Waymo & DeepMind: How Evolutionary Selection Can Train More Capable Self-Driving Cars

The first experiments that DeepMind and Waymo collaborated on involved training a network that generates boxes around pedestrians, bicyclists, and motorcyclists detected by our sensors — named a “region proposal network.” The aim was to investigate whether PBT [Population Based Training] could improve a neural net’s ability to detect pedestrians along two measures: recall (the fraction of pedestrians identified by the neural net over total number of pedestrians in the scene) and precision (the fraction of detected pedestrians that are actually pedestrians, and not spurious “false positives”). Waymo’s vehicles detect these road users using multiple neural nets and other methods, but the goal of this experiment was to train this single neural net to maintain recall over 99%, while reducing false positives using population-based training.

PBT enabled dramatic improvements in model performance. For the experiment above, our PBT models were able to achieve higher precision by reducing false positives by 24% compared to its hand-tuned equivalent, while maintaining a high recall rate