Level of Autonomy and Reliability in Co-located Multiple Robot Operation: A Five-Level Framework and Practical Design Guidance

Teleoperated robots augmented with autonomous assistance are increasingly used for conversational customer service in co-located deployments; we need a systematic method for determining which functions to automate and which to retain for the operator. We introduce a Level of Autonomy (LOA) framework with five levels and empirically examine how LOA and autonomy reliability jointly affect outcomes in co-located deployments. We conducted a laboratory study in which participants (N=32) acted as robot operators and, via a teleoperated robot in a simulated shop, engaged in conversational product recommendation interactions using a teleoperation interface. We compared five LOA conditions across multiple reliability conditions and measured the NASA-TLX, System Usability Scale (SUS), interpersonal effects, and task performance. The results show that when reliability is high, the most effective strategy was either to fully automate the target function or to keep operator control minimal and clearly bounded; designs that required operators to both supervise the automation and intervene frequently tended to increase workload. In addition, in early deployments, when operators are unfamiliar with teleoperation, avoid designs that require frequent operator decisions. When reliability is limited, lower LOA was preferable, reducing mode-switching between error recovery and normal teleoperation. This study provides a five-level LOA framework for co-located multi-robot customer service and suggests that effective customer-facing HRI in such settings requires aligning LOA with autonomy reliability and clear human-robot role allocation.