OASIcs, Volume 68

Workshop on Autonomous Systems Design (ASD 2019)



Thumbnail PDF

Event

ASD 2019, March 29, 2019, Florence, Italy

Editors

Selma Saidi
  • Hamburg University of Technology, Germany
Rolf Ernst
  • Technical University of Braunschweig, Germany
Dirk Ziegenbein
  • Robert Bosch GmbH, Germany

Publication Details

  • published at: 2019-03-28
  • Publisher: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
  • ISBN: 978-3-95977-102-3
  • DBLP: db/conf/date/asd2019

Access Numbers

Documents

No documents found matching your filter selection.
Document
Complete Volume
OASIcs, Volume 68, ASD'19, Complete Volume

Authors: Selma Saidi, Rolf Ernst, and Dirk Ziegenbein


Abstract
OASIcs, Volume 68, ASD'19, Complete Volume

Cite as

Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@Proceedings{saidi_et_al:OASIcs.ASD.2019,
  title =	{{OASIcs, Volume 68, ASD'19, Complete Volume}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019},
  URN =		{urn:nbn:de:0030-drops-103628},
  doi =		{10.4230/OASIcs.ASD.2019},
  annote =	{Keywords: Hardware, Analysis and design of emerging devices and systems, Computer systems organization, Robotic autonomy, Software and its engineering, Software safety, Dependable and fault-tolerant systems and networks}
}
Document
Front Matter
Front Matter, Table of Contents, Preface, Conference Organization

Authors: Selma Saidi, Rolf Ernst, and Dirk Ziegenbein


Abstract
Front Matter, Table of Contents, Preface, Conference Organization

Cite as

Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 0:i-0:xviii, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{saidi_et_al:OASIcs.ASD.2019.0,
  author =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  title =	{{Front Matter, Table of Contents, Preface, Conference Organization}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{0:i--0:xviii},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.0},
  URN =		{urn:nbn:de:0030-drops-103337},
  doi =		{10.4230/OASIcs.ASD.2019.0},
  annote =	{Keywords: Front Matter, Table of Contents, Preface, Conference Organization}
}
Document
Fault-Tolerance by Graceful Degradation for Car Platoons

Authors: M. Baha E. Zarrouki, Verena Klös, Markus Grabowski, and Sabine Glesner


Abstract
The key advantage of autonomous car platoons are their short inter-vehicle distances that increase traffic flow and reduce fuel consumption. However, this is challenging for operational and functional safety. If a failure occurs, the affected vehicles cannot suddenly stop driving but instead should continue their operation with reduced performance until a safe state can be reached or, in the case of temporal failures, full functionality can be guaranteed again. To achieve this degradation, platoon members have to be able to compensate sensor and communication failures and have to adjust their inter-vehicle distances to ensure safety. In this work, we describe a systematic design of degradation cascades for sensor and communication failures in autonomous car platoons using the example of an autonomous model car. We describe our systematic design method, the resulting degradation modes, and formulate contracts for each degradation level. We model and test our resulting degradation controller in Simulink/Stateflow.

Cite as

M. Baha E. Zarrouki, Verena Klös, Markus Grabowski, and Sabine Glesner. Fault-Tolerance by Graceful Degradation for Car Platoons. In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 1:1-1:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{zarrouki_et_al:OASIcs.ASD.2019.1,
  author =	{Zarrouki, M. Baha E. and Kl\"{o}s, Verena and Grabowski, Markus and Glesner, Sabine},
  title =	{{Fault-Tolerance by Graceful Degradation for Car Platoons}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{1:1--1:15},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.1},
  URN =		{urn:nbn:de:0030-drops-103344},
  doi =		{10.4230/OASIcs.ASD.2019.1},
  annote =	{Keywords: fault-tolerance, degradation, car platoons, autonomous driving, contracts}
}
Document
Feasibility Study and Benchmarking of Embedded MPC for Vehicle Platoons

