Michael Gillham

Weightless Neural System Employing Simple Sensor Data for Efficient Real-Time Round-Corner, Junction and Doorway Detection for Autonomous System Path Planning in Smart Robotic Assisted Healthcare Wheelchairs

Human assistive devices need to be effective with real-time assistance in real world situations: powered wheelchair users require reassuring robust support, especially in the area of collision avoidance. However, it is important that the intelligent system does not take away control from the user. The patient must be allowed to provide the intelligence in the system and the assistive technology must be engineered to be sufficiently smart to recognize and accommodate this. Robotic assistance employed in the healthcare arena must therefore emphasize positive support rather than adopting an intrusive role. Weightless Neural Networks are an excellent pattern recognition tool for real-time applications. This paper introduces a technique for look-ahead identification of open doorways and junctions. Simple sensor data in real-time is used to detect open doors with inherent data uncertainties using a technique applied to a Weightless Neural Network Architecture.

A Dynamic Localized Adjustable Force Field Method for Real-Time Assistive Non-Holonomic Mobile Robotics

Providing an assistive navigation system that augments rather than usurps user control of a powered wheelchair represents a significant technical challenge. This paper evaluates an assistive collision avoidance method for a powered wheelchair that allows the user to navigate safely whilst maintaining their overall governance of the platform motion. The paper shows that by shaping, switching and adjusting localized potential fields we are able to negotiate different obstacles by generating a more intuitively natural trajectory, one that does not deviate significantly from the operator in the loop desired-trajectory. It can also be seen that this method does not suffer from the local minima problem, or narrow corridor and proximity oscillation, which are common problems that occur when using potential fields. Furthermore this localized method enables the robotic platform to pass very close to obstacles, such as when negotiating a narrow passage or doorway.

Real-Time Doorway Detection and Alignment Determination for Improved Trajectory Generation in Assistive Mobile Robotic Wheelchairs

Powered wheelchair users may find operation in enclosed environments such as buildings difficult, a fundamental problem exists: wheelchairs are not much narrower than the doorway they wish to pass through. The ability to detect and pass through doorways represents a major current challenge for automated guided wheelchairs. We utilize a simple doorway pattern recognition technique for fast processing in a real-time system for robotic wheelchair users. We are able to show a 96% detection and identification of 5 individual doorways and an 86% recognition rate of 22 separate approach angles and translations. We conclude that pattern recognition using features obtained from simple constrained infrared ranging sensor data binning can be utilized for fast identification of doorways, and important coarse position and approach angle determination, suitable for real-time trajectory adjustment, representing a significant enhancement in this area.

Powered Wheelchair Platform for Assistive Technology Development

Literature shows that numerous wheelchair platforms, of various complexities, have been developed and evaluated for Assistive Technology purposes. However there has been little consideration to providing researchers with an embedded system which is fully compatible, and communicates seamlessly with current manufacturers wheelchair systems. We present our powered wheelchair platform which allows researchers to mount various inertial and environment sensors, and run guidance and navigation algorithms which can modify the human desired joystick trajectory, so as to assist users with negotiating obstacles, and moving from room to room. We are also able to directly access other currently manufactured human input devices and integrate new and novel input devices into the powered wheelchair platform for clinical and research assessment.

Embedded hardware for closing the gap between research and industry in the assistive powered wheelchair market

Literature is abound with smart wheelchair platforms of various developments, yet to date there has been little technology to find its way to the market place. Many trials and much research has taken place over the last few decades however the end user has benefited precious little. There exists two fundamental difficulties when developing a smart powered wheelchair assistive system, the first is need for the system to be fully compatible with all of the manufacturers, and the second is to produce a technology and business model which is marketable and therefore desirable to the manufacturers. However this requires the researchers to have access to hardware which can be used to develop practical systems which will seamlessly integrate and communicate with existing manufacturers wheelchair systems. We have developed a low-cost embedded system which integrates with 95% of the powered wheelchair controller market; our system allows researchers to access the low level embedded system with more powerful computational devices running sophisticated software enabling rapid development of algorithms and techniques. When they have been evaluated they can be easily ported to the embedded processor for real-time evaluation and clinical trial.

Assistive Trajectories for Human-in-the-Loop Mobile Robotic Platforms

Autonomous and semi-autonomous smoothly interruptible trajectories are developed which are highly suitable for application in tele-operated mobile robots, operator on-board military mobile ground platforms, and other mobility assistance platforms. These trajectories will allow a navigational system to provide assistance to the operator in the loop, for purpose built robots or remotely operated platforms. This will allow the platform to function well beyond the line-of-sight of the operator, enabling remote operation inside a building, surveillance, or advanced observations whilst keeping the operator in a safe location. In addition, on-board operators can be assisted to navigate without collision when distracted, or under-fire, or when physically disabled by injury.

Evaluation of 3D obstacle avoidance algorithm for smart powered wheelchairs

This research investigates the feasibility for the development of a novel 3D collision avoidance system for smart powered wheelchairs operating in a cluttered setting by using a scenario generated in a simulated environment using the Robot Operating System development framework. We constructed an innovative interface with a commercially available powered wheelchair system in order to extract joystick data to provide the input for interacting with the simulation. By integrating with a standard PWC control system the user can operate the PWC joystick with the model responding in real-time. The wheelchair model was equipped with a Kinect depth sensor segmented into three layers, two representing the upper body and torso, and a third layer fused with a LIDAR for the leg section. When using the assisted driving algorithm there was a 91.7% reduction in collisions and the course completion rate was 100% compared to 87.5% when not using the algorithm.

Attitude Control of Small Probes for De-Orbit, Descent and Surface Impact on Airless Bodies Using a Single PWM Thruster

A single thruster attitude and de-orbital control method is proposed, capable of delivering a small spin stabilized probe with payload to the surface of an airless body such as the Moon. Nutation removal, attitude control and fast large angle maneuvers have been demonstrated and shown to be effective using a model of a commercially available single standard cold gas pulse width modulated controlled thruster. Maximum final impact angle due to drift and residual velocities was found to be less than 5 degrees and the maximum angle of attack to be 4 deg. The conventional 3-axis control would require as many as twelve thrusters a more substantial structure with complex pipe-work, and a more sophisticated controller. The single thruster concept reduces launch mass and thus cost of the mission, making the concept of small networked surface probes for extended science missions more viable. Experiments based on computer simulation have shown that strict design and mission profile requirements can be fulfilled using the single thruster control method.