<ul><li>Study on scaling laws of encoder-decoder autoregressive transformer models for motion forecasting and planning in autonomous driving domain.</li><li>Model performance improves with total compute budget following a power-law function, similar to language modeling, with a correlation between training loss and evaluation metrics.</li><li>Closed-loop metrics also improve with scaling, impacting the suitability of open-loop metrics for model development and hill climbing.</li><li>Optimal scaling of transformer parameters and training data size shows the need to increase model size faster than dataset size as the training compute budget grows.</li></ul>

Scaling Laws of Motion Forecasting and Planning -- A Technical Report

Discover more