Browse Topic: Automated driving systems
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 implementation in order to comment on its validity.
This concept for an Aeronautical Design Standard for autonomous systems is methodology to determine the acceptable level of supervision for autonomy in military systems. The level of autonomy is directly related to the level of supervision required for the trust in the autonomous system functionality. The approach defines representative Autonomous Task Elements (ATEs), operational considerations, and levels of autonomy. Each ATE is characterized by an objective, description, and performance standards. Performance standards are expressed as metrics related to the trust in the autonomous behavior and the system’s capability to conduct the ATE. The capability of the autonomous system to meet performance standards is expressed as risk. This risk is compared to specified operational / allowable limits. The corresponding acceptable level of autonomy for the ATE is then determined using the probability of failure to meet the limits. The approach for this concept autonomy ADS parallels ADS 33E-PRF for the assignment of Levels of Handling Qualities based on measurable flight performance characteristics.
Over the last 100 years, the automobile has become integrated in a fundamental way into the broader economy. A broad and deep ecosystem has emerged, and critical components of this ecosystem include insurance, after-market services, automobile retail sales, automobile lending, energy suppliers (e.g., gas stations), medical services, advertising, lawyers, banking, public planners, and law enforcement. These components - which together represent almost $2 trillion of the U.S. economy - are in equilibrium based on the current capabilities of automotive technology. However, the advent of autonomous vehicles (AVs) and technologies like electrification have the potential to significantly disrupt the automotive ecosystem. The critical cog governing the rate and pace of this shift is the management of the test and verification of AVs. In this SAE EDGE™ report, six senior industry leaders in the impacted ecosystems essay articles which describe sectors of the current automotive ecosystem and the manner in which AV technology can potentially reshape them - providing a mosaic of the massive infrastructure shifts which will be required to absorb AV technologies. NOTE: SAE EDGE™ Research Reports are intended to identify and illuminate key issues in emerging, but still unsettled, technologies of interest to the mobility industry. The goal of SAE EDGE™ Research Reports is to stimulate discussion and work in the hope of promoting and speeding resolution of identified issues. SAE EDGE™ Research Reports are not intended to resolve the issues they identify or close any topic to further scrutiny. Click here to access the full SAE EDGETM Research Report portfolio.
Items per page:
50
1 – 50 of 178