpage:

When applying please note the project code ENGN3420217

Funding notes:

Home/EU applicants only. Please use the online application form and state the project code and studentship title in the personal statement section.

An appropriate first or upper second class honours degree of any United Kingdom university or a recognised equivalent non-UK degree of the same standard honours degree or equivalent in a relevant subject or a master’s degree in an appropriate subject. Exceptionally, equivalent professional experience and/or qualifications will be considered.

References to recent published articles:

1. Sanders D, Bausch N, Liu H, et al. (2015) Improving Steering of a Powered Wheelchair Using an Expert System to Interpret Hand Tremor, Intelligent Robotics and Applications Pt II Volume: 9245 Pages: 460-471.

2. Sanders D, Langner M and Gegov A (2015) Perception of motion-lag compared with actual phase-lag for a powered wheelchair system. Proc’ Int’ Conf’ Health Informatics & Medical Systems, USA: CSREA Press, p. 79-81.

3. Sanders D (2016) Using a self-reliance factor for a disabled driver to decide on the share of combined-control between a powered wheelchair and an ultrasonic sensor system. IEEE Transactions on Neural Systems and Rehab Engineering (In Press).