Paper Reading AI Learner

Evaluation of Teleoperation Concepts to solve Automated Vehicle Disengagements

2024-04-23 13:35:50
David Brecht, Nils Gehrke, Tobias Kerbl, Niklas Krauss, Domagoj Majstorovic, Florian Pfab, Maria-Magdalena Wolf, Frank Diermeyer

Abstract

Teleoperation is a popular solution to remotely support highly automated vehicles through a human remote operator whenever a disengagement of the automated driving system is present. The remote operator wirelessly connects to the vehicle and solves the disengagement through support or substitution of automated driving functions and therefore enables the vehicle to resume automation. There are different approaches to support automated driving functions on various levels, commonly known as teleoperation concepts. A variety of teleoperation concepts is described in the literature, yet there has been no comprehensive and structured comparison of these concepts, and it is not clear what subset of teleoperation concepts is suitable to enable safe and efficient remote support of highly automated vehicles in a broad spectrum of disengagements. The following work establishes a basis for comparing teleoperation concepts through a literature overview on automated vehicle disengagements and on already conducted studies on the comparison of teleoperation concepts and metrics used to evaluate teleoperation performance. An evaluation of the teleoperation concepts is carried out in an expert workshop, comparing different teleoperation concepts using a selection of automated vehicle disengagement scenarios and metrics. Based on the workshop results, a set of teleoperation concepts is derived that can be used to address a wide variety of automated vehicle disengagements in a safe and efficient way.

Abstract (translated)

遥控操作是通过一个远程操作员来支持高度自动化车辆的常见解决方案,在任何自动驾驶系统断开的情况下,都可以通过支持或替代自动驾驶功能来解决断开问题,从而使车辆重新进入自动化。在支持自动驾驶功能的不同级别上有不同的方法,通常称为遥控概念。文献中描述了各种遥控概念,然而,还没有对这些概念进行全面的结构比较,而且不清楚哪些遥控概念适合在广泛的断开范围内安全有效地支持高度自动化车辆。以下工作为比较遥控概念提供了一个基础,通过对自动驾驶断开和已经进行的研究进行文献回顾,对遥控概念和评价遥控性能的指标进行比较。在专家研讨会中,通过选择不同的自动驾驶断开场景和指标,对遥控概念进行评估。根据研讨会结果,得出了一组适用于各种自动驾驶断开的安全高效的遥控概念。

URL

https://arxiv.org/abs/2404.15030

PDF

https://arxiv.org/pdf/2404.15030.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot