Tag: Self-Driving Car
Searchable Ground Truth: Querying Uncommon Scenarios in Self-Driving Car Development
When developing Uber's self driving car systems, engineers found a way to identify edge case scenarios amongst terabytes of sensor data representing real-world situations.
SBNet: Leveraging Activation Block Sparsity for Speeding up Convolutional Neural Networks
Uber ATG Toronto developed Sparse Blocks Network (SBNet), an open source algorithm for TensorFlow, to speed up inference of our 3D vehicle detection systems while lowering computational costs.
Engineering a Million-Mile Journey with Uber ATG
Uber ATG's Poornima Kaniarasu shares how she found her "place" developing the machine learning technologies behind our self-driving vehicles.