Teleoperation allows the use of human intelligence and decision making in remote tasks which are too dangerous for humans to perform. Technologies such as force feedback and haptic guidance have shown to increase task efficiency during teleoperation. In an unmodeled environment, sensors provide input for haptic guidance or present extra information about the environment to the user in order to make decisions and to perform the tasks. These sensors come with inherent errors and uncertainties which propagate through the teleoperation system. The absence of knowledge of these errors has been shown to cause deterioration in the task performance. These errors can further cause the application of forces on the environment by the robot without the knowledge of the user while using haptic guidance. Thereby, the strategies being used to increase task performance can have some adverse hidden effects. Thus, it crucial to have an understanding of the behaviour of the errors and uncertainties in the system. It is considered critical for making decisions about how the robot system can be controlled and used to manipulate objects remotely.

In this thesis, a novel framework for estimating the uncertainties in a vision-aided teleoperation system in real-time is introduced. The uncertainty estimate can then be used by the control system or communicated to the user. Methods to use the uncertainty estimate for haptic guidance and for user display are proposed. Furthermore, the thesis analyzes the behaviour of the uncertainties in the system and the sensitivity of the system to individual component errors. It evaluates the uncertainties in individual components of the system and implements an uncertainty model for each of them. It then provides a method to propagate these uncertainty models through the system. This results in a final uncertainty estimate in the frame of reference of interest for the task. Experiments were performed to validate the component uncertainty models, the propagation method, and the system as a whole. Additionally, an inverse of the propagation method is also conceived so as to obtain the component accuracy specification from system uncertainty requirements. This can be used in the design of future teleoperation systems.

Teleoperation – performing tasks remotely by controlling a robot – permits the execution of many important tasks that would otherwise be infeasible for people to carry out directly. Nuclear accident recovery, deep water operations, and remote satellite servicing are just three examples. Remote task execution principally offers two extremes for control of the teleoperated robot: direct tele manipulation, which provides flexible task execution, but requires continuous operator attention, and automation, which lacks flexibility but offers superior performance in predictable and repetitive tasks (where the human assumes a supervisory role). This dissertation explores a third option, termed hap- tic shared control, which lies in-between these two extremes, and in which the control forces exerted by the human operator are continuously merged with ‘guidance’ forces generated by the automation. In a haptic shared control system, the operators continually contribute to the task execution, keeping their skills and situational awareness. It is common practice to design the haptic shared control systems heuristically, by iteratively adjusting them to the satisfaction of the system designer, primarily based on human-in- the-loop experiments. In this dissertation, we aim to improve this design and evaluation process. Our goal is to follow a system-theoretic approach and formalize the design procedures of haptic shared control systems applied to teleoperation. Such a formalization should provide designers of future HSC systems with a better understanding and more control over the design process, with the ultimate goal of making the HSC systems safer, easier and more intuitive to use, and overall to perform better. The research goal of this dissertation has been divided into three parts.