Skip to main content
Go to the home page of the European Commission (opens in new window)
English English
CORDIS - EU research results
CORDIS

Automated Urban Parking and Driving

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Deliverables

Final specification and design of on-board sensing (opens in new window)

The deliverable provides a report on the detailed specification of the perception goals and of the sensorial model of the environment. It also describes the sensors selection and their optimal setup configuration for obtaining a robust and redundant perception solution for each individual perception task – in alignment with the system-wide specification of WP1.

Software specification and architecture for the decision making and navigation (opens in new window)

This deliverable will provide the general architecture of the navigation stack. It will list all software components involved in the decision making and navigation processes, the interfaces between them as well as to components from other work packages. It will also provide approaches identified to be pursued in the project.

Second development and integration cycle of scene understanding (opens in new window)

The deliverable covers the second development and integration cycle and reports on current state of all tasks within the Work Package.. It will report details statistical insights on semantic aspects of urban scenes (e.g. parking lot usage). It will furthermore consist of software modules able to extract said information from the map representation of WP5. It will also provide a report and a software able to analyze the ego-behavior and synthesize it in terms of high level representation.

Initial version of low-level perception functions (opens in new window)

The deliverable provides first a report and code on the design and implementation evaluation of the spatio-temporal and appearance based low level representation. It provides also a report and code on the perception adaptation to adverse visibility conditions functions and their design, implementation and evaluation.

Periodic status report period 2 (opens in new window)

The deliverable provides a technical report on the overall status of the project every period. The second report will describe the status of the the first iteration of specifications and integration and evaluation, as well as the advancements reached in each WP.

First development and integration cycle of lifelong mapping (opens in new window)

This deliverable describes the lifelong mapping framework after the first development & Integration cycle. All components, notably the metric and semantic map, the metric online localization, the semantic data aggregation and the map summarization are functional and integrated on the vehicles, fulfill their basic purposes and interact with each other in a limited fashion. All components deliver first evaluation results.

Final version of higher-level perception functions (opens in new window)

The deliverable provides a report and code on the road perception, terrain mapping, road users and signaling perception functions and their design, implementation and evaluation. It also provides sensor fusion based perception refinement and environment model design, implementation and evaluation.

Initial version of higher-level perception functions (opens in new window)

The deliverable provides a report and code on the road perception, terrain mapping, road users and signaling perception functions and their design, implementation and evaluation. It also provides sensor fusion based perception refinement and environment model design, implementation and evaluation.

Software specification and architecture for scene understanding (opens in new window)

In this report detailed input and outputs of scene understanding will be produced. Input will include the specific interfaces from other Work Packages. Outputs will define the format of the data produced to detect the current scene and predict the expected behavior of traffic occupants. Also the Interfaces between the individual modules involved into scene understanding will be provided.

Specification of the map frontend and storage concept (opens in new window)

This deliverable consists of all software and hardware specifications related to the mapping frontend and the internal map storage concept as described in Task 5.1 and Task 5.3, as well as a concept on how data is to be exchanged between the vehicles and the mapping backend.

Final version of low-level perception functions (opens in new window)

The deliverable provides first a report and code on the design and implementation evaluation of the spatio-temporal and appearance based low level representation. It provides also a report and code on the perception adaptation to adverse visibility conditions functions and their design, implementation and evaluation.

First development and integration cycle of decision making and navigation (opens in new window)

This deliverable will provide a detailed explanation of the individual modules involved into the decision making and navigation processes. By this time the full software stack is expected to be functional with tasks such as route planning, trajectory control being in a state only requiring minor updates. The deliverable will report first results gained both in simulation as well as with the real car system. Most importantly it will provide results from automated driving trials performed with the first version of the full system as expected for MS3. The deliverable will be in form of a technical report or a publication.

Periodic status report period 3 (opens in new window)

The deliverable provides a technical report on the overall status of the project every period. The third report will describe the status of the the second iteration of specifications and integration and evaluation, as well as the advancements reached in each WP.

First development and integration cycle of scene understanding (opens in new window)

The deliverable covers the first development and integration cycle and reports on current state of all Tasks within theWork Package. This report details statistical insights on semantic aspects of urban scenes (e.g. parking lot usage). It will furthermore consist of software modules able to extract said information from the map representation of WP5. It will also provide an exhaustive list of urban driving scenario and their characteristics. It will furthermore consist of software modules able to profile the road user behavior in terms of dynamic and predicted intentions.

Final dissemination report (opens in new window)

A report about achieved dissemination and exploitation activities.

First vehicle platform fully operational (opens in new window)

This document will mark the completion of the first vehicle platform and its full utility for the consecutive Work Packages. Specifically, it will document the calibration as well as data integrity validation of the sensors (including the reference sensors). It will also present relevant features of the high-level maintenance framework. Furthermore, it will contain a short report on communication capabilities (bandwidth, latency, etc., measured under good conditions). Last but not least: it will explain the safety elements and precautions.

Second development and integration cycle of cloud infrastructure (opens in new window)

This deliverable describes the cloud infrastructure framework after the second development and integration cycle. All components mentioned in D3.2 including the final, horizontally scaled hardware stack, the updated development and deployment toolchain, the updated and iterated communication framework and the extended bulk data storage service have reached full maturity and adhere to the specifications and quality goals defined in this work package. Interaction between the components is seamless and according to specification. The deliverable contains the results of the module's final performance evaluation.

Periodic status report period 1 (opens in new window)

The deliverable provides a technical report on the overall status of the project every period. The first report will describe the status of the specifications, as well as the advancements reached in each WP.

Second vehicle platform fully functional (opens in new window)

This deliverable will document the full utility of the second vehicle platform analogously to Deliverable D2.2.

Development infrastructure (opens in new window)

A report documenting access to running instances of both the project-internal development repository and the public open-access repository together with issue-tracking and wiki support.

Integration and test tools and processes (opens in new window)

A report describing the integration tools and processes available.

Initial dissemination report (opens in new window)

A report about achieved dissemination and exploitation activities.

Evaluation report on integration process and results of second development cycle (opens in new window)

A report on the conducted evaluation of the overall system and its performance. A report about the conducted integration activities, problems and resolutions as well as a summary of the integration weeks and related activities.

First vehicle platform available (opens in new window)

This deliverable will mark the completion of the hardware and low level software of the first vehicle platform. It will include a vehicle manual with photos of all relevant hardware elements. This will be accompanied by figures and short descriptions of basic features of the communication, acquisition and processing framework. It will further provide a dataset including data from all sensors and a report with figures of visualized raw data. Finally it will provide a video demonstrating drive by wire operation using a gamepad / keyboard.

First development and integration cycle of cloud infrastructure (opens in new window)

This deliverable describes the cloud infrastructure framework after the first development and integration cycle. All components, including the initial hardware stack, the development and deployment toolchain, the communication framework and the bulk data storage service are functional and fulfill their basic purpose. All components deliver first implementation results.

Second development and integration cycle of lifelong mapping (opens in new window)

This deliverable describes the final lifelong mapping framework after the second development & Integration cycle. All components, as mentioned in deliverable D 5.2 above, are functional and integrated on the vehicles, have reached full maturity and adhere to the specifications and quality goals defined in this work package. Interaction between the components is seamless and according to specification. The deliverable contains the results of each module’s final performance evaluation.

Evaluation report on integration process and results of first development cycle (opens in new window)

A report on the conducted evaluation of the overall system and its performance. A report about the conducted integration activities, problems and resolutions as well as a summary of the integration weeks and related activities.

Second vehicle platform available (opens in new window)

Responsible beneficiary: VW This deliverable will document the availability of the second vehicle platform analogously to Deliverable D2.1.

Initial specification and design of on-board sensing (opens in new window)

The deliverable provides a report on the detailed specification of the perception goals and of the sensorial model of the environment. It also describes the sensors selection and their optimal setup configuration for obtaining a robust and redundant perception solution for each individual perception task – in alignment with the system-wide specification of WP1.

Second development and integration cycle of decision making and navigation (opens in new window)

This deliverable will provide a detailed explanation of the individual modules involved into the decision making and navigation processes as well as their evaluation. By this time the full software stack is expected to be fully functional with modules such as tactical and trajectory planning as well as mission executive able to handle all relevant scenarios. The deliverable will report results gained in simulation and with the real car system. It is also expected that the system will be well integrated with other work packages so the deliverable will provide results from automated driving trials performed with the full integrated system. The deliverable will be in form of a technical report or a publication.

Final demonstration (opens in new window)

A public demonstration with press representatives showcasing the final result of the project and the impact on the society.

Press video (opens in new window)

A press video motivating the aims of the project, and showcasing the scientific results, and the impact on society.

Brochure, newsletter (opens in new window)

A nicely laid out brochure at M16 to inform the public about the project and its main objectives and content. A knowledge management report will be provided to keep internal and external experts informed about new knowledge or patents created in the project.

Mid-term demonstration (opens in new window)

An internal demonstration (optionally with press representatives) showcasing the final result of the project and the impact on the society.

Project Web-page (opens in new window)

The website including a public document database will be operational from month 2 on. It will be updated continuously during the project.

Publications

Semantic segmentation-based stereo reconstruction with statistically improved long range accuracy (opens in new window)

Author(s): Vlad-Cristian Miclea, Sergiu Nedevschi
Published in: 2017 IEEE Intelligent Vehicles Symposium (IV), 2017, Page(s) 1795-1802, ISBN 978-1-5090-4804-5
Publisher: IEEE
DOI: 10.1109/IVS.2017.7995967

Traffic scene segmentation based on boosting over multimodal low, intermediate and high order multi-range channel features (opens in new window)

Author(s): Arthur D. Costea, Sergiu Nedevschi
Published in: 2017 IEEE Intelligent Vehicles Symposium (IV), 2017, Page(s) 74-81, ISBN 978-1-5090-4804-5
Publisher: IEEE
DOI: 10.1109/IVS.2017.7995701

Semi-automatic image annotation of street scenes (opens in new window)

Author(s): Andra Petrovai, Arthur D. Costea, Sergiu Nedevschi
Published in: 2017 IEEE Intelligent Vehicles Symposium (IV), 2017, Page(s) 448-455, ISBN 978-1-5090-4804-5
Publisher: IEEE
DOI: 10.1109/IVS.2017.7995759

Fast Boosting Based Detection Using Scale Invariant Multimodal Multiresolution Filtered Features (opens in new window)

Author(s): Arthur Daniel Costea, Robert Varga, Sergiu Nedevschi
Published in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Page(s) 993-1002, ISBN 978-1-5386-0457-1
Publisher: IEEE
DOI: 10.1109/CVPR.2017.112

Super-sensor for 360-degree environment perception: Point cloud segmentation using image features (opens in new window)

Author(s): Robert Varga, Arthur Costea, Horatiu Florea, Ion Giosan, Sergiu Nedevschi
Published in: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017, Page(s) 1-8, ISBN 978-1-5386-1526-3
Publisher: IEEE
DOI: 10.1109/ITSC.2017.8317846

Online cross-calibration of camera and LIDAR (opens in new window)

Author(s): Bianca-Cerasela-Zelia Blaga, Sergiu Nedevschi
Published in: 2017 13th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), 2017, Page(s) 295-301, ISBN 978-1-5386-3368-7
Publisher: IEEE
DOI: 10.1109/ICCP.2017.8117020

Real-time object detection using a sparse 4-layer LIDAR (opens in new window)

