Workshop on AI for Autonomous Driving (AIAD)
Self-driving cars and advanced safety features present one of today’s greatest challenges and opportunities for Artificial Intelligence (AI). Despite billions of dollars of investments and encouraging progress under certain operational constraints, there are no driverless cars on public roads today without human safety drivers. Autonomous Driving research spans a wide spectrum, from modular architectures -- composed of hardcoded or independently learned sub-systems -- to end-to-end deep networks with a single model from sensors to controls. In any system, Machine Learning is a key component. However, there are formidable learning challenges due to safety constraints, the need for large-scale manual labeling, and the complex high dimensional structure of driving data, whether inputs (from cameras, HD maps, inertial measurement units, wheel encoders, LiDAR, radar, etc.) or predictions (e.g., world state representations, behavior models, trajectory forecasts, plans, controls). The goal of this workshop is to explore the frontier of learning approaches for safe, robust, and efficient Autonomous Driving (AD) at scale. The workshop will span both theoretical frameworks and practical issues especially in the area of deep learning.
In this paper, we describe our winning approach to solving the Lane Following Challenge at the AI Driving Olympics Competition through imitation learning on a mixed set of simulation and real-world data. AI Driving Olympics is a two-stage competition: at stage one, algorithms compete in a simulated environment with the best ones advancing to a real-world final. One of the main problems that participants encounter during the competition is that algorithms trained for the best performance in simulated environments do not hold up in a real-world environment and vice versa. Classic control algorithms also do not translate well between tasks since most of them have to be tuned to specific driving conditions such as lighting, road type, camera position, etc. To overcome this problem, we employed the imitation learning algorithm and trained it on a dataset collected from sources both from simulation and real-world, forcing our model to perform equally well in all environments.