Operator Object Function Guidance for a Real-Time Unmanned Vehicle Scheduling Algorithm

Abstract

Advances in autonomy have made it possible to invert the typical operator-to-unmanned-vehicle ratio so that a single operator can now control multiple heterogeneous unmanned vehicles. Algorithms used in unmanned-vehicle path planning and task allocation typically have an objective function that only takes into account variables initially identified by designers with set weightings. This can make the algorithm seemingly opaque to an operator and brittle under changing mission priorities. To address these issues, it is proposed that allowing operators to dynamically modify objective function weightings of an automated planner during a mission can have performance benefits. A multiple-unmanned-vehicle simulation test bed was modified so that operators could either choose one variable or choose any combination of equally weighted variables for the automated planner to use in evaluating mission plans. Results from a human-participant experiment showed that operators rated their performance and confidence highest when using the dynamic objective function with multiple objectives. Allowing operators to adjust multiple objectives resulted in enhanced situational awareness, increased spare mental capacity, fewer interventions to modify the objective function, and no significant differences in mission performance. Adding this form of flexibility and transparency to automation in future unmanned vehicle systems could improve performance, engender operator trust, and reduce errors.

Human Interaction With Multiple Remote Robots

“…In a subsequent experiment (Clare, Cummings, How, Whitten, & Toupet, 2012), weightings of the objective function were added to elements under the operator's control. Operators were allowed to select plan characteristics, such as target tracking or fuel efficiency, through either a radio button interface (allowing a single selection) or a check box (when multiple alternatives were available).…”

Computational design of mixed-initiative human–robot teaming that considers human factors: situational awareness, workload, and workflow preferences

“…Human–robot teaming has the potential to increase the productivity of human labor and improve the ergonomics of manual tasks. Based on recent industry interest in fielding human–robot teams, researchers have been investigating how best to include a human participant in the decision-making loop as a member of a human–robot team (Adams, 2009; Ardissono et al, 2012; Barnes et al, 2011; Clare et al, 2012; Dragan and Srinivasa, 2012; Goodrich et al, 2009; Herlant et al, 2016; Hooten et al, 2011; Pierce and Kuchenbecker, 2012; Sanderson, 1989; Zhang et al, 2012). However, the intricate choreography required to coordinate human-robot teams safely and efficiently represents a challenging computational problem.…”

“…This interface mediates the consequences of a human operator not being in close physical proximity to the action performed in order to make teleoperation more seamless, and leverages the autonomous capabilities of the robot to assist in accomplishing a given task. In such work, researchers often view the human operator as a vital component of the decision-making loop, particularly when this operator has knowledge of factors that are difficult to capture within a manually encoded, autonomous framework (Clare et al, 2012; Cummings et al, 2007; Durfee et al, 2014). Complementary to approaches that include the human operator in the loop, other work has focused on the development of computational methods able to generate scheduling solutions using information collected a priori from human experts (Ardissono et al, 2012; Hamasaki et al, 2004; Haynes et al, 1997; Macho et al, 2000; Zhang et al, 2012).…”

Biologically Inspired Model with Feature Selection for Target Recognition Using Biogeography-Based Optimization

“…Automatic target recognition is a key problem to be solved for fulfilling these complicated tasks. The target-tracking performance is necessary for improving in aerial tasks, and researchers have proposed many algorithms such as the shape-matching approach with optimized edge potential function [4], vision-based feature matching [5,6], navigation [7,8], and real-time task scheduling [9]. However, understanding how the visual cortex recognizes objects is a critical question for neuroscience [10].…”