Toward explainable and advisable model for self-driving cars

Jinkyu Kim, Anna Rohrbach, Zeynep Akata, Suhong Moon, Teruhisa Misu, Yi Ting Chen, Trevor Darrell, John Canny

Research output: Contribution to journalLetterpeer-review

15 Citations (Scopus)

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.

Original languageEnglish
Article numbere56
JournalApplied AI Letters
Volume2
Issue number4
DOIs
Publication statusPublished - 2021 Dec

Bibliographical note

Publisher Copyright:
© 2021 The Authors. Applied AI Letters published by John Wiley & Sons Ltd.

Keywords

  • advisable AI
  • eXplainable AI
  • self-driving vehicles

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Toward explainable and advisable model for self-driving cars'. Together they form a unique fingerprint.

Cite this