The Role of Human-Automation Consensus in Multiple Unmanned Vehicle Scheduling

Abstract

Objective: This study examined the impact of increasing automation replanning rates on operator performance and workload when supervising a decentralized network of heterogeneous unmanned vehicles. Background: Futuristic unmanned vehicles systems will invert the operator-to-vehicle ratio so that one operator can control multiple dissimilar vehicles, connected through a decentralized network. Significant human-automation collaboration will be needed due to automation brittleness, but such collaboration could cause high workload. Method: Three increasing levels of replanning were tested on an existing, multiple unmanned vehicle simulation environment that leverages decentralized algorithms for vehicle routing and task allocation, in conjunction with human supervision. Results: Rapid replanning can cause high operator workload, ultimately resulting in poorer overall system performance. Poor performance was associated with a lack of operator consensus for when to accept the automation"s suggested prompts for new plan consideration, as well as negative attitudes towards unmanned aerial vehicles in general. Participants with video game experience tended to collaborate more with the automation, which resulted in better performance. Conclusion: In decentralized unmanned vehicle networks, operators who ignore the automation"s requests for new plan consideration and impose rapid replans both increase their own workload and reduce the ability of the vehicle network to operate at its maximum capacity. Application: These findings have implications for personnel selection and training for futuristic systems involving human collaboration with decentralized algorithms embedded in networks of autonomous systems.

Assessing operator strategies for real-time replanning of multiple unmanned vehicles

“…For the 120 second initial replan prompting interval, however, only 8 operators never changed the prompting in- terval. These results reflect a finding from the previous experiment [10], where operators generally could not wait the full 120 seconds between replans. For operators who did use the Replan Interval Dial, the average number of Replan Interval Dial changes was evaluated.…”

“…Surveys conducted after each trial revealed that approximately 35% of the participants were frustrated by the automated planner. Results from this experiment also showed that operators who collaborated with the automated planner had significantly higher performance and lower workload than those who ignored automation requests for replan consideration [10].…”

“…In futuristic multiple unmanned vehicle settings, the rate at which a human operator must confirm or alter plans has been shown to have a significant impact on operator workload and system performance [10]. In this previous work, operators were prompted to replan at three different intervals: 30 seconds, 45 seconds, and 120 seconds.…”

“…Given previous results that showed that at least onethird of operators ignored preset automation replanning intervals [10], a new component was added to the map display, as shown in Fig. 3.…”

“…The dial can be set to a preferred value, as long as it is between the two boundary values, 1 and 360 seconds. The maximum setting of 360 seconds was chosen to be three times longer than the maximum initial prompting interval of 120 seconds from the previous experiment [10]. In addition, automated replan prompting intervals could be disabled by selecting the manual replan option.…”