This field report presents an overview of the development and testing of a semiautonomous underwater vehicle (sAUV). The work presented here is aimed at bridging the gap between current remotely operated vehicles and autonomous research platforms by developing shared autonomy capabilities for low-cost underwater vehicles. We use commercially available components and open-source software interfaces to provide a wider range of capabilities for underwater autonomy research at a lower cost than previously available systems. We describe the overall structure of the system, discuss its capabilities, and provide results demonstrating system performance. We place particular emphasis on shared autonomy, where a human operator is assisted in controlling an underwater tethered vehicle. We present three capabilities developed for the sAUV: (a) an assisted control mode that provides a variable level of assistance using an on-line estimate of user skill level, (b) a planner to generate paths that avoid tether entanglement, and (c) a sonar processing algorithm that identifies informative sonar images for selecting features for 3D scene reconstruction. The vehicle has been deployed on five off-shore and near-shore marine field deployments since 2015, and this report includes selected results from four of those trials to demonstrate the capabilities and limitations of the sAUV system. K E Y W O R D S human robot interaction, perception, planning, underwater robotics 1 | INTRODUCTION Unmanned underwater vehicles (UUVs) are used for a wide variety of tasks, from short-duration (hour-scale) inspection tasks to longduration (month-scale) data gathering missions. Within this group of vehicles there exists a wide range of autonomous capability, from limited or no autonomy on most industry-standard remotely operated vehicles (ROVs) to full autonomy on research-grade autonomous underwater vehicles (AUVs). In this paper, we examine partial-autonomy approaches that leverage the capabilities of autonomous systems to complement the skills of human operators.We use the term semi-autonomous to refer to a system that has some autonomous capabilities but must rely on a human operator for certain mission-critical capabilities. In this study, we develop and demonstrate a semi-autonomous underwater vehicle (sAUV) system.One of the primary limitations to deployment of AUVs is the perception that autonomy capabilities are not sufficiently robust for wide adoption. In many cases, the expense and specialized design of AUVs for particular tasks limits their applicability to a wider audience.In time-sensitive deployments, the robustness and task flexibility of ROVs means that they can be more readily deployed for a wider variety of tasks than autonomous systems (Murphy et al., 2012). J Field Robotics. 2019;36:495-516.wileyonlinelibrary.com/journal/rob