DATE 2022 Initiative on Autonomous Systems Design (ASD)

 

https://www.date-conference.com/asd

 

14-18 March 2022

Fully virtual event

 

Please visit https://asd-initiative.org/ for information about our previous successful events in 2019, 2020 and 2021!

The preliminary program for the ASD Friday Interactive Day can be found here: https://www.date-conference.com/workshop/w10.

 

Scope of the Initiative on Autonomous Systems Design (ASD)

Fueled by the progress of artificial intelligence, autonomous systems become more and more integral parts of many Internet-of-Things (IoT) and Cyber-Physical Systems (CPS) applications, such as automated driving, robotics, avionics, industrial automation and smart systems in general. Autonomous systems are self-governed and self-adaptive systems that are designed to operate in an open and evolving environment which is not completely defined at design time. This poses a unique challenge to the design and verification of dependable autonomous systems. Following the successful editions from previous years, DATE is again hosting the Initiative on Autonomous Systems Design on Tuesday, Thursday and Friday. The initiative will include peer-reviewed papers, invited contributions and interactive sessions.

 

 

ASD 2022 Program Overview 

---

Date: Tuesday, 15 March 2022 (online)

Panel Discussion: Autonomous Systems Design as a Research Challenge

Time: 16:30-18:00 CET 

Session Description: Autonomous systems require specific design methods that leave behavioral freedom and plan for the unexpected without losing trustworthiness and dependability. How does this requirement influence research at major research institutions? How is it reflected in public funding? Should autonomous systems design become a new discipline or should the regular design process be adapted to handle autonomy? The panel will begin with position statements by the panelists, followed by an open discussion with the hybrid audience.

Panelists: Karl-Erik Arzen, Lund University and co-director Wallenberg AI, Autonomous Systems and Software Program, Sweden;   Peter Liggesmeyer, Director Fraunhofer Institute for Experimental Software Engineering IESE, Germany;   Axel Jantsch, Director Institute of Computer Technology, TU Wien, Austria

Organizers:

• Selma Saidi, TU Dortmund, DE
• Rolf Ernst, TU Braunschweig, DE

 

---

Date: Thursday, 17 March 2022 (online)

 

Chair: Sharon Hu, University of Notre Dame, USA

Co-chair: Selma Saidi, TU Dortmund, DE

 

Session 1: Interactive Presentations Session

Time: 11:30-12:15 CET (Interactive Presentations Session)

 

Session Chair: Philipp Mundhenk, Robert Bosch GmbH, DE

Session Co-Chair: Rolf Ernst, TU Braunschweig, DE

• “Deadlock Analysis and Prevention for Intersection Management Based on Colored Timed Petri Nets”, Tsung-Lin Tsou, Chung-Wei Lin and Iris Hui-Ru Jiang, National Taiwan University, Taiwan

• “Attack Data Generation Framework for Autonomous Vehicle Sensors”, Jan Lauinger1, Andreas Finkenzeller1, Henrik Lautebach2, Mohammad Hamad1 and Sebastian Steinhorst1,  1Technical University of Munich, DE, 2ZF Group, DE

• “Contract-Based Quality-of-Service Assurance in Dynamic Distributed System”, Lea Schönberger1, Susanne Graf2, Selma Saidi1, Dirk Ziegenbein3 and Arne Hamann3, 1TU Dortmund University, DE, 2University Grenoble Alpes, CNRS, FR, 3Robert Bosch GmbH, DE

 

Lunch Keynote: "Probabilistic and Deep Learning Techniques for Robot Navigation and Automated Driving"

Time: 13:00 - 13:50 CET

      

• Wolfram Burgard, Technical University of Nuremberg, Germany

• Bio: Wolfram Burgard is a Professor for Robotics and Artificial Intelligence at the Technical University of Nuremberg. His interests lie in Robotics, Artificial Intelligence, Machine Learning, and Computer Vision. He has published over 400 publications, more than 15 of which received best paper awards. In 2009, he was awarded the Gottfried Wilhelm Leibniz Prize, the most prestigious German research award. In 2010, he received an Advanced Grant from the European Research Council. In 2021, he received the IEEE Technical Field Award for Robotics and Automation. He is a Fellow of the IEEE, the AAAI, the EurAI, and a member of the German Academy of Sciences Leopoldina as well as of the Heidelberg Academy of Sciences and Humanities.

• Abstract: For autonomous robots and automated driving, the capability to robustly perceive environments and execute their actions is the ultimate goal. The key challenge is that no sensors and actuators are perfect, which means that robots and cars need the ability to properly deal with the resulting uncertainty. In this presentation, I will introduce the probabilistic approach to robotics, which provides a rigorous statistical methodology to deal with state estimation problems. I will furthermore discuss how this approach can be extended using state-of-the-art technology from machine learning to deal with complex and changing real-world environments.

 

Session 2: An Industrial Perspective on Autonomous Systems Design (Industrial Session)

Time: 14:30-15:30 CET

Session Description This session presents 4 talks from industry sharing current practices and perspectives on autonomous systems and their design. The session discusses several challenges related to software architecture solutions for safe and efficient operational autonomous systems, novel rule-based methods for guaranteeing safety, and requirements on infrastructure for autonomy currently merging CPSs as well as IT domains.    

Session Chair: Rolf Ernst, TU Braunschweig, DE

Session Co-Chair: Selma Saidi, TU Dortmund, DE

• “Symbiotic Safety: Safe and Efficient Human-Machine Collaboration by utilizing Rules”,  Tasuku Ishigooka, Hiroyuki Yamada, Satoshi Otsuka, Nobuyasu Kanekawa and Junya Takahashi,  Hitachi, Ltd., JP
• “A Middleware Journey from Microcontrollers to Microprocessors”, Michael Pöhnl, Alban Tamisier and Tobias Blass,  Apex. AI, DE
• “Reliable Distributed Systems”, Philipp Mundhenk, Arne Hamann, Andreas Heyl and Dirk Ziegenbein, Robert Bosch GmbH, DE
• "PAVE 360 - A paradigm Shift in  autonomous driving verification with a  Digital Twin", Tapan Vikas, Siemens EDA GmbH, DE

 

Session 3: Bringing Robust Deep Learning to the Autonomous Edge: New Challenges and Algorithm-Hardware Solutions (Special Session)

Time: 15:40-16:30 CET

Session Description: Deep neural networks (DNNs) are being continually deployed at the autonomous edge systems for many applications, such as speech recognition, image classification, and object detection. While DNNs have proven to be effective in handling these tasks, their robustness (i.e. accuracy) can suffer postdeployment at the edge. Moreover, designing robust deep learning algorithms for the autonomous edge is highly challenging because such systems are severely resource-constrained. This session includes four different invited talks that present the challenges and propose novel, lightweight algorithm-hardware codesign methods to improve DNN robustness at the edge. The first paper evaluates the effectiveness of various unsupervised DNN adaptation methods on real-world edge systems, followed by selecting the best technique in terms of accuracy, performance and energy. The second paper explores a lightweight image super-resolution technique to prevent adversarial attacks, which is also characterized on an Arm neural processing unit. The third paper tackles the issue of loss in DNN prediction accuracy in resistive memory-based in-memory accelerators by proposing a stochastic fault-tolerant training scheme. The final paper focuses on robust distributed reinforcement learning for swarm intelligence where it analyzes and mitigates the effect of various transient/permanent faults.

Session Organizers: Kshitij Bhardwaj, Maya Gokhale and Bhavya Kailkhura, Lawrence Livermore National Lab (LLNL), USA

Session Chair: Dirk Ziegenbein, Robert Bosch GmbH, DE
Session Co-Chair: Chung-Wei Lin, National Taiwan University, Taiwan

Talks:

