We conduct research on algorithms, hardware and software systems that enable sensing, (semi) autonomous operation and decision making across a range of real-world domains, such as UAVs and robotics
The UCL-CS Autonomous Systems group conducts research on theoretical, computational and experimental aspects of autonomous systems.
Our research in machine learning, reinforcement learning, and vision develops novel theoretical methods that act as fundamental technology enablers of autonomous systems.
We then deploy these methods on real systems (that we sometime fabricate), and investigate how to make them work when operating in unconstrained real world settings.
In so doing, we explore and tackle challenges that emerge both in robot-people interactions (e.g., collaborative decision making, explainable AI, affective robots) and in robot-environment interactions (e.g., sensing, control, mapping, swarms).
We are concerned with a broad variety of real-world problems autonomous systems can contribute to, from surgical robots to space missions, from emergency response to advanced decision-making.
- Legged robot navigation in unstructured terrain
- Fault recovery in autonomous robotic space operations
- Hand-eye calibration for robotic-assisted minimally invasive surgery
- Algorithmic policy-making