To work on the ORCA PRF project “Towards the Accountable and Explainable Learning-enabled Autonomous Robotic Systems (AELARS)”.
This RA/SRA position is funded by Partnership Resource Funding from Offshore Robotics for the Certification of Assets (ORCA) Hub. ORCA Hub is managed by the Edinburgh Centre for Robotics (Heriot-Watt University and University of Edinburgh). The Hub develops Robotics, Artificial Intelligence and Autonomous Systems for the offshore sector.
This specific ORCA PRF project aims to unleash the power of deep learning on safety-critical robotic systems in a safe, controllable and interpretable way. Solutions based on deep learning are now also widely deployed in real-world robotic systems, from environment perception to real-time planning and navigation. Unfortunately, the black-box nature and instability of deep neural networks is raising concerns about the readiness of this technology applied in safety-critical robotic systems. This project intends to bridge such a research gap. Specifically, this project has two goals. One is on the algorithmic level, which will develop a series of safety verification and testing techniques that can guarantee deep learning models to output robust and explainable decisions with respect to any adversarial perturbations. Another goal is on the application level, which aims to design and implement the developed algorithms and tools on a real-world robotic platform so that the proposed robust deep learning models can be practically workable on robotic systems for various safety-critical missions.
The media report about this project can be found here:
https://www.lancaster.ac.uk/news/lancaster-researchers-to-tackle-the-mysteries-of-the-ai-black-box-problem.
We invite applications from enthusiastic individuals with experience in human-robot interaction, autonomous systems, intelligent perception, machine learning or deep learning, robotics, and computer vision. This project is expected to produce practical methodology, tools, and demonstrations, in order to provide guidance to the industrial development of safe and accountable robotic systems. Therefore, you should possess excellent ROS or related programming skills, know how to implement algorithms (e.g., learning-based perception methods) in a robotic system (such as TurtleBot).
The School of Computing and Communications offers a highly inclusive and stimulating environment for research career development. You will join an ambitious research group that is internationally recognised, and you will be expected to contribute to the already strong profile of the group by participation in the development and publication of research results.
This is a fixed term appointment until 28 Feb 2021. Informal enquiries please, to Dr Wenjie Ruan, email:
[email protected]We welcome applications from people in all diversity groups.