• “Unsupervised Test-Time Adaptation of Deep Neural Networks at the Edge: A Case Study”, Kshitij Bhardwaj, James Diffenderfer, Bhavya Kailkhura and Maya Gokhale,  Lawrence Livermore National Lab (LLNC Lab), USA
• “Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge”, Kartikeya Bhardwaj1, Dibakar Gope2, James Ward1, Paul Whatmough2 and Danny Loh1, 1ARM Inc,USA, 2ARM Research, USA
• “Fault-Tolerant Deep Neural Networks for Processing-In-Memory based Autonomous Edge Systems”, Siyue Wang, Geng Yuan, Xiaolong Ma, Yanyu Li, Xue Lin and Bhavya Kailkhura,  Northeastern University, USA, Lawrence Livermore National Lab, USA
• “FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systems”, Zishen Wan1, Aqeel Anwar1, Abdulrahman Mahmoud2, Tianyu Jia3, Yu-Shun Hsiao, Vijay Janapa Reddi2 and Arijit Raychowdhury1, 1Georgia Institute of Technology, USA, 2Harvard University, USA, 3Carnegie Mellon University, USA.

 

Session 4: Safe and Efficient Engineering of Autonomous Systems (Regular Session)

Time: 16:40-17:20 CET

Session Description: This session discusses novel approaches for engineering autonomous systems considering safety and validation aspects as well as efficiency. The first paper uses an ontology-based perception for autonomous vehicles which enables a comprehensive safety analysis, the second paper relies on formal approaches for generating relevant critical scenarios for automated driving. The last paper proposes an efficient method for recharging unmanned Aerial Vehicles (UAVs) to perform a large-scale remote sensing with maximal coverage.

Session Chair: Sebastian Steinhorst, Technical University Munich, DE

Session Co-Chair: Sharon Hu, University of Notre Dame, USA

Talks:

• “Using ontologies for dataset engineering in automotive AI applications”, Martin Herrmann1, Christian Witt2, Laureen Lake1, Stefani Guneshka3, Christian Heinzemann1, Frank Bonarens4, Patrick Feifel4 and Simon Funke3, 1Robert Bosch GmbH, DE, 2Valeo Schalter und Sensoren GmbH, DE, 3Understand AI, DE, 4Stellantis, Opel Automobile GmbH, DE. 
• “Using Formal Conformance Testing to Generate Scenarios for Autonomous Vehicles”, Jean-Baptiste Horel1,3, Christian Laugier1,3, Lina Marsso2, Radu Mateescu3, Lucie Muller3, Anshul Paigwar1,3, Alessandro Renzaglia1,3 and Wendelin Serwe3,  1Univ. Grenoble Alpes, FR, 2University of Toronto, CA, 3INRIA, FR.  
• “Remote Sensing with UAV and Mobile Recharging Vehicle Rendezvous”, Michael Ostertag, Jason Ma and Tajana Rosing, University of California, San Diego, USA

 

 

---

Date: Friday, 18 March 2022 (online)

For a detailed program of the ASD Friday Interactive Day please visit: https://www.date-conference.com/workshop/w10

 

Chair: Chung-Wei Lin, National Taiwan University, Taiwan

Co-chair:  Sebastian Steinhorst, Technical University of Munich, DE

 

Opening Session

Time: 08:30-09:30 CET

 

8:30 - 8:45: Opening of ASD Friday Interactive Day, Introduction of Sponsors

8:45 - 9:30: Keynote: Trustworthy Autonomous Systems Development

Keynote Speaker: Joseph Sifakis, Verimag Laboratory

Session Chair: Rolf Ernst, TU Braunschweig, DE

Abstract: Autonomous systems emerge from the needs to automate existing organizations by progressive replacement of human operators by autonomous agents. Their development raises multi-faceted challenges, which go well beyond the limits of weak AI.

We attempt an analysis of the current state of art focusing on design and validation.   
First, we explain that existing approaches to agent design are unsatisfactory. Traditional model-based approaches are defeated by the complexity of the problem, while solutions based on end-to-end machine learning fail to provide the necessary trustworthiness guarantees. We advocate "hybrid design" solutions that take the best of each approach and seek tradeoffs between trustworthiness and performance. In addition, we argue that traditional case-by-case risk analysis and mitigation techniques are failing to scale, and we discuss the trend away from correctness at design time and toward reliance on runtime assurance techniques. 
Second, we explain that simulation and testing remain the only realistic approach for global validation, and we show how current methods and practices can be transposed to autonomous systems by identifying the technical requirements involved.

