Explainable deep learning improves human mental models of self-driving cars
Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. However, the opacity of such black-box motion planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with potentially catastrophic consequences. Here, we introduce concept-wrapper network (i.e., CW-Net), a method for explaining the behavior of black-box motion planners by grounding their reasoning in human-interpretable concepts. We deploy CW-Net on a real self-driving car and show that the resulting explanations refine the human driver's mental model of the car, allowing them to better predict its behavior and adjust their own behavior accordingly. Unlike previous work using toy domains or simulations, our study presents the first real-world demonstration of how to build authentic autonomous vehicles (AVs) that give interpretable, causally faithful explanations for their decisions, without sacrificing performance. We anticipate our method could be applied to other safety-critical systems with a human in the loop, such as autonomous drones and robotic surgeons. Overall, our study suggests a pathway to explainability for autonomous agents as a whole, which can help make them more transparent, their deployment safer, and their usage more ethical.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous VehiclesSelf-Driving CarsSimilar Papers 제목 키워드 기반
Beyond Fixed Thresholds and Domain-Specific Benchmarks for Explainable Multi-Task Classification in Autonomous Vehicles
Scene understanding is a vital part of autonomous driving systems, which requires the use of deep learning models. Deep learning methods are intrinsically black box models, which lack transparency and safety in autonomou…
Autonomous VehiclesScene UnderstandingAutonomous DrivingHuman-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language Models
Achieving full automation in self-driving vehicles remains a challenge, especially in dynamic urban environments where navigation requires real-time adaptability. Existing systems struggle to handle navigation plans when…
Autonomous DrivingAutonomous NavigationAutonomous VehiclesDME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving
In the field of autonomous driving, two important features of autonomous driving car systems are the explainability of decision logic and the accuracy of environmental perception. This paper introduces DME-Driver, a new …
Autonomous DrivingLanguage ModelingLanguage ModellingSelf-Driving CarsDevelopment and testing of an image transformer for explainable autonomous driving systems
In the last decade, deep learning (DL) approaches have been used successfully in computer vision (CV) applications. However, DL-based CV models are generally considered to be black boxes due to their lack of interpretabi…
Autonomous DrivingDiagnosticSelf-Driving like a Human driver instead of a Robocar: Personalized comfortable driving experience for autonomous vehicles
This paper issues an integrated control system of self-driving autonomous vehicles based on the personal driving preference to provide personalized comfortable driving experience to autonomous vehicle users. We propose a…
Autonomous Vehicles