Research Log

Writing on autonomous vehicles, motion forecasting, LiDAR perception, and ML systems engineering.

Filter:
2025
Jan 15
Wayformer: Rethinking Motion Forecasting with Efficient Attention
A deep-dive into the Wayformer architecture — how factorized attention over agents and scene context achieves state-of-the-art trajectory prediction while staying practical for production AV stacks.
~5 min Motion Forecasting Autonomous Driving Transformer Deep Learning
2024
Nov 10
Polar Space LiDAR: Why Coordinate Systems Are a Design Choice
How switching from Cartesian to polar coordinates for LiDAR point cloud processing cuts latency by 2× without hurting accuracy — and the non-obvious trade-offs involved.
~5 min LiDAR 3D Detection Autonomous Driving Deep Learning
Aug 20
Neural Rendering for Autonomous Vehicle Simulation
How NeRF-based scene representations are replacing hand-crafted 3-D asset pipelines in AV simulation — what we built at Rivian, and where the method still breaks down.
~5 min Generative AI Autonomous Driving Deep Learning Robotics