Research Assistant or Research Associate in Robot Learning and Fast Recovery

The Adaptive and Intelligent Robotics Lab (AIRL) in the Department of Computing at Imperial College London is seeking a talented Research Associate (post-doc) or Research Assistant (pre-doc) to work on a new project called TRUSTLINE, which is part of the Learning Introspective Control (LINC) DARPA Program. The project aims to develop machine learning (ML)--based introspection and monitoring technologies that enable robotic systems and critical infrastructures to detect and understand ongoing situations as they encounter uncertainty or unexpected events. The program also seeks to develop technologies to communicate these changes to a human or AI operator while retaining operator confidence and ensuring continuity of operations. The successful applicant will focus on developing and testing new methods to improve the deployment, adaptation capabilities and safety of robots and critical infrastructures. The developed algorithms will be evaluated on legged robots, wheel-based robots and under-actuated large-scale manipulators (., container cranes).

For further information on Dr Antoine Cully’s research and projects, see

This project will be achieved by combining state-of-the-art algorithms from multiple domains such as evolutionary algorithms, reinforcement learning, and control theory. Familiarity with existing methods from these domains, such as Quality-Diversity algorithms, reinforcement learning, model predictive control, parallel computing using JAX and rapid online learning, is highly desirable, but candidates demonstrating an ability and willingness to become familiar with these topics and able to contribute to them will also be considered. This project has a strong emphasis on applications on physical robots, experience and appetite to face the challenge of applying learning algorithms on physical robots are therefore required. One of the goals of this project is to commercialise the developed technology. Therefore, an entrepreneurial mindset and willingness to take challenges is a plus.

You must have a strong computer science background and have experience in one or more of the following areas: Robotics, Evolutionary Computation, Deep Reinforcement Learning, and Machine Learning. This should include a proven publication track record.

You should also have:

Please see job description for a full list of requirements.

*Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant, salary range £43,003 - £46,297 per annum.