Our brain can easily estimate the 3D position and the orientation of the objects we see. This task, however, is non-trivial for computers and robots. Computer scientists have been working on the problem of recovering the 3D position and orientation of objects in data captured from image sensors for years. This problem, formulated as the ‘pose estimation’ problem, is important because recovering the position and orientation of objects in a scene is often a necessary step to understanding the scene.

Remember when your piano teacher used to insist you practise your scales every single day? Turns out she wasn’t just being a tyrannical tormentor, but a firm believer in the old adage “practice makes perfect.”

In 1958, a curious sight began appearing on the sidewalks of California. People were taking apart roller skates, attaching them to the underside of wooden planks, sometimes boxes, and whizzing down the streets.

Mention “Bayesian Optimisation” to Professor Bryan Low Kian Hsiang and he begins to talk about baking cookies. That’s because to the uninitiated, concepts such as “distributed batch Gaussian process optimisation” and “decentralised high-dimensional Bayesian optimisation” can sound either downright intimidating or like pure gobbledygook.