A Framework for Predicting Future System Performance in Autonomous Unmanned Ground Vehicles

Abstract

The development of complex self-adaptive systems has accelerated rapidly over the past decade, led by the Department of Defense, which has sought to develop and field military systems, such as unmanned aerial vehicles and unmanned ground vehicles, with elevated levels of autonomy to accomplish their mission with reduced funding and manpower. As their role increases, such systems must be able to adapt and learn, and make nondeterministic decisions. To field such systems requires extensive testing, evaluation, verification, and validation-a challenging task. To address this, we apply a novel systems perspective to develop a framework to predict future system performance based on the complexity of the operating environment using newly introduced complexity measures and learned costs. In this paper, we consider an autonomous military ground robot navigating in complex off-road environments. Using our model and experimental data from Defense Advanced Research Projects Agency-led experiments, we demonstrate the accuracy with which our model can predict system performance and then validate our model against other experimental results.

Improving user specifications for robot behavior through active preference learning: Framework and evaluation

“…In addition, Anderson and Yang (2007) proposed a secondary complexity measure based on the distribution of obstacle types and the compressibility of the environment. In Young et al (2017), the measurement of complexity was extended from a binary distribution of local obstacles to a continuous one, enabling the use of dynamic obstacles.…”

A stakeholder framework for evaluating the ‐ilities of autonomous behaviors in complex adaptive systems

“…CASs are not very well understood and provide researchers with significant opportunities for concept exploration and behavior definition. Young's research addresses the challenge of test and evaluation of autonomous ground vehicles by predicting their performance over various terrains and disturbances 10 . The model developed in this work was used to predict the performance of a ground vehicle in a unique environment, but it did not extend to multiple agents working together in a swarm as a CAS.…”

Urban Navigation System With Multiple Sub-Maps and Multiple Sub-Navigators

“…Urban environment is also dynamic, i.e., spontaneous changes in working condition are expected [16], [17]. For example, in parking lots where cars move around frequently during rush hours, the user may mandate that the robot must yield to cars and move less aggressively but the robot can move freely during off-peak periods.…”