Authors: Iñaki Martín Soroa, Amr Ibrahim, Dip Goswami, and Hong Li


Abstract
This paper performs a feasibility analysis of deploying Model Predictive Control (MPC) for vehicle platooning on an On-Board Unit (OBU) and performance benchmarking considering interference from other (system) tasks running on an OBU. MPC is a control strategy that solves an implicit (on-line) or explicit (off-line) optimisation problem for computing the control input in every sample. OBUs have limited computational resources. The challenge is to implement an MPC algorithm on such automotive Electronic Control Units (ECUs) with an acceptable timing behavior. Moreover, we should be able to stop the execution if necessary at the cost of performance. We measured the computational capability of a unit developed by Cohda Wireless and NXP under the influence of its Operating System (OS). Next, we analysed the computational requirements of different state-of-the-art MPC algorithms by estimating their execution times. We use off-the-shelf and free automatic code generators for MPC to run a number of relevant MPC algorithms on the platform. From the results, we conclude that it is feasible to implement MPC on automotive ECUs for vehicle platooning and we further benchmark their performance in terms of MPC parameters such as prediction horizon and system dimension.

Cite as

Iñaki Martín Soroa, Amr Ibrahim, Dip Goswami, and Hong Li. Feasibility Study and Benchmarking of Embedded MPC for Vehicle Platoons. In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 2:1-2:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{martinsoroa_et_al:OASIcs.ASD.2019.2,
  author =	{Mart{\'\i}n Soroa, I\~{n}aki and Ibrahim, Amr and Goswami, Dip and Li, Hong},
  title =	{{Feasibility Study and Benchmarking of Embedded MPC for Vehicle Platoons}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{2:1--2:15},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.2},
  URN =		{urn:nbn:de:0030-drops-103359},
  doi =		{10.4230/OASIcs.ASD.2019.2},
  annote =	{Keywords: Model predictive control, vehicle platoon, embedded implementation, code generation}
}
Document
IDF-Autoware: Integrated Development Framework for ROS-Based Self-Driving Systems Using MATLAB/Simulink

Authors: Shota Tokunaga, Yuki Horita, Yasuhiro Oda, and Takuya Azumi


Abstract
This paper proposes an integrated development framework that enables co-simulation and operation of a Robot Operating System (ROS)-based self-driving system using MATLAB/Simulink (IDF-Autoware). The management of self-driving systems is becoming more complex as the development of self-driving technology progresses. One approach to the development of self-driving systems is the use of ROS; however, the system used in the automotive industry is typically designed using MATLAB/Simulink, which can simulate and evaluate the models used for self-driving. These models are incompatible with ROS-based systems. To allow the two to be used in tandem, it is necessary to rewrite the C++ code and incorporate them into the ROS-based system, which makes development inefficient. Therefore, the proposed framework allows models created using MATLAB/Simulink to be used in a ROS-based self-driving system, thereby improving development efficiency. Furthermore, our evaluations of the proposed framework demonstrated its practical potential.

Cite as

Shota Tokunaga, Yuki Horita, Yasuhiro Oda, and Takuya Azumi. IDF-Autoware: Integrated Development Framework for ROS-Based Self-Driving Systems Using MATLAB/Simulink. In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 3:1-3:9, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{tokunaga_et_al:OASIcs.ASD.2019.3,
  author =	{Tokunaga, Shota and Horita, Yuki and Oda, Yasuhiro and Azumi, Takuya},
  title =	{{IDF-Autoware: Integrated Development Framework for ROS-Based Self-Driving Systems Using MATLAB/Simulink}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{3:1--3:9},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.3},
  URN =		{urn:nbn:de:0030-drops-103367},
  doi =		{10.4230/OASIcs.ASD.2019.3},
  annote =	{Keywords: self-driving systems, framework, robot operating system (ROS), MATLAB/Simulink}
}
Document
Controlling Concurrent Change - A Multiview Approach Toward Updatable Vehicle Automation Systems

