Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain knowledge by observing human drivers. This eliminates the need for human engineers to anticipate what is important in an image and foresee all the necessary rules for safe driving. Road tests demonstrated that PilotNet can successfully perform lane keeping in a wide variety of driving conditions, regardless of whether lane markings are present or not. The goal of the work described here is to explain what PilotNet learns and how it makes its decisions. To this end we developed a method for determining which elements in the road image most influence PilotNet's steering decision. Results show that PilotNet indeed learns to recognize relevant objects on the road. In addition to learning the obvious features such as lane markings, edges of roads, and other cars, PilotNet learns more subtle features that would be hard to anticipate and program by engineers, for example, bushes lining the edge of the road and atypical vehicle classes.
Code (8)
Tasks
Autonomous DrivingSelf-Driving CarsSimilar Papers 제목 키워드 기반
SteerSeg: Attention Steering for Reasoning Video Segmentation
Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-la…
Video SegmentationSpatial ReasoningText GenerationWord Embeddings Are Steers for Language Models
Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model g…
Language ModelingLanguage ModellingWord EmbeddingsOptimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers. Central to our method is an optimization framework that modifies an instance so that the…
Explaining Predictive Uncertainty by Looking Back at Model Explanations
Predictive uncertainty estimation of pre-trained language models is an important measure of how likely people can trust their predictions. However, little is known about what makes a model prediction uncertain. Explainin…
Decision MakingNatural Language InferenceParaphrase IdentificationPrediction+1A Rate-Distortion Framework for Explaining Black-box Model Decisions
We present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions. The framework is based on perturbations of the target input signal and applies to…
Physical Simulations