Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues

Abstract

In recent years, autonomous driving algorithms using low-cost vehicle-mounted cameras have attracted increasing endeavors from both academia and industry. There are multiple fronts to these endeavors, including object detection on roads, 3-D reconstruction etc., but in this work we focus on a vision-based model that directly maps raw input images to steering angles using deep networks. This represents a nascent research topic in computer vision. The technical contributions of this work are three-fold. First, the model is learned and evaluated on real human driving videos that are time-synchronized with other vehicle sensors. This differs from many prior models trained from synthetic data in racing games. Second, state-of-the-art models, such as PilotNet, mostly predict the wheel angles independently on each video frame, which contradicts common understanding of driving as a stateful process. Instead, our proposed model strikes a combination of spatial and temporal cues, jointly investigating instantaneous monocular camera observations and vehicle's historical states. This is in practice accomplished by inserting carefully-designed recurrent units (e.g., LSTM and Conv-LSTM) at proper network layers. Third, to facilitate the interpretability of the learned model, we utilize a visual back-propagation scheme for discovering and visualizing image regions crucially influencing the final steering prediction. Our experimental study is based on about 6 hours of human driving data provided by Udacity. Comprehensive quantitative evaluations demonstrate the effectiveness and robustness of our model, even under scenarios like drastic lighting changes and abrupt turning. The comparison with other state-of-the-art models clearly reveals its superior performance in predicting the due wheel angle for a self-driving car.

12 pages, 15 figures

Cited by in corpus (15)

• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
• F1/10: An Open-Source Autonomous Cyber-Physical Platform
• Learned Visual Navigation for Under-Canopy Agricultural Robots
• End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perception
• Rethinking Self-driving: Multi-task Knowledge for Better Generalization and Accident Explanation Ability
• Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
• Affordance-based Reinforcement Learning for Urban Driving
• Learning predictive representations in autonomous driving to improve deep reinforcement learning
• Cost-effective Interactive Attention Learning with Neural Attention Processes
• Ignition: An End-to-End Supervised Model for Training Simulated Self-Driving Vehicles
• Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
• N 2 C : Neural Network Controller Design Using Behavioral Cloning
• Feudal Steering: Hierarchical Learning for Steering Angle Prediction
• Learning robust driving policies without online exploration