Authors: Mischa Möstl, Marcus Nolte, Johannes Schlatow, and Rolf Ernst


Abstract
The development of SAE Level 3+ vehicles [{SAE}, 2014] poses new challenges not only for the functional development, but also for design and development processes. Such systems consist of a growing number of interconnected functional, as well as hardware and software components, making safety design increasingly difficult. In order to cope with emergent behavior at the vehicle level, thorough systems engineering becomes a key requirement, which enables traceability between different design viewpoints. Ensuring traceability is a key factor towards an efficient validation and verification of such systems. Formal models can in turn assist in keeping track of how the different viewpoints relate to each other and how the interplay of components affects the overall system behavior. Based on experience from the project Controlling Concurrent Change, this paper presents an approach towards model-based integration and verification of a cause effect chain for a component-based vehicle automation system. It reasons on a cross-layer model of the resulting system, which covers necessary aspects of a design in individual architectural views, e.g. safety and timing. In the synthesis stage of integration, our approach is capable of inserting enforcement mechanisms into the design to ensure adherence to the model. We present a use case description for an environment perception system, starting with a functional architecture, which is the basis for componentization of the cause effect chain. By tying the vehicle architecture to the cross-layer integration model, we are able to map the reasoning done during verification to vehicle behavior.

Cite as

Mischa Möstl, Marcus Nolte, Johannes Schlatow, and Rolf Ernst. Controlling Concurrent Change - A Multiview Approach Toward Updatable Vehicle Automation Systems. In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 4:1-4:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{mostl_et_al:OASIcs.ASD.2019.4,
  author =	{M\"{o}stl, Mischa and Nolte, Marcus and Schlatow, Johannes and Ernst, Rolf},
  title =	{{Controlling Concurrent Change - A Multiview Approach Toward Updatable Vehicle Automation Systems}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{4:1--4:15},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.4},
  URN =		{urn:nbn:de:0030-drops-103376},
  doi =		{10.4230/OASIcs.ASD.2019.4},
  annote =	{Keywords: safety, behavior, functional, architecture, multi-view, automated driving}
}
Document
Safety and Security Analysis of AEB for L4 Autonomous Vehicle Using STPA

Authors: Shefali Sharma, Adan Flores, Chris Hobbs, Jeff Stafford, and Sebastian Fischmeister


Abstract
Autonomous vehicles (AVs) are coming to our streets. Due to the presence of highly complex software systems in AVs, there is a need for a new hazard analysis technique to meet stringent safety standards. System Theoretic Process Analysis (STPA), based on Systems Theoretic Accident Modeling and Processes (STAMP), is a powerful tool that can identify, define, analyze and mitigate hazards from the earliest conceptual stage deployment to the operation of a system. Applying STPA to autonomous vehicles demonstrates STPA's applicability to preliminary hazard analysis, alternative available, developmental tests, organizational design, and functional design of each unique safety operation. This paper describes the STPA process used to generate system design requirements for an Autonomous Emergency Braking (AEB) system using a top-down analysis approach to system safety. The paper makes the following contributions to practicing STPA for safety and security: 1) It describes the incorporation of safety and security analysis in one process and discusses the benefits of this; 2) It provides an improved, structural approach for scenario analysis, concentrating on safety and security; 3) It demonstrates the utility of STPA for gap analysis of existing designs in the automotive domain; 4) It provides lessons learned throughout the process of applying STPA and STPA-Sec .

