The excerpt note is about the novel approach of learning to navigate proposed by DeepMind research team in past few period of time.

How did you learn to navigate the neighborhood of your childhood, to go to a friend’s house, to your school or to the grocery store? Probably without a map and simply by remembering the visual appearance of streets and turns along the way. As you gradually explored your neighborhood, you grew more confident, mastered your whereabouts and learned new and increasingly complex paths. You may have gotten briefly lost, but found your way again thanks to landmarks, or perhaps even by looking to the sun for an impromptu compass.

Navigation is an important cognitive task that enables humans and animals to traverse, without maps, over long distances in a complex world. Such long-range navigation can simultaneously support self-localisation (“I am here”) and a representation of the goal (“I am going there”).

DeepMind Research Team has published several papers about learning to navigate. Their approach departs from the traditional approaches which rely on explicit mapping and exploration (like a cartographer who tries to localise themselves and draw a map at the same time). Their approach, in contrast, is to learn to navigate as humans used to do, without maps, GPS localisation, or other aids, using only visual observations. They build a neural network agent that inputs images observed from the environment and predicts the next action it should take in that environment. 

For further info, please read the following references.

Andrea Banino, Caswell Barry, Benigno Uria, Charles Blundell, Timothy Lillicrap, Piotr Mirowski, Alexander Pritzel, Martin J. Chadwick, Thomas Degris, Joseph Modayil, Greg Wayne, Hubert Soyer, Fabio Viola, Brian Zhang, Ross Goroshin, Neil Rabinowitz, Razvan Pascanu, Charlie Beattie, Stig Petersen, Amir Sadik, Stephen Gaffney, Helen King, Koray Kavukcuoglu, Demis Hassabis, Raia Hadsell & Dharshan Kumaran. Vector-based navigation using grid-like representations in artificial agents. Nature (2018), doi:10.1038/s41586-018-0102-6. 

Mirowski, Piotr, Matthew Koichi Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, and Raia Hadsell. “Learning to Navigate in Cities Without a Map.” arXiv preprint arXiv:1804.00168 (2018).

Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap. “Unsupervised Predictive Memory in a Goal-Directed Agent.” arXiv preprint arXiv:1803.10760 (2018).

Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell. “Learning to navigate in complex environments.” arXiv preprint arXiv:1611.03673 (2016).

Further Reading

Learning to drive in a day by Wayve.AI at Blog of Wayve.ai

The first example of reinforcement learning on-board an autonomous car. 

Do you remember learning to ride a bicycle as a child? Excited and mildly anxious, you probably sat on a bicycle for the first time and pedalled while an adult hovered over you, prepared to catch you if you lost balance. After some wobbly attempts, you perhaps managed to balance for a few metres. Several hours in, you probably were zipping around the park on gravel and grass alike.

The adult would have only given you brief tips along the way. You did not need a dense 3D map of the park nor a high fidelity laser on your head. You did not need a long list of rules to follow to be able to balance on the bicycle. The adult simply gave you a safe environment for you to learn how to map what you see to what you should do, to successfully ride a bicycle.

Today’s self-driving cars have been packed with a large array of sensors, and are told how to drive with a long list of carefully hand-engineered rules through slow development cycles. In this blogpost, they go back to basics, and let a car learn to follow a lane from scratch, with clever trial and error, much like how you learnt to ride a bicycle.

For more info, please read the blog at https://wayve.ai/blog/learning-to-drive-in-a-day-with-reinforcement-learning 

Learning to Drive in a Day. https://arxiv.org/pdf/1807.00412.pdf