Planning-oriented Autonomous Driving

🤖 Plain-English Summary

Modern autonomous driving system is characterized as modular tasks in sequential order, i.e., perception, prediction, and planning. We instantiate UniAD on the challenging nuScenes benchmark.

🔑 Key Findings

• In order to perform a wide diversity of tasks and achieve advanced-level intelligence, contemporary approaches either deploy standalone models for individual tasks, or design a multi-task paradigm with separate heads.
• However, they might suffer from accumulative errors or deficient task coordination.
• Instead, we argue that a favorable framework should be devised and optimized in pursuit of the ultimate goal, i.e., planning of the self-driving car.

🔗 Related Resources