Cite as

Shefali Sharma, Adan Flores, Chris Hobbs, Jeff Stafford, and Sebastian Fischmeister. Safety and Security Analysis of AEB for L4 Autonomous Vehicle Using STPA. In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 5:1-5:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{sharma_et_al:OASIcs.ASD.2019.5,
  author =	{Sharma, Shefali and Flores, Adan and Hobbs, Chris and Stafford, Jeff and Fischmeister, Sebastian},
  title =	{{Safety and Security Analysis of AEB for L4 Autonomous Vehicle Using STPA}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{5:1--5:13},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.5},
  URN =		{urn:nbn:de:0030-drops-103388},
  doi =		{10.4230/OASIcs.ASD.2019.5},
  annote =	{Keywords: Functional Safety, Security, STAMP, STPA, STPA-Sec, ISO 26262, AEB, Advanced Driver Assistance Systems (ADAS), Automated Vehicles, SoC (System-On-Chip)}
}
Document
Towards a Formal Model of Recursive Self-Reflection

Authors: Axel Jantsch


Abstract
Self-awareness holds the promise of better decision making based on a comprehensive assessment of a system’s own situation. Therefore it has been studied for more than ten years in a range of settings and applications. However, in the literature the term has been used in a variety of meanings and today there is no consensus on what features and properties it should include. In fact, researchers disagree on the relative benefits of a self-aware system compared to one that is very similar but lacks self-awareness. We sketch a formal model, and thus a formal definition, of self-awareness. The model is based on dynamic dataflow semantics and includes self-assessment, a simulation and an abstraction as facilitating techniques, which are modeled by spawning new dataflow actors in the system. Most importantly, it has a method to focus on any of its parts to make it a subject of analysis by applying abstraction, self-assessment and simulation. In particular, it can apply this process to itself, which we call recursive self-reflection. There is no arbitrary limit to this self-scrutiny except resource constraints.

Cite as

Axel Jantsch. Towards a Formal Model of Recursive Self-Reflection. In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 6:1-6:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{jantsch:OASIcs.ASD.2019.6,
  author =	{Jantsch, Axel},
  title =	{{Towards a Formal Model of Recursive Self-Reflection}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{6:1--6:15},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.6},
  URN =		{urn:nbn:de:0030-drops-103395},
  doi =		{10.4230/OASIcs.ASD.2019.6},
  annote =	{Keywords: Cyber-physical systems, self-aware systems, self-reflection, self-assessment}
}
Document
Interactive Presentation
A Dependable Detection Mechanism for Intersection Management of Connected Autonomous Vehicles (Interactive Presentation)

Authors: Rachel Dedinsky, Mohammad Khayatian, Mohammadreza Mehrabian, and Aviral Shrivastava


Abstract
Traffic intersections will become automated in the near future with the advent of Connected Autonomous Vehicles (CAVs). Researchers have proposed intersection management approaches that use the position and velocity that are reported by vehicles to compute a schedule for vehicles to safely and efficiently traverse the intersection. However, a vehicle may fail to follow intersection manager (IM) scheduling commands due to erroneous sensor readings or unexpected incidents like engine failure, which can cause an accident if the failure happens inside the intersection. Additionally, rogue vehicles can take the advantage of the IM by providing false position and velocity data and cause traffic congestion. In this paper, we present a new technique and infrastructure to detect anomalies and inform the IM. We propose a vision system that can monitor the position of incoming vehicles and provide real-time data for the IM. The IM can use this data to verify the trajectories of CAVs and broadcast a warning when a vehicle fails to follow commands, making the IM more resilient against attacks and false data. We implemented our method by building infrastructure for an intersection with 1/10 scale model CAVs. Results show our method, when combined with an IM dataflows, is more dependable in the event of a failure compared to an IM without it.

Cite as

Rachel Dedinsky, Mohammad Khayatian, Mohammadreza Mehrabian, and Aviral Shrivastava. A Dependable Detection Mechanism for Intersection Management of Connected Autonomous Vehicles (Interactive Presentation). In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 7:1-7:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{dedinsky_et_al:OASIcs.ASD.2019.7,
  author =	{Dedinsky, Rachel and Khayatian, Mohammad and Mehrabian, Mohammadreza and Shrivastava, Aviral},
  title =	{{A Dependable Detection Mechanism for Intersection Management of Connected Autonomous Vehicles}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{7:1--7:13},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.7},
  URN =		{urn:nbn:de:0030-drops-103408},
  doi =		{10.4230/OASIcs.ASD.2019.7},
  annote =	{Keywords: Connected Autonomous Vehicles, Intersection Management, Dependable Systems}
}
Document
Interactive Presentation
TrueView: A LIDAR Only Perception System for Autonomous Vehicle (Interactive Presentation)

