Model-Based Reinforcement Learning for Time-Optimal Velocity Control

Gabriel Hartmann, Zvi Shiller, Amos Azaria

نتاج البحث: نشر في مجلةمقالةمراجعة النظراء

10 اقتباسات (Scopus)

ملخص

Autonomous navigation has recently gained great interest in the field of reinforcement learning. However, little attention was given to the time-optimal velocity control problem, i.e. controlling a vehicle such that it travels at the maximal speed without becoming dynamically unstable (roll-over or sliding). Time optimal velocity control can be solved numerically using existing methods that are based on optimal control and vehicle dynamics. In this letter, we develop a model-based deep reinforcement learning to generate the time-optimal velocity control. Moreover, we introduce a method that uses a numerical solution that predicts whether the vehicle may become unstable and intervenes if needed. We show that our combined model outperforms several baselines as it achieves higher velocities (with only one minute of training) and does not encounter any failures during the training process.

اللغة الأصليةالإنجليزيّة
رقم المقال9149717
الصفحات (من إلى)6185-6192
عدد الصفحات8
دوريةIEEE Robotics and Automation Letters
مستوى الصوت5
رقم الإصدار4
المعرِّفات الرقمية للأشياء
حالة النشرنُشِر - أكتوبر 2020

بصمة

أدرس بدقة موضوعات البحث “Model-Based Reinforcement Learning for Time-Optimal Velocity Control'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا