A multimodality fusion deep neural network and safety test strategy for intelligent vehicles
Multimodality fusion based on deep neural networks (DNN) is a significant method for
intelligent vehicles. The special characteristics of DNN lead to the issue of AI safety and …
intelligent vehicles. The special characteristics of DNN lead to the issue of AI safety and …
Small-shot Multi-modal Distillation for Vision-based Autonomous Steering
In this paper, we propose a novel learning framework for autonomous systems that uses a
small amount of “auxiliary information” that complements the learning of the main modality …
small amount of “auxiliary information” that complements the learning of the main modality …
End-to-end driving model based on deep learning and attention mechanism
W Zhu, Y Lu, Y Zhang, X Wei… - Journal of Intelligent & …, 2022 - content.iospress.com
End-to-end deep learning has gained considerable interests in autonomous driving
vehicles. End-to-end autonomous driving uses the deep convolutional neural network to …
vehicles. End-to-end autonomous driving uses the deep convolutional neural network to …
FlowDriveNet: An end-to-end network for learning driving policies from image optical flow and LiDAR point flow
Learning driving policies using an end-to-end network has been proved a promising
solution for autonomous driving. Due to the lack of a benchmark driver behavior dataset that …
solution for autonomous driving. Due to the lack of a benchmark driver behavior dataset that …
Spatio-Temporal Ultrasonic Dataset: Learning Driving from Spatial and Temporal Ultrasonic Cues
S Wang, J Qin, Z Zhang - 2020 IEEE/RSJ International …, 2020 - ieeexplore.ieee.org
Recent works have proved that combining spatial and temporal visual cues can significantly
improve the performance of various vision-based robotic systems. However, for the …
improve the performance of various vision-based robotic systems. However, for the …