An integrated collision avoidance system for autonomous underwater vehicles

A review on improving the autonomy of unmanned surface vehicles through intelligent collision avoidance manoeuvres

“…A map of the current environment is maintained and the system uses reasoning to make behavioural decisions, which can be optimised as far as possible before being executed in sequence (Jong Tamba et al, 2007). However changing environments are known to cause unpredictable or unresponsive behaviour (Tan, 2006). Collision with a dynamic obstacle is also possible, as the computationally-intensive algorithms are not designed to run in real-time.…”

Making AUVs Truly Autonomous

“…This way of avoiding dynamic constraints on the path considerably simplifies path planning. The planning complexity can also be reduced through implicit path planning which does not create an explicit path for the vehicle to follow, but rather transforms the environment into an artificial potential field (Tan et al, 2004). In this field, obstacles and other forbidden areas serve as repulsors, pushing the vehicle away from them, while goals serves as attractors pulling the vehicle towards them.…”

“…about obstacles and bathymetry, and data gathered during the mission can be useful. This geographical information can be presented as map layers and typically includes parameters like (Midtgaard et al, 2006): Seabottom type Traditionally, significant amount of work has been spent on developing memory-efficient representations of maps, such as the quadtree, TIN models and spatial decomposition (Tan et al, 2004). While these methods may reduce memory requirements by several orders of magnitude without loss of information, the time to access information can increase dramatically.…”

“…By replanning the path, the vehicle is able to account for changes in its internal status and in the environment. The plan typically constitutes an explicit path to follow, but can alternatively be in the form of an artificial potential field used by the vehicle to guide it (Tan et al, 2004). At the very least, the plan may consist of a sequence of behaviour parameter sets for a reactive controller.…”

Real Time Underwater Obstacle Avoidance and Path Re-planning Using Simulated Multi-beam Forward Looking Sonar Images for Autonomous Surface Vehicle

“…In [11], they describe a heuristic search technique based on the fuzzy relation products carrying out path planning and collision avoidance for AUVs. Tan et al [12] present an integrated approach to the design of an obstacle avoidance system for AUVs, a type of incremental stochastic algorithm known as rapidly-exploring random tree (RRT) is merged with a maneuver automaton (MA) representation to form the motion planner. A fastest and efficient path planning method that is suitable for real-time missions based on a visibility graphs search is an A* algorithm [13].…”