Authors: Mohammed Yazid Lachachi, Mohamed Ouslim, Smail Niar, and Abdelmalik Taleb-Ahmed


Abstract
Real time perception and understanding of the environment is essential for an autonomous vehicle. To obtain the most accurate perception, existing solutions propose to combine multiple sensors. However, a large number of embedded sensors in the vehicle implies to process a large amount of data thus increasing the system complexity and cost. In this work, we present a novel approach that uses only one LIDAR sensor. Our approach enables reducing the size and complexity of the used machine learning algorithm. A novel approach is proposed to generate multiple 2D representation from 3D points cloud using the LIDAR sensor. The obtained representation solves the sparsity and connectivity issues encountered with LIDAR-based solution.

Cite as

Mohammed Yazid Lachachi, Mohamed Ouslim, Smail Niar, and Abdelmalik Taleb-Ahmed. TrueView: A LIDAR Only Perception System for Autonomous Vehicle (Interactive Presentation). In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 8:1-8:10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{lachachi_et_al:OASIcs.ASD.2019.8,
  author =	{Lachachi, Mohammed Yazid and Ouslim, Mohamed and Niar, Smail and Taleb-Ahmed, Abdelmalik},
  title =	{{TrueView: A LIDAR Only Perception System for Autonomous Vehicle}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{8:1--8:10},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.8},
  URN =		{urn:nbn:de:0030-drops-103411},
  doi =		{10.4230/OASIcs.ASD.2019.8},
  annote =	{Keywords: Ranging Data, Computer Vision, Machine Learning}
}
Document
Interactive Presentation
Generation of a Reconfigurable Probabilistic Decision-Making Engine based on Decision Networks: UAV Case Study (Interactive Presentation)

Authors: Sara Zermani and Catherine Dezan


Abstract
Making decisions under uncertainty is a common challenge in numerous application domains, such as autonomic robotics, finance and medicine. Decision Networks are probabilistic graphical models that propose an extension of Bayesian Networks and can address the problem of Decision-Making under uncertainty. For an embedded version of Decision-Making, the related implementation must be adapted to constraints on resources, performance and power consumption. In this paper, we introduce a high-level tool to design probabilistic Decision-Making engines based on Decision Networks tailored to embedded constraints in terms of performance and energy consumption. This tool integrates high-level transformations and optimizations and produces efficient implementation solutions on a reconfigurable support, with the generation of HLS-Compliant C code. The proposed approach is validated with a simple Decision-Making example for UAV mission planning implemented on the Zynq SoC platform.

Cite as

Sara Zermani and Catherine Dezan. Generation of a Reconfigurable Probabilistic Decision-Making Engine based on Decision Networks: UAV Case Study (Interactive Presentation). In Workshop on Autonomous Systems Design (ASD 2019). Open Access Series in Informatics (OASIcs), Volume 68, pp. 9:1-9:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{zermani_et_al:OASIcs.ASD.2019.9,
  author =	{Zermani, Sara and Dezan, Catherine},
  title =	{{Generation of a Reconfigurable Probabilistic Decision-Making Engine based on Decision Networks: UAV Case Study}},
  booktitle =	{Workshop on Autonomous Systems Design (ASD 2019)},
  pages =	{9:1--9:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-102-3},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{68},
  editor =	{Saidi, Selma and Ernst, Rolf and Ziegenbein, Dirk},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ASD.2019.9},
  URN =		{urn:nbn:de:0030-drops-103429},
  doi =		{10.4230/OASIcs.ASD.2019.9},
  annote =	{Keywords: Decision networks, Bayesian networks, HLS, FPGA}
}

Filters


Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail