Fig 6 - uploaded by Alexandru Sorici
Content may be subject to copyright.
Histograms of sensor measurements for the entire dataset. The Y axis represents the number of data points for each of the raw stream (sensors produce data at different rates). Note that we are using log scale.
Contexts in source publication
Context 1
... visualize_session.py -We use this tool after the session data has been processed for viewing several statistics such as those mentioned in Table I and Figure 6. Also the scrip visually replays all important dataset features while easily annotating important timestamps. ...
Similar publications
We present preliminary results on the reconstruction of the $B^0\to J\mskip 1mu / \psi\mskip 2mu K^0_{\scriptscriptstyle L}$ decay, where $J\mskip 1mu / \psi\mskip 2mu\to\mu^+\mu^-$ or $e^+e^-$. Using a dataset corresponding to a luminosity of $62.8\pm0.6\mbox{fb}^{-1}$ collected by the Belle II experiment at the SuperKEKB asymmetric energy $e^+e^-...
Citations
... UPB campus dataset: the UPB campus dataset [43] was collected on the streets belonging to the campus of University Politehnica of Bucharest and presented in a work focused on defining a guideline on collecting, processing and annotating a self-driving dataset. ...
... By weighting the five class equally, our model can forget about the actual trajectory distribution. UPB dataset [43] lacks of diversity in terms of intersection and curved roads, and we suspect that our model has difficulties in generalizing. We leave the analysis of other balancing strategies for future work. ...
... We have presented a fully self-supervised labeling pipeline for an autonomous driving dataset in the context of steering control and path labeling. We applied our method on two open-source driving datasets [43,44], and we proved the robustness and accuracy by achieving competitive results against the ground-truth labeling counterpart. Consequently, this shows that leveraging self-labeled data for learning a steering model can be almost as reliable as using the ground truth data. ...
Autonomous driving is a complex task that requires high-level hierarchical reasoning. Various solutions based on hand-crafted rules, multi-modal systems, or end-to-end learning have been proposed over time but are not quite ready to deliver the accuracy and safety necessary for real-world urban autonomous driving. Those methods require expensive hardware for data collection or environmental perception and are sensitive to distribution shifts, making large-scale adoption impractical. We present an approach that solely uses monocular camera inputs to generate valuable data without any supervision. Our main contributions involve a mechanism that can provide steering data annotations starting from unlabeled data alongside a different pipeline that generates path labels in a completely self-supervised manner. Thus, our method represents a natural step towards leveraging the large amounts of available online data ensuring the complexity and the diversity required to learn a robust autonomous driving policy.
... An interesting method for creating a dataset is presented in paper [8] which addresses the problem of Collecting and Processing a Self-Driving Dataset. In their paper, they provide a guideline going through all the steps from configuring the hardware setup to obtaining a clean dataset. ...
... We attempted to use different categories with a "top down" approach, based, e.g., on lifecycle stages, architectural levels or components, but those classifications did not match well with the coverage of papers we actually found, due to several factors, including heterogeneity in reference architectural models and immaturity of new V&V approaches for AVs, compared to more stable sectors such as avionics or railways (e.g., automatic train control), where those classifications work better. [2], [10], [29], [30], [52], [60], [66], [69], [71], [75], [87], [90], [91], [91], [100], [106] Test Case Definition and Generation [17], [25], [36], [40], [46], [51], [52], [54], [67], [72], [81], [86], [87], [100] Corner Cases and Adversarial Examples [8], [14], [18], [22], [24], [31], [32], [38], [41], [47]- [49], [53], [55], [85], [89], [95], [96], [102], [104], [105] Fault Injection [3], [4], [6], [15], [37], [62], [64] [73] [74], [92]- [94], [97], [103], [107] Mutation Testing [4], [50], [55], [58] Software Safety Cages [7], [68] Techniques for CPS [20], [21], [28], [35], [39], [56], [65], [76], [99] Formal Methods [16], [27], [34], [61], [63], [70], [79], [82], [87], [98], [99], [101], [102] ...
Autonomous, or self-driving, cars are emerging as the solution to several problems primarily caused by humans on roads, such as accidents and traffic congestion. However, those benefits come with great challenges in the verification and validation (V&V) for safety assessment. In fact, due to the possibly unpredictable nature of Artificial Intelligence (AI), its use in autonomous cars creates concerns that need to be addressed using appropriate V&V processes that can address trustworthy AI and safe autonomy. In this study, the relevant research literature in recent years has been systematically reviewed and classified in order to investigate the state-of-the-art in the software V&V of autonomous cars. By appropriate criteria, a subset of primary studies has been selected for more in-depth analysis. The first part of the review addresses certification issues against reference standards, challenges in assessing machine learning, as well as general V&V methodologies. The second part investigates more specific approaches, including simulation environments and mutation testing, corner cases and adversarial examples, fault injection, software safety cages, techniques for cyber-physical systems, and formal methods. Relevant approaches and related tools have been discussed and compared in order to highlight open issues and opportunities.
