Michael Cashmore

AUV mission control via temporal planning

Underwater installations require regular inspection and maintenance. We are exploring the idea of performing these tasks using an autonomous underwater vehicle, achieving persistent autonomous behaviour in order to avoid the need for frequent human intervention. In this paper we consider one aspect of this problem, which is the construction of a suitable plan for a single inspection tour. In particular we generate a temporal plan that optimises the time taken to complete the inspection mission. We report on physical trials with the system at the Diver and ROV driver Training Center in Fort William, Scotland, discussing some of the lessons learned.

Toward persistent autonomous intervention in a subsea panel

Intervention autonomous underwater vehicles (I-AUVs) have the potential to open new avenues for the maintenance and monitoring of offshore subsea facilities in a cost-effective way. However, this requires challenging intervention operations to be carried out persistently, thus minimizing human supervision and ensuring a reliable vehicle behaviour under unexpected perturbances and failures. This paper describes a system to perform autonomous intervention—in particular valve-turning—using the concept of persistent autonomy. To achieve this goal, we build a framework that integrates different disciplines, involving mechatronics, localization, control, machine learning and planning techniques, bearing in mind robustness in the implementation of all of them. We present experiments in a water tank, conducted with Girona 500 I-AUV in the context of a multiple intervention mission. Results show how the vehicle sets several valve panel configurations throughout the experiment while handling different errors, either spontaneous or induced. Finally, we report the insights gained from our experience and we discuss the main aspects that must be matured and refined in order to promote the future development of intervention autonomous vehicles that can operate, persistently, in subsea facilities.

Planning as Quantified Boolean Formula

This paper introduces two techniques for translating bounded propositional reachability problems into Quantified Boolean Formulae (QBF). Both exploit the binary-tree structure of the QBF problem to produce encodings logarithmic in the size of the instance and thus exponentially smaller than the corresponding SAT encoding with the same bound. The first encoding is based on the iterative squaring formulation of Rintanen. The second encoding is a compact tree encoding that is more efficient than the first one, requiring fewer alternations of quantifiers and fewer variables. We present experimental results showing that the approach is feasible, although not yet competitive with current state of the art SAT-based solvers.

Opportunistic Planning in Autonomous Underwater Missions

This paper explores the execution of planned autonomous underwater vehicle (AUV) missions where opportunities to achieve additional utility can arise during execution. The missions are represented as temporal planning problems, with hard goals and time constraints. Opportunities are soft goals with high utility. The probability distributions for the occurrences of these opportunities are not known, but it is known that they are unlikely, so it is not worth trying to anticipate their occurrence prior to plan execution. However, as they are high utility, it is worth trying to address them dynamically when they are encountered, as long as this can be done without sacrificing the achievement of the hard goals of the problem. We formally characterize the opportunistic planning problem, introduce a novel approach to opportunistic planning, and compare it with an on-board replanning approach in the domain of AUVs performing pillar expection and chain-following tasks.Note to Practitioners—This paper concerns high-level intelligent automation of unmanned vehicle operations in the context of undersea inspection and maintenance. The objective is to provide a robust long-term autonomy, enabling the vehicle to make its own decisions about how to prioritize goals and use its resources. Plans to achieve large numbers of goals over time are constructed autonomously by a planning system using models of activity and resource consumption. In order to avoid running up against resource bounds in a way that would compromise robustness, models of resource consumption are conservative. An important aspect of long-term autonomy concerns how unused resources that accumulate over time because of conservative assumptions can be used to increase overall utility. The approach we describe is deterministic: we do not model uncertainty or allow the planner to reason with contingencies. Instead, we focus on how to exploit resource intelligently to obtain the best available utility, in a way that does not undermine the reliability or predictability of operational behavior.

Decreasing Uncertainty in Planning with State Prediction

In real world environments the state is almost never completely known. Exploration is often expensive. The application of planning in these environments is consequently more difficult and less robust. In this paper we present an approach for predicting new information about a partially-known state. The state is translated into a partially-known multigraph, which can then be extended using machine-learning techniques. We demonstrate the effectiveness of our approach, showing that it enhances the scalability of our planners, and leads to less time spent on sensing actions.

On AUV actions to correctly label world information

An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on autonomous missions with success. One of the key areas is correctly understanding the surrounding environment. However, most of the state-of-the-art approaches in labelling world information are based on the analysis of a single frame, whilst - especially in scenarios where the vehicle interact with complex structures - there is the need of sensor data from multiple views, in order to correctly classify world information. This paper presents an active approach to solve this problem, with a tree-based (path)-planner which makes the vehicle executing a specific set of actions (following a specific trajectory), in order to discriminate among several possibilities. Results in simulation, with varying parameters, have shown that the algorithm is always bringing the robot to locations where it is expected that measurements would be different, according to the different environment.