Collaborative control: a robot-centric model for vehicle teleoperation

Abstract

Lausanne (EPFL) served as host institution (institution d’accueil) for this thesis and provided research facilities and infrastructure. Telerobotic systems have traditionally been designed and solely operated from a human point of view. Though this approach suffices for some domains, it is sub-optimal for tasks such as operating multiple vehicles or controlling planetary rovers. Thus, I believe it is worthwhile to examine a new system model for teleoperation: collaborative control. In collaborative control, a human and a robot collaborate to perform tasks and to achieve common goals. Instead of a supervisor dictating to a subordinate, the human and the robot engage in dialogue to exchange information, to ask questions, and to resolve differences. Instead of serving the human as a mere tool, the robot can operate more like a partner. With this approach, the robot has more freedom in execution and is more likely to find good solutions when there are problems. With collaborative control, the human is able to function as a resource for the robot, providing information and processing just like other system modules. In particular, the robot can ask the human questions as it works, to obtain assistance with cognition and perception during task