Author(s): Mircea Paul Muresan, Sergiu Nedevschi, Ion Giosan
Published in: 2017 13th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), 2017, Page(s) 317-322, ISBN 978-1-5386-3368-7
Publisher: IEEE
DOI: 10.1109/ICCP.2017.8117023

An approach for segmenting 3D LiDAR data using multi-volume grid structures (opens in new window)

Author(s): Selma Goga, Sergiu Nedevschi
Published in: 2017 13th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), 2017, Page(s) 309-315, ISBN 978-1-5386-3368-7
Publisher: IEEE
DOI: 10.1109/ICCP.2017.8117022

Real-time Semantic Segmentation-based Depth Upsampling using Deep Learning

Author(s): V. Miclea and S. Nedevschi
Published in: 2018
Publisher: IEEE

Lessons learned from developing the Gödel Deep Learning library

Author(s): Robert Varga
Published in: 2017
Publisher: IEEE

Boosting over deep convolutional features for object detection

Author(s): Arthur Costea
Published in: 2017
Publisher: IEEE

Fusion Scheme for Semantic and Instance-level Segmentation

Author(s): A. Costea, A. Petrovai, S. Nedevschi
Published in: Deep vision workshop; 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 18), 2018
Publisher: IEEE

Deep learning-based approaches for stereo reconstruction

Author(s): Vlad Miclea
Published in: 2017
Publisher: IEEE

Deep learning for semantic image segmentation

Author(s): Andra Petrovai
Published in: 2017
Publisher: IEEE

Fusion Scheme for Semantic and Instance-level Segmentation

Author(s): A.D. Costea, A. Petrovai, S. Nedevschi
Published in: 2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC 2018), 2018
Publisher: IEEE

Appearance-Based Landmark Selection for Efficient Long-Term Visual Localization

Author(s): Mathias Buerki, Igor Gilitschenski, Elena Stumm, Roland Siegwart, and Juan Nieto
Published in: International Conference on Intelligent Robots and Systems (IROS) 2016, 2016
Publisher: Mathias Buerki, Igor Gilitschenski, Elena Stumm, Roland Siegwart, and Juan Nieto

Modular Sensor Fusion for Semantic Segmentation (opens in new window)

Author(s): Hermann Blum, Abel Gawel, Roland Siegwart, Cesar Cadena
Published in: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, Page(s) 3670-3677, ISBN 978-1-5386-8094-0
Publisher: IEEE
DOI: 10.1109/IROS.2018.8593786

OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios (opens in new window)

Author(s): Schaupp, Lukas; Bürki, Mathias; Cadena, Cesar; Dube, Renaud; Siegwart, Roland
Published in: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Issue 1, 2019
Publisher: IEEE
DOI: 10.13140/rg.2.2.10859.59685

VIZARD: Reliable Visual Localization for Autonomous Vehicles in Urban Outdoor Environments (opens in new window)

Author(s): Mathias Burki, Lukas Schaupp, Marcin Dymczyk, Renaud Dube, Cesar Cadena, Roland Siegwart, Juan Nieto
Published in: 2019 IEEE Intelligent Vehicles Symposium (IV), 2019, Page(s) 1124-1130, ISBN 978-1-7281-0560-4
Publisher: IEEE
DOI: 10.1109/IVS.2019.8814017

Design of an Autonomous Racecar: Perception, State Estimation and System Integration (opens in new window)

Author(s): Miguel I. Valls, Hubertus F.C. Hendrikx, Victor J.F. Reijgwart, Fabio V. Meier, Inkyu Sa, Renaud Dube, Abel Gawel, Mathias Burki, Roland Siegwart
Published in: 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, Page(s) 2048-2055, ISBN 978-1-5386-3081-5
Publisher: IEEE
DOI: 10.1109/ICRA.2018.8462829

Map Management for Efficient Long-Term Visual Localization in Outdoor Environments

Author(s): Bürki, Mathias; Dymczyk, Marcin; Gilitschenski, Igor; Cadena, Cesar; Siegwart, Roland; Nieto, Juan
Published in: IEEE Intelligent Vehicles Symposium, Issue 1, 2018
Publisher: IEEE

A Fast Ransac Based Approach for Computing the Orientation of Obstacles in Traffic Scenes (opens in new window)

Author(s): Florin Oniga, Sergiu Nedevschi
Published in: 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP), 2018, Page(s) 209-214, ISBN 978-1-5386-8445-0
Publisher: IEEE
DOI: 10.1109/iccp.2018.8516642

Curb detection in urban traffic scenarios using LiDARs point cloud and semantically segmented color images (opens in new window)

Author(s): Selma Evelyn Catalina Deac, Ion Giosan, Sergiu Nedevschi
Published in: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019, Page(s) 3433-3440, ISBN 978-1-5386-7024-8
Publisher: IEEE
DOI: 10.1109/itsc.2019.8917020

Efficient Instance and Semantic Segmentation for Automated Driving (opens in new window)

Author(s): Andra Petrovai, Sergiu Nedevschi
Published in: 2019 IEEE Intelligent Vehicles Symposium (IV), 2019, Page(s) 2575-2581, ISBN 978-1-7281-0560-4
Publisher: IEEE
DOI: 10.1109/ivs.2019.8814177

Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space (opens in new window)

Author(s): Berta Bescos, Jose Neira, Roland Siegwart, Cesar Cadena
Published in: 2019 International Conference on Robotics and Automation (ICRA), 2019, Page(s) 5460-5466, ISBN 978-1-5386-6027-0
Publisher: IEEE
DOI: 10.1109/icra.2019.8794417

Environment Perception Architecture using Images and 3D Data (opens in new window)

Author(s): Horatiu FLOREA, Robert VARGA, Sergiu NEDEVSCHI
Published in: 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP), 2018, Page(s) 223-228, ISBN 978-1-5386-8445-0
Publisher: IEEE
DOI: 10.1109/iccp.2018.8516581

Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data

Author(s): Danila Rukhovich, Daniel Mouritzen, Ralf Kaestner, Martin Rufli, Alexander Velizhev
Published in: International Conference on Computer Vision (ICCV); Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving, 2019
Publisher: IEEE

Semantic information based vehicle relative orientation and taillight detection (opens in new window)

Author(s): Flaviu Ionut Vancea, Sergiu Nedevschi
Published in: 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP), 2018, Page(s) 259-264, ISBN 978-1-5386-8445-0
Publisher: IEEE
DOI: 10.1109/iccp.2018.8516631

Motion Prediction Influence on the Pedestrian Intention Estimation Near a Zebra Crossing

Author(s): J. Škovierová, A. Vobecký, M. Uller, R. Škoviera, V. Hlaváč
Published in: 4th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS 2018), 2018
Publisher: Scitepress

Multi-Object Tracking of 3D Cuboids Using Aggregated Features (opens in new window)

Author(s): Mircea Paul Muresan, Sergiu Nedevschi
Published in: 2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP), 2019, Page(s) 11-18, ISBN 978-1-7281-4914-1
Publisher: IEEE
DOI: 10.1109/iccp48234.2019.8959552

Multi-task Network for Panoptic Segmentation in Automated Driving (opens in new window)

Author(s): Andra Petrovai, Sergiu Nedevschi
Published in: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019, Page(s) 2394-2401, ISBN 978-1-5386-7024-8
Publisher: IEEE
DOI: 10.1109/itsc.2019.8917422

Object Classification Based on Unsupervised Learned Multi-Modal Features For Overcoming Sensor Failures (opens in new window)

Author(s): Julia Nitsch, Juan Nieto, Roland Siegwart, Max Schmidt, Cesar Cadena
Published in: 2019 International Conference on Robotics and Automation (ICRA), 2019, Page(s) 4369-4375, ISBN 978-1-5386-6027-0
Publisher: IEEE
DOI: 10.1109/icra.2019.8793628

Robust Maximum-likelihood On-line LiDAR-to-Camera Calibration Monitoring and Refinement

Author(s): J. Moravec, R. Šára
Published in: Proceedings of the 23rd Computer Vision Winter Workshop, 2018
Publisher: .

Fusing semantic labeled camera images and 3D LiDAR data for the detection of urban curbs (opens in new window)

Author(s): Selma Evelyn Catalina Goga, Sergiu Nedevschi
Published in: 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP), 2018, Page(s) 301-308, ISBN 978-1-5386-8445-0
Publisher: IEEE
DOI: 10.1109/iccp.2018.8516649

A Decentralized Trust-minimized Cloud Robotics Architecture

Author(s): Alessandro Simovic, Ralf Kaestner, Martin Rufli
Published in: 2017
Publisher: Institute of Electrical and Electronics

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (opens in new window)

Author(s): Cesar Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, Jose Neira, Ian Reid, John J. Leonard
Published in: IEEE Transactions on Robotics, Issue 32/6, 2016, Page(s) 1309-1332, ISSN 1552-3098
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TRO.2016.2624754

Appearance‐based landmark selection for visual localization (opens in new window)

Author(s): Mathias Bürki, Cesar Cadena, Igor Gilitschenski, Roland Siegwart, Juan Nieto
Published in: Journal of Field Robotics, Issue 36/6, 2019, Page(s) 1041-1073, ISSN 1556-4959
Publisher: John Wiley & Sons Ltd.
DOI: 10.1002/rob.21870

Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization (opens in new window)

Author(s): Thomas Schneider, Marcin Dymczyk, Marius Fehr, Kevin Egger, Simon Lynen, Igor Gilitschenski, Roland Siegwart
Published in: IEEE Robotics and Automation Letters, Issue 3/3, 2018, Page(s) 1418-1425, ISSN 2377-3766
Publisher: IEEE
DOI: 10.1109/LRA.2018.2800113

Multiple Hypothesis Semantic Mapping for Robust Data Association (opens in new window)

Author(s): Lukas Bernreiter, Abel Roman Gawel, Hannes Sommer, Juan Nieto, Roland Siegwart, Cesar Cadena Lerma
Published in: IEEE Robotics and Automation Letters, 2019, Page(s) 1-1, ISSN 2377-3766
Publisher: IEEE
DOI: 10.1109/lra.2019.2925756

Real-Time Semantic Segmentation-Based Stereo Reconstruction (opens in new window)

Author(s): Vlad-Cristian Miclea, Sergiu Nedevschi
Published in: IEEE Transactions on Intelligent Transportation Systems, 2019, Page(s) 1-11, ISSN 1524-9050
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tits.2019.2913883

SegMap: Segment-based mapping and localization using data-driven descriptors (opens in new window)

Author(s): Renaud Dubé, Andrei Cramariuc, Daniel Dugas, Hannes Sommer, Marcin Dymczyk, Juan Nieto, Roland Siegwart, Cesar Cadena
Published in: The International Journal of Robotics Research, Issue 39/2-3, 2020, Page(s) 339-355, ISSN 0278-3649
Publisher: SAGE Publications
DOI: 10.1177/0278364919863090

Stabilization and Validation of 3D Object Position Using Multimodal Sensor Fusion and Semantic Segmentation (opens in new window)

Author(s): Mircea Paul Muresan, Ion Giosan, Sergiu Nedevschi
Published in: Sensors, Issue 20/4, 2020, Page(s) 1110, ISSN 1424-8220
Publisher: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/s20041110

Searching for OpenAIRE data...

There was an error trying to search data from OpenAIRE

No results available

My booklet 0 0