Generalized Shared Control versus Classical Shared Control: Illustrative Examples
This work tackles safety and efficiency issues in shared control for applications like search and rescue robots, teleoperation, and assistive driving, but it is incremental as it describes prior results in a more accessible format.
The paper addresses the problem of suboptimal safety, efficiency, and operator-autonomy agreement in shared control systems under multimodal conditions, where existing methods can fuse safe inputs into unsafe outputs. It presents generalized shared control (GSC), which optimizes these objectives simultaneously to prevent unsafe shared control, as introduced in prior work.
Shared control fuses operator inputs and autonomy inputs into a single command. However, if environmental or operator predictions are multimodal, state of the art approaches are suboptimal with respect to safety, efficiency, and operator-autonomy agreement: even under mildly challenging conditions, existing approaches can fuse two safe inputs into an unsafe shared control [13]. Multi-modal conditions are common to many real world applications, such as search and rescue robots navigating disaster zones, teleoperated robots facing communication degradation, and assistive driving technologies. In [11, 13], we introduced a novel approach called generalized shared control (GSC) that simultaneously optimizes autonomy objectives (e.g., safety and efficiency) and operator-autonomy agreement under multimodal conditions; this optimality prevents such unsafe shared control. In this paper, we describe those results in more user friendly language by using illustrations and text.