Accurate trajectory prediction is crucial for safe and efficient autonomous driving, but handling partial observations presents significant challenges. To address this, we propose a novel trajectory prediction framework called Partial Observations Prediction (POP) for congested urban road scenarios. The framework consists of two stages: self-supervised learning (SSL) and feature distillation. In SSL, a reconstruction branch reconstructs the hidden history of partial observations using a mask procedure and reconstruction head. The feature distillation stage transfers knowledge from a fully observed teacher model to a partially observed student model, improving prediction accuracy. POP achieves comparable results to top-performing methods in open-loop experiments and outperforms the baseline method in closed-loop simulations, including safety metrics. Qualitative results illustrate the superiority of POP in providing reasonable and safe trajectory predictions.

Autonomous driving safety is in the development stage. Whether on the highway or in a multi-story parking garage, highly automated driving features must perform safely and reliably in all situations. Parallel systems monitor the environment and determine what to do in key conditions. This is called redundancy and is one of the ways developers from Porsche Engineering ensure safety in autonomous driving applications. The cargo of a truck in front of us is lost.

A startup company called Ghost has raised $100 million Series D financing, fueling the development of its autonomous driving system that features what it describes as "a revolutionary breakthrough in crash prevention". Returning investors Sutter Hill Ventures and Founders Fund participated in the round, along with a new commitment from Coatue. Ghost was founded in 2017 with the belief that driving should not be dangerous. Despite all the technology and features included in modern cars, cars still crash – accidents and fatalities are going up, not down. Even semi-autonomous and fully autonomous vehicles struggle to recognize and avoid every potential obstacle on the road, instead relying on human intervention to handle edge cases and prevent crashes.