Towards Scenario- and Capability-Driven Dataset Development and Evaluation: An Approach in the Context of Mapless Automated Driving

• URL: http://arxiv.org/abs/2404.19656v1
• Date: Tue, 30 Apr 2024 15:52:49 GMT
• Title: Towards Scenario- and Capability-Driven Dataset Development and Evaluation: An Approach in the Context of Mapless Automated Driving
• Authors: Felix Grün, Marcus Nolte, Markus Maurer,
• Abstract summary: This paper focuses on the process of dataset development for environment perception in automated driving. We propose a scenario- and capability-based approach to dataset development. Applying this methodology to a broad range of existing lane detection datasets, we identify significant limitations in current datasets.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The foundational role of datasets in defining the capabilities of deep learning models has led to their rapid proliferation. At the same time, published research focusing on the process of dataset development for environment perception in automated driving has been scarce, thereby reducing the applicability of openly available datasets and impeding the development of effective environment perception systems. Sensor-based, mapless automated driving is one of the contexts where this limitation is evident. While leveraging real-time sensor data, instead of pre-defined HD maps promises enhanced adaptability and safety by effectively navigating unexpected environmental changes, it also increases the demands on the scope and complexity of the information provided by the perception system. To address these challenges, we propose a scenario- and capability-based approach to dataset development. Grounded in the principles of ISO 21448 (safety of the intended functionality, SOTIF), extended by ISO/TR 4804, our approach facilitates the structured derivation of dataset requirements. This not only aids in the development of meaningful new datasets but also enables the effective comparison of existing ones. Applying this methodology to a broad range of existing lane detection datasets, we identify significant limitations in current datasets, particularly in terms of real-world applicability, a lack of labeling of critical features, and an absence of comprehensive information for complex driving maneuvers.

Related papers

• A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lighting [36.58899868946257]
  We present A-BDD, a large set of over 60,000 synthetically augmented images based on BDD100K. The dataset contains augmented data for rain, fog, overcast and sunglare/shadow with varying intensity levels. We provide evidence that data augmentations can play a pivotal role in closing performance gaps in adverse weather and lighting conditions.
  arXiv  Detail & Related papers  (2024-08-12T11:44:47Z)
• Reconsidering utility: unveiling the limitations of synthetic mobility data generation algorithms in real-life scenarios [49.1574468325115]
  We evaluate the utility of five state-of-the-art synthesis approaches in terms of real-world applicability. We focus on so-called trip data that encode fine granular urban movements such as GPS-tracked taxi rides. One model fails to produce data within reasonable time and another generates too many jumps to meet the requirements for map matching.
  arXiv  Detail & Related papers  (2024-07-03T16:08:05Z)
• A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook [24.691922611156937]
  We present an exhaustive study of 265 autonomous driving datasets from multiple perspectives. We introduce a novel metric to evaluate the impact of datasets, which can also be a guide for creating new datasets. We discuss the current challenges and the development trend of the future autonomous driving datasets.
  arXiv  Detail & Related papers  (2024-01-02T22:35:33Z)
• Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future [130.87142103774752]
  This review systematically assesses over seventy open-source autonomous driving datasets. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets. It also delves into the scientific and technical challenges that warrant resolution.
  arXiv  Detail & Related papers  (2023-12-06T10:46:53Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• TII-SSRC-23 Dataset: Typological Exploration of Diverse Traffic Patterns for Intrusion Detection [0.5261718469769447]
  Existing datasets often fall short, lacking the necessary diversity and alignment with the contemporary network environment. This paper introduces TII-SSRC-23, a novel and comprehensive dataset designed to overcome these challenges.
  arXiv  Detail & Related papers  (2023-09-14T05:23:36Z)
• A Survey on Datasets for Decision-making of Autonomous Vehicle [11.556769001552768]
  Decision-making is one of the critical modules toward high-level automated driving. Data-driven decision-making approaches have aroused more and more focus. This study compares the state-of-the-art datasets of vehicle, environment, and driver related data.
  arXiv  Detail & Related papers  (2023-06-29T08:42:18Z)
• LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting [65.71129509623587]
  Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning. However, the promising results achieved on current public datasets may not be applicable to practical scenarios. We introduce the LargeST benchmark dataset, which includes a total of 8,600 sensors in California with a 5-year time coverage.
  arXiv  Detail & Related papers  (2023-06-14T05:48:36Z)
• Multimodal Dataset from Harsh Sub-Terranean Environment with Aerosol Particles for Frontier Exploration [55.41644538483948]
  This paper introduces a multimodal dataset from the harsh and unstructured underground environment with aerosol particles. It contains synchronized raw data measurements from all onboard sensors in Robot Operating System (ROS) format. The focus of this paper is not only to capture both temporal and spatial data diversities but also to present the impact of harsh conditions on captured data.
  arXiv  Detail & Related papers  (2023-04-27T20:21:18Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)
• Deep learning for radar data exploitation of autonomous vehicle [0.0]
  This thesis focuses on the on automotive RADAR, which is a low-cost active sensor measuring properties of surrounding objects. The RADAR sensor is seldom used for scene understanding due to its poor angular resolution, the size, noise, and complexity of RADAR raw data. This thesis proposes an extensive study of RADAR scene understanding, from the construction of an annotated dataset to the conception of adapted deep learning architectures.
  arXiv  Detail & Related papers  (2022-03-15T16:19:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.