What Matters to Enhance Traffic Rule Compliance of Imitation Learning for Automated Driving

by   Hongkuan Zhou, et al.
HUAWEI Technologies Co., Ltd.

More research attention has recently been given to end-to-end autonomous driving technologies where the entire driving pipeline is replaced with a single neural network because of its simpler structure and faster inference time. Despite this appealing approach largely reducing the components in driving pipeline, its simplicity also leads to interpretability problems and safety issues arXiv:2003.06404. The trained policy is not always compliant with the traffic rules and it is also hard to discover the reason for the misbehavior because of the lack of intermediate outputs. Meanwhile, Sensors are also critical to autonomous driving's security and feasibility to perceive the surrounding environment under complex driving scenarios. In this paper, we proposed P-CSG, a novel penalty-based imitation learning approach with cross semantics generation sensor fusion technologies to increase the overall performance of End-to-End Autonomous Driving. We conducted an assessment of our model's performance using the Town 05 Long benchmark, achieving an impressive driving score improvement of over 15 evaluations against adversarial attacks like FGSM and Dot attacks, revealing a substantial increase in robustness compared to baseline models.More detailed information, such as code-based resources, ablation studies and videos can be found at https://hk-zh.github.io/p-csg-plus.


page 1

page 3

page 6


Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving

With the rapid development of Pattern Recognition and Computer Vision te...

Explaining Autonomous Driving by Learning End-to-End Visual Attention

Current deep learning based autonomous driving approaches yield impressi...

NEAT: Neural Attention Fields for End-to-End Autonomous Driving

Efficient reasoning about the semantic, spatial, and temporal structure ...

TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving

How should we integrate representations from complementary sensors for a...

Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey

End-to-End driving is a promising paradigm as it circumvents the drawbac...

Exploring the Limitations of Behavior Cloning for Autonomous Driving

Driving requires reacting to a wide variety of complex environment condi...

Multi-task Learning with Attention for End-to-end Autonomous Driving

Autonomous driving systems need to handle complex scenarios such as lane...

Please sign up or login with your details

Forgot password? Click here to reset