Developing Operator Models for UAV Search Scheduling

Abstract

With the increased use of Unmanned Aerial Vehicles (UAVs), it is envisioned that UAV operators will become high level mission supervisors, responsible for information management and task planning. In the context of search missions, operators supervising a large number of UAVs can become overwhelmed with the sheer amount of information collected by the UAVs, making it difficult to optimize the information collection or direct their attention to the relevant data. Novel decisionsupport methods that account for realistic operator performance will therefore be required to aid the operators. This paper considers a decision support formulation for sequential search tasks, and discusses a non-preemptive scheduling formulation for a single operator performing a search mission in a time-constrained environment. The formulation is then generalized to include operator performance obtained from previous human-in-the-loop experiments, and presents one of the principal contributions of the paper. The sensitivity of the proposed model is analyzed in the presence of uncertainty to the operator model and search times, and a comparison is made between the expected performance difference between this scheduling system and a greedy scheduling strategy representative of operator planning. The paper concludes with the design of a human-in-the-loop experiment for a scheduling, replanning task for a simulated UAV mission.

Identifying Suitable Algorithms for Human-Computer Collaborative Scheduling of Multiple Unmanned Vehicles

“…48 Increasing automation transparency may be difficult with the use of meta-heuristic and auction algorithms, whereas deterministic solvers such as greedy algorithms often emulate the method by which humans would choose to solve the problem. 49 with an "inferior," but understandable algorithm perform better than a human operator collaborating with a more "advanced" but less predictable and more opaque algorithm? Finally, one of the largest issues with the adoption of stochastic algorithms for UV scheduling may be regulatory 50 -how does one certify that an algorithm with no guarantee of repeatability is safe or ready for deployment in safety critical missions?…”

Optimal task allocation in multi-human multi-robot interaction

“…In [2], a decision support system is developed to aid a single operator manage information received by multiple UAVs. Savla et al developed a queuing model in which UAVs and human are servers and targets appear over time [20].…”

Mixed-initiative nested classification by optimal thresholding

“…A number of human-machine interaction strategies are proposed in [17] for a single operator-multiple heterogeneous vehicles scenario. In [18], a decision support system for sequential visual search tasks is presented while the effectiveness of the system is validated by human-subject experiments. It is shown that the human operator performance improves under the decision support system with automated algorithmic aids.…”