Research @ A2I
The research we do at A2I spans a diverse range of application areas, from robot perception to reinforcement learning and learning from demonstration. Our focus lies on exploring fundamental challenges at the intersection of machine learning, AI, and robotics.
Here’s a closer look at some of the exciting work going on in the group…
Learn from Experience: Probabilistic Prediction of Perception Performance to Avoid Failure Abstract –Despite the significant advances in machine learning and perception over the past few decades, perception algorithms can still be unreliable when deployed in [...]
Learning Sparse Representations with CNNs for Efficient Object Detection in 3D Point Clouds Abstract – Convolutional neural networks (CNNs) have exhibited state-of-the-art performance across a number of domains, but have yet to realise the same success [...]
Classification precision and recall have been widely adopted by roboticists as canonical metrics to quantify the performance of learning algorithms. This paper advocates that for robotics applications, which often involve mission-critical decision making, good performance [...]