Research

Share    

Peer-to-peer synchronisation

Objective

To develop algorithms that address peer-to-peer model of collaboration with mobility, communication and sensing/processing constraints.


Description

Machine collaboration concepts have been extended to UAVs in order to search and prosecute targets in an area, where the positions of the targets are unknown to the UAVs. The major challenge in trajectory planning of multiple UAVs is that the planning of individual agent cannot be independent from other agents’ planning, as trajectories generated by agents intended for independent exhaustive coverage may yield redundancy. The proposed cognitive team theoretic solution aims to minimise predefined cost like fuel and time needed in locating the target. This method has been exclusively proposed to deal with the practical scenario, where the UAVs are predisposed to communication constraints due to the limitation in sensor detection range.


Simulation Result

                     
              Multi-agent search problem with 4 targets and 4 agents that cover a search area of 100 x 100  



Video Demonstration





Principal Investigators


Associate Prof. Suresh Sundaram (NTU)

Telephone: 6790 6185
Office: N4-02b-45
Email: ssundaram@ntu.edu.sg
Mr. Paul Tan (STE)

Telephone: 6660 1052
Office: S1-B4a-03
Email: paultan@stengg.com