Imagine a system with 30-50 unmanned vehicles (UXV), deployed for instance to detect survivors after an earthquake. Each UXV is continuously capturing video and other data. For situation awareness and the control of various entities, it is crucial for the human operators to be informed about the most important events in the field in real-time. In other words, the operators need to be informed of what matters when it matters.
We extract “events” from the data streams. In other words, each UXV reports a story of what it is seeing and experiencing, more generally. This will lead to lists of events. These lists would still be too long and convoluted for human operators to parse in real-time. Therefore, further filtering is required. The proposed system will prioritize the events to be reported to the human operator, according to the tasks at hand.
Since the mission and hence individual tasks may change on the fly, the prioritizing of the events needs to be adaptive and real-time. For important events (such as detection of survivors, enemy targets, dangerous situations, etc.), the operator can be alarmed and the raw video footage and other data streams can be shown from the relevant UXV.
More specifically, in this project we have the following aims:
• Develop algorithms for real-time data streaming for heterogeneous UXVs
• Developing UI for operator
• Writing technical documents and user guides.
The research fellow will assist in conducting this research, writing journal publications, and preparing grant applications.
The candidate should have a PhD in Electrical Engineering, Industrial Engineering or Statistics
Required skills include:
• Signal processing
• Machine learning
• Data modelling
• Design of unmanned vehicles
Interested applicants may send his/her CV and supporting information to:
Asst Prof Justin Dauwels
School of Electrical & Electronic Engineering
Nanyang Technological University
50 Nanyang Avenue
E-mail Address for E-mailed Applications: JDAUWELS@ntu.edu.sg
Electronic submission of application is highly encouraged.
Only short-listed candidates will be notified for interview. Application closes when the positions are filled.