Task Allocation

Multi-Role Goal Assignment MRGA which enables for more efficient computation of plans using temporal planners. The approach allocates a mission’s goals based on robot capabilities, the redundancy of the sensor system, the spatial distribution of the goals and task implementation time, avoiding the need to compute a large number of possible assignments.

Decentralised Heterogeneous Robot Task Allocator DHRTA which distributes goals (in a decentralised manner) in a heterogeneous fleet considering, goals makespan, goals position, robot capabilities (example can be found here).

Robotic Frameworks for Task Planning

Task Planning & UUV_Simulator TP-UUV Framework that allows the implementation of multi-robot missions in the underwater domain. This project present a Digital Twin for Inpection, Planning and Intervention (some description can be found here)

Task Planning & ORCA Sim ORCA-TAP Framework that allows the implementation of multi-robot missions in the in the ORCA Hub simulator, which is a ROS-enabled oil rig environment composed of four Autonomous Robot for Gas and Oil Sites (ARGOS) rescue scenario towers. The task planning framework deals with the following robots: Quadcopter and Husky, a medium size robot with large payload capabilities.

Online Planning, Plan Deviation and Execution

Plan refinement/adaptation while feeding into simulations and anomaly detection required for self-certification. To enable the offshore industry to certify the integrity of structures via frequent surveying and accurate 3D modelling, we are working to increase the accuracy of robotic mapping systems to the optimal standard that the industry requires using multiple AI plannining solutions (using BlueRov, Falcon and SonarBot platforms).