補助監督で学ぶエンドツーエンド自動運転
Learning End-to-end Autonomous Driving using Guided Auxiliary Supervision
視覚的アフォーダンスと行動プリミティブを補助タスクとして同時予測させるマルチタスク学習により、CARLA上のエンドツーエンド自動運転の学習効率と性能・透明性を向上させた研究。
著者: Ashish Mehta, Adithya Subramanian, Anbumani Subramanian
分類: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML
原文アブストラクト
Learning to drive faithfully in highly stochastic urban settings remains an open problem. To that end, we propose a Multi-task Learning from Demonstration (MT-LfD) framework which uses supervised auxiliary task prediction to guide the main task of predicting the driving commands. Our framework involves an end-to-end trainable network for imitating the expert demonstrator's driving commands. The network intermediately predicts visual affordances and action primitives through direct supervision which provide the aforementioned auxiliary supervised guidance. We demonstrate that such joint learning and supervised guidance facilitates hierarchical task decomposition, assisting the agent to learn faster, achieve better driving performance and increases transparency of the otherwise black-box end-to-end network. We run our experiments to validate the MT-LfD framework in CARLA, an open-source urban driving simulator. We introduce multiple non-player agents in CARLA and induce temporal noise in them for realistic stochasticity.
