Supervisory Control Of Multiple Robots Research Articles

Supervisory Control of Multiple Robots Through Group Communication

Single-human supervision of collaborative semi-autonomous multirobot teams is recently getting the attention of the robotic community. In this context, the adoption of a growing number of robots does not necessarily produce a gain in performance, due to the increased workload of the human supervisor. However, enabling human operators to communicate with groups of robots can reduce the operators’ effort in guiding the team. Here, group communicating is intended not only to assign a task to a group but also as a way to identify the group members. This is particularly relevant in proximate interactions or in the necessity of freeing operator’s hands. In this paper, starting from an analysis of real human utterances in selecting groups of robots, we extracted the features that are useful to define a basic vocabulary and analyzed the single robot needed awareness about its own characteristics and those of the robots in the neighborhood. Such analysis is used to develop a semi-autonomous multirobot simulated environment, where a human operator can guide groups of robots. The simulated environment is used to measure the humans’ interaction effort and the task effectiveness while increasing the number of robots involved in a joint task, in the two cases where the commands are issued toward single or grouped robots.

Modeling Teamwork in Supervisory Control of Multiple Robots

Simultaneously controlling multiple robots requires multiple operators working together as a team. Determining how to construct the team to promote performance and reduce workload are critical questions that must be answered in these settings. To this end, we investigated the effect of team structure and scheduling notification on operators' performance, subjective workload, work processes, and communication using a human-in-the-loop experiment. In an urban search and rescue setting, we compared a pooled condition, in which team members shared control of 24 robots, with a sector condition, in which each team member controlled half of all the robots. For scheduling notification, an alert was given when the operator spent too much time on one robot and either suggested or forced the operator to change to another robot. A discrete-event simulation model was constructed to model the teamwork in supervisory control of multiple robots. The model was significantly improved by the inclusion of a behavior termed as “backup.” Backup behavior is a critical coordination mechanism often observed in teams, but rarely explicitly modeled. Pooled teams showed an advantage when performing backup behaviors in both the experiment and the model. However, other factors must be considered when making a decision on what team structure to use.

Supervisory control of multiple robots in dynamic tasking environments

A military targeting environment was simulated to examine the effects of an intelligent route-planning agent RoboLeader, which could support dynamic robot re-tasking based on battlefield developments, on the performance of robotics operators. We manipulated the level of assistance (LOAs) provided by RoboLeader as well as the presence of a visualisation tool that provided feedback to the participants on their primary task (target encapsulation) performance. Results showed that the participants’ primary task benefited from RoboLeader on all LOAs conditions compared to manual performance; however, visualisation had little effect. Frequent video gamers demonstrated significantly better situation awareness of the mission environment than did infrequent gamers. Those participants with higher spatial ability performed better on a secondary target detection task than did those with lower spatial ability. Finally, participants’ workload assessments were significantly lower when they were assisted by RoboLeader than when they performed the target entrapment task manually. Practitioner Summary: This study demonstrated the utility of an intelligent agent for enhancing robotics operators’ supervisory control performance as well as reducing their workload during a complex urban scenario involving moving targets. The results furthered the understanding of the interplay among level-of-autonomy, multitasking performance and individual differences in military tasking environments.

Supervisory Control of Multiple Robots

A military multitasking environment was simulated to examine the effects of an intelligent agent, RoboLeader, on the performance of robotics operators. The participants' task was to manage a team of ground robots with the assistance of RoboLeader, an intelligent agent capable of coordinating the robots and changing their routes on the basis of battlefield developments. In the first experiment, RoboLeader was perfectly reliable; in the second experiment, RoboLeader's recommendations were manipulated to be either false-alarm prone or miss prone, with a reliability level of either 60% or 90%. The visual density of the targeting environment was manipulated by the presence or absence of friendly soldiers. RoboLeader, when perfectly reliable, was helpful in reducing the overall mission times.The type of RoboLeader imperfection (false-alarm vs. miss prone) affected operators' performance of tasks involving visual scanning (target detection, route editing, and situation awareness). There was a consistent effect of visual density (clutter of the visual scene) for multiple performance measures. Participants' attentional control and video gaming experience affected their overall multitasking performance. In both experiments, participants with greater spatial ability consistently outperformed their low-spatial-ability counterparts in tasks that required effective visual scanning. Intelligent agents, such as RoboLeader, can benefit the overall human-robot teaming performance. However, the effects of type of agent unreliability, tasking requirements, and individual differences have complex effects on human-agent interaction. The current results will facilitate the implementation of robots in military settings and will provide useful data to designs of systems for multirobot control.

Supervisory Control of Multiple Robots: Human-Performance Issues and User-Interface Design

The purpose of this paper is to review research pertaining to the limitations and advantages of supervisory control for unmanned systems. We identify and discuss results showing technologies that mitigate the observed problems such as specialized interfaces, and adaptive systems. In the report, we first present an overview of definitions and important terms of supervisory control and human-agent teaming. We then discuss human performance issues in supervisory control of multiple robots with regard to operator multitasking performance, trust in automation, situation awareness, and operator workload. In the following sections, we review research findings for specific areas of supervisory control of multiple ground robots, aerial robots, and heterogeneous robots (using different types of robots in the same mission). In the last section, we review innovative techniques and technologies designed to enhance operator performance and reduce potential performance degradations identified in the literature.

Identifying Predictive Metrics for Supervisory Control of Multiple Robots

In recent years, much research has focused on making possible single-operator control of multiple robots. In these high workload situations, many questions arise including how many robots should be in the team, which autonomy levels should they employ, and when should these autonomy levels change? To answer these questions, sets of metric classes should be identified that capture these aspects of the human-robot team. Such a set of metric classes should have three properties. First, it should contain the key performance parameters of the system. Second, it should identify the limitations of the agents in the system. Third, it should have predictive power. In this paper, we decompose a human-robot team consisting of a single human and multiple robots in an effort to identify such a set of metric classes. We assess the ability of this set of metric classes to: 1) predict the number of robots that should be in the team and 2) predict system effectiveness. We do so by comparing predictions with actual data from a user study, which is also described.