Browse Topic: Big data
In this work, we present a lightweight pipeline for robust behavioral cloning of a human driver using end-to-end imitation learning. The proposed pipeline was employed to train and deploy three distinct driving behavior models onto a simulated vehicle. The training phase comprised of data collection, balancing, augmentation, preprocessing, and training a neural network, following which the trained model was deployed onto the ego vehicle to predict steering commands based on the feed from an onboard camera. A novel coupled control law was formulated to generate longitudinal control commands on the go based on the predicted steering angle and other parameters such as the actual speed of the ego vehicle and the prescribed constraints for speed and steering. We analyzed the computational efficiency of the pipeline and evaluated the robustness of the trained models through exhaustive experimentation during the deployment phase. We also compared our approach against state-of-the-art
Unsettled Topics in Automated Vehicle Data Sharing for Verification and Validation Purposes discusses the unsettled issue of sharing the terabytes of driving data generated by Automated Vehicles (AVs) on a daily basis. Perception engineers use these large datasets to analyze and model the automated driving systems (ADS) that will eventually be integrated into future “self-driving” vehicles. However, the current industry practices of collecting data by driving on public roads to understand real-world scenarios is not practical and will be unlikely to lead to safe deployment of this technology anytime soon. Estimates show that it could take 400 years for a fleet of 100 AVs to drive enough miles to prove that they are as safe as human drivers.Yet, data-sharing can be developed – as a technology, culture, and business – and allow for rapid generation and testing of the billions of possible scenarios that are needed to prove practicality and safety of an ADS – resulting in lower research
Items per page:
50
1 – 50 of 93