Toward explainable and advisable model for self‐driving cars. Issue 4 (30th December 2021)

• Record Type: Journal Article
• Authors: Kim, Jinkyu; Rohrbach, Anna; Akata, Zeynep; Moon, Suhong; Misu, Teruhisa; Chen, Yi‐Ting; Darrell, Trevor; Canny, John
• Other Names: Gunning Dave guestEditor.; Vorm Eric guestEditor.; Wang Jennifer Yunyan guestEditor.; Turek Matt guestEditor.
• Is Part Of: Applied AI Letters. Volume 2:Issue 4(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-12-30
• Subjects: advisable AI -- eXplainable AI -- self‐driving vehicles; 006.3
• DOI: 10.1002/ail2.56
• Languages: English
• ISSNs: 2689-5595

Abstract

Abstract: Humans learn to drive through both practice and theory, for example, by studying the rules, while most self‐driving systems are limited to the former. Being able to incorporate human knowledge of typical causal driving behavior should benefit autonomous systems. We propose a new approach that learns vehicle control with the help of human advice. Specifically, our system learns to summarize its visual observations in natural language, predict an appropriate action response (eg, "I see a pedestrian crossing, so I stop"), and predict the controls, accordingly. Moreover, to enhance the interpretability of our system, we introduce a fine‐grained attention mechanism that relies on semantic segmentation and object‐centric RoI pooling. We show that our approach of training the autonomous system with human advice, grounded in a rich semantic representation, matches or outperforms prior work in terms of control prediction and explanation generation. Our approach also results in more interpretable visual explanations by visualizing object‐centric attention maps. We evaluate our approach on a novel driving dataset with ground‐truth human explanations, the Berkeley DeepDrive eXplanation (BDD‐X) dataset. Abstract : Towards learning more human‐like driving behavior, we propose to use human advice in the form of observation‐action rules.