Enabling Swarms and Multi Robot Systems
Location: DST Fisherman’s Bend, VIC
Duration: 5 months
Proposed start date: January 2020 (or earlier)
Please note: Due to the sensitivity and security of this project, students must have Australian Citizenship to apply. Any applicants not meeting this requirement will automatically be deemed ineligible for this project.
The Advanced Vehicle Systems (AVS) group of Land Division (LD), DST conducts research and innovates in the multi-disciplinary field of self-managing vehicle-hosted mission systems. A current area of research focus addresses the coordination of multi unmanned autonomous system deployments or swarms. Such swarms are required to coordinate amongst themselves to best achieve a task (e.g. surveillance or provide communication links) and dynamically adapt their formation and allocation to changes in the environment in which they operate. The selected candidate will join a team working both with DST scientists and academia to research and demonstrate such technology.
Research to be Conducted
Research will be carried out in the areas of:
- Formation control approaches and path traversal within such formations to ensure a swarm deployment can effectively traverse an area
- Task allocation to allow a swarm with multiple objectives to appropriately and effectively allocate members of the swarm to perform those tasks noting the assumption of heterogeneity in individual swarm member capability.
- Distributed decision-making approaches to enable task allocation in a scalable and communications efficient manner.
- Swarm adaptability to enable the ability to deal with changes in the environment for all of the above research areas.
Preferred candidates will require a strong background in either area of control systems, robotics, computer science, or other related sciences. The projects will involve programming and implementation of the swarm algorithms using python and or Java based simulation environments and then transition towards the Robot Operating System (ROS) and the Gazebo environment. Prior experience with these software frameworks and languages is desirable.
We are looking for a PhD student with the following:
- Multi robot system / swarm behaviour control
- Experience with either task allocation or distributed decision-making approaches.
- Experience with the simulation of multi robot systems (in a high order programming language)
- Experience in optimisation
- Experience in computational intelligence approaches
- Familiarity with the ROS/Gazebo environment
It is expected that the research will result in software artefacts which will be demonstrated in simulation. The experimentation will be of sufficient quality to validate the approaches for use in robotic systems. The results of this experimentation are to be documented in a research paper of sufficient quality for publication at a high-ranking robotics, control, or multi agent systems conference.
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
6 November 2019
APR – 1080