... We made an attempt to use different categories with a "top down" approach, based, e.g., on life-cycle stages, architectural levels or components, but those classifications did not match well with the coverage of papers we actually found, due to several factors, including heterogeneity in reference architectural models and immaturity of many new V&V approaches for AVs, compared to more stable sectors such as avionics or railways (e.g., automatic train control), where those classifications work better. [2], [10], [29], [30], [52], [60], [66], [69], [71], [75], [87], [90], [91], [91], [100], [106] Test Case Definition and Generation [17], [25], [36], [40], [46], [51], [52], [54], [67], [72], [81], [86], [87], [100] Corner Cases and Adversarial Examples [8], [14], [18], [22], [24], [31], [32], [38], [41], [47]- [49], [53], [55], [85], [89], [95], [96], [102], [104], [105] Fault Injection [3], [4], [6], [15], [37], [62], [64] [73] [74], [92]- [94], [97], [103], [107] Mutation Testing [4], [50], [55], [58] Software Safety Cages [7], [68] Techniques for CPS [20], [21], [28], [35], [39], [56], [65], [76], [99] Formal Methods [16], [27], [34], [61], [63], [70], [79], [82], [87], [98], [99], [101], [102] ...
Autonomous, or self-driving, cars are emerging as the solution to several problems primarily caused by humans on roads, such as accidents and traffic congestion. However, those benefits come with great challenges in the verification and validation (V&V) for their safety assessment. In fact, due to the possibly unpredictable nature of Artificial Intelligence (AI), its use in autonomous cars creates concerns that need to be addressed using appropriate V&V processes that are able to address trustworthy AI and thus achieve a safe autonomy. In this study, the research work in the last ten years is reviewed to investigate the state-of-the-art in the software V&V of safe autonomous cars and summarize open issues in this field. Relevant papers have been found and classified using a systematic approach. By appropriate inclusion and exclusion criteria, a subset of primary studies have been selected for more in-depth analysis. The applicability of current approaches within reference standards such as the ISO 26262 has also been reviewed. Finally, the review has investigated the adoption of formal methods with a focus on cyber-physical systems, as well as more conventional software verification approaches such as simulation and fault injection, together with mutation testing of machine learning systems, with comparison between relevant approaches.
... In this work we have pursued to design, implement and evaluate an end-to-end model for predicting steering commands of an autonomous vehicle. Starting from our previously collected dataset [10] we used deep convolutional neural networks on the input frames and provided as output a distribution over the discretized steering command. The proposed model yielded better results on our dataset when using data augmentation techniques during training. ...
On-road behavior analysis is a crucial and challenging problem in the autonomous driving vision-based area. Several endeavors have been proposed to deal with different related tasks and it has gained wide attention recently. Much of the excitement about on-road behavior understanding has been the labor of advancement witnessed in the fields of computer vision, machine, and deep learning. Remarkable achievements have been made in the Road Behavior Understanding area over the last years. This paper reviews 100+ papers of on-road behavior analysis related work in the light of the milestones achieved, spanning over the last 2 decades. This review paper provides the first attempt to draw smart mobility researchers’ attention to the road behavior understanding field and its potential impact on road safety to the whole road agents such as: drivers, pedestrians, stuffs, etc. To push for an holistic understanding, we investigate the complementary relationships between different elementary tasks that we define as the main components of road behavior understanding to achieve a comprehensive understanding of approaches and techniques. For this, five related topics have been covered in this review, including situational awareness, driver-road interaction, road scene understanding, trajectories forecast, driving activities, and status analysis. This paper also reviews the contribution of deep learning approaches and makes an in-depth analysis of recent benchmarks as well, with a specific taxonomy that can help stakeholders in selecting their best-fit architecture. We also finally provide a comprehensive discussion leading us to identify novel research directions some of which have been implemented and validated in our current smart mobility research work. This paper presents the first survey of road behavior understanding-related work without overlap with existing reviews.
When talking about automation, “autonomous vehicles”, often abbreviated as AVs, come to mind. In transitioning from the “driver” mode to the different automation levels, there is an inevitable need for modeling driving behavior. This often happens through data collection from experiments and studies, but also information extraction, a key step in behavioral modeling. Particularly, naturalistic driving studies and field operational trials are used to collect meaningful data on drivers’ interactions in real–world conditions. On the other hand, information extraction methods allow to predict or mimic driving behavior, by using a set of statistical learning methods. In simple words, the way to understand drivers’ needs and wants in the era of automation can be represented in a data–information cycle, starting from data collection, and ending with information extraction. To develop this cycle, this research reviews studies with keywords “data collection”, “information extraction”, “AVs”, while keeping the focus on driving behavior. The resulting review led to a screening of about 161 papers, out of which about 30 were selected for a detailed analysis. The analysis included an investigation of the methods and equipment used for data collection, the features collected, the size and frequency of the data along with the main problems associated with the different sensory equipment; the studies also looked at the models used to extract information, including various statistical techniques used in AV studies. This paved the way to the development of a framework for data analytics and fusion, allowing the use of highly heterogeneous data to reach the defined objectives; for this paper, the example of impacts of AVs on a network level and AV acceptance is given. The authors suggest that such a framework could be extended and transferred across the various transportation sectors.
