Elicitation of trustworthiness requirements for highly dexterous teleoperation systems with signal latency

Abstract

IntroductionTeleoperated robotic manipulators allow us to bring human dexterity and cognition to hard-to-reach places on Earth and in space. In long-distance teleoperation, however, the limits of the speed of light results in an unavoidable and perceivable signal delay. The resultant disconnect between command, action, and feedback means that systems often behave unexpectedly, reducing operators' trust in their systems. If we are to widely adopt telemanipulation technology in high-latency applications, we must identify and specify what would make these systems trustworthy.MethodsIn this requirements elicitation study, we present the results of 13 interviews with expert operators of remote machinery from four different application areas—nuclear reactor maintenance, robot-assisted surgery, underwater exploration, and ordnance disposal—exploring which features, techniques, or experiences lead them to trust their systems.ResultsWe found that across all applications, except for surgery, the top-priority requirement for developing trust is that operators must have a comprehensive engineering understanding of the systems' capabilities and limitations. The remaining requirements can be summarized into three areas: improving situational awareness, facilitating operator training, and familiarity, and easing the operator's cognitive load.DiscussionWhile the inclusion of technical features to assist the operators was welcomed, these were given lower priority than non-technical, user-centric approaches. The signal delays in the participants' systems ranged from none perceived to 1 min, and included examples of successful dexterous telemanipulation for maintenance tasks with a 2 s delay. As this is comparable to Earth-to-orbit and Earth-to-Moon delays, the requirements discussed could be transferable to telemanipulation tasks in space.

Verification of a virtual lunar regolith simulant

“…As suggested by Pereira and Schmidt (2021), this model would be of benefit for time-adjusted, model-mediated teleoperation system (Hulin et al, 2021), where a more general approximation of regolith would be acceptable. It could also be used to train operators using virtual robots in a low-risk scenario, which we have previously identified as a key requirement for developing trust in teleoperated systems (Louca et al, 2023). When compared with using physical simulants, conducting early training using a simulation such as this would likely be cheaper and safer.…”

Network Latency in Teleoperation of Connected and Autonomous Vehicles: A Review of Trends, Challenges, and Mitigation Strategies

“…Such delays often cause operators to adjust strategies, transitioning from open-loop to closed-loop control methods, including start-and-stop or move-and-wait, sometimes even disregarding the visual feedback [ 18 , 19 ]. The cognitive threshold for maintaining real-time performance is typically within 0.4 s. Upon receiving feedback from the vehicle, operators must respond within 0 to 3 s, with a minimum response time of 0.2 s [ 39 , 40 ].…”

“…Teleoperation is generally used as a fallback solution to maintain the safety of a vehicle in cases of failure scenarios such as malfunction, challenging weather, confusing situations, collision, or other such situations [ 93 ]. Other use cases of teleoperation include places where it is dangerous or difficult for humans to reach, such as telerobotics for space and underwater exploration, satellite communications, use of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) for reconnaissance missions, search and rescue, or surveillance in military/defensive applications, and also for telesurgery in medical domains [ 40 ]. The impact of network latency and requirements across various domains are detailed in Table 3 .…”