We conclude by discussing the factors that will play a decisive role in the acceptance of autonomous systems, and by arguing for the urgent need for new theoretical foundations.

 

Session 1: Human-Machine Systems

Time: 09:30-10:45 CET

Session Description: The technology of autonomous vehicles continues advancing, but there will be a long time before human-driven vehicles are completely replaced by fully-autonomous vehicles. Therefore, mixed traffic environments need to be taken care of to provide safe, efficient, and comfortable transportation. In this session, the experts will discuss the roles of autonomous vehicles, human-driven vehicles, and roadside units and share their visions on human-machine systems. The ultimate goal is to support a smooth transition from current transportation to autonomous transportation.

Session Chair: Chung-Wei Lin, National Taiwan University

Agenda of Talks and Speakers/Panelists:

• 09:30 - 09:45: "Towards Cooperative Autonomous Vehicles for Mixed Traffic Environments", Shunsuke Aoki, National Institute of Informatics, JP

• 09:45 - 10:00: "Automation as a Service Provider for Shared Mobility", Meike Jipp, German Aerospace Center (DLR), DE

• 10:00 - 10:15: "Human-Like Autonomous Driving and Human-Machine Systems", Chen Lv, Nanyang Technological University, SG

• 10:15 - 10:45: Interactive panel discussion on Human-Machine Systems

 

Session 2: Hardware and Components

Time: 11:00-12:15 CET

Session Description: For the design of autonomous systems, powerful hardware and system components are as much a core enabler of advanced autonomy as the software running on them. With the increase in cognitive capabilities by integration of computation and sensing platforms, many opportunities as well as challenges arise, such that both hardware and AI-centric software can operate fully synergetic and, hence, reach their full potential. The purpose of this session is to discuss the latest trends in hardware components and their design aspects for efficient and holistic integration of computation, sensing and communication.

Session Chair: Sebastian Steinhorst, Technical University of Munich

Agenda of Talks and Speakers/Panelists:

• 11:00 - 11:15: "PULP: An Open Ultra Low-Power Platform for Autonomous Nano Drones", Luca Benini, ETH Zürich, CH
• 11:15 - 11:30: "Challenges & Solutions for Next-Generation E/E Architectures", Bart Vermeulen, NXP, NL
• 11:30 - 11:45: "Efficient Machine Learning: Algorithms-Circuits-Devices Co-design", Hai (Helen) Li, Duke University, US
• 11:45 - 12:15: Interactive panel discussion on Hardware and Components

 

Session 3: Panel Discussion "Autonomous Systems Design"

Time: 13:30-15:00 CET

Organizers:

• David Harel, Weizmann Institute of Science
• Joseph Sifakis, Verimag Laboratory

Moderator:

• David Harel, Weizmann Institute of Science

Panelists:

• Sandeep Neema, DARPA
• Alberto Sangiovanni-Vincentelli, UC Berkeley
• Carlo Ghezzi, Politecnico di Milano
• Simon Burton, Fraunhofer
• Michael Paulitsch, Intel
• Arne Hamann, Bosch

 

Topics to be discussed by the panel:

1) What is your vision for AS? For example, the role of these systems in the IoT and AI revolutions; autonomy as a step from weak to strong AI; the gap between automated and autonomous systems.

 2) What challenges do you see in AS design? For example, AI-enabled end-to-end solutions; "hybrid design" approaches, integrating model- and data-driven components; systems engineering issues.

3) How should we ensure the reliability of AS? For example, achieving explainable AI; adapting and extending rigorous V&V techniques to ASs; ensuring safety based exclusively on simulation and testing.

4) Looking to the future, is the vision of total autonomy viable? how can we make it happen? For example, decisive factors for acceptance; research challenges; ethical issues; "easy" total autonomy categories.

 

Session 4: V2X, Edge Computing, and Connected Applications

Time: 15:10-16:50 CET

Session Description: Connectivity realizes many advanced applications for vehicles. Especially, the interactions between vehicles and edge servers (or roadside units) further boost the trend and involve more players in the business. In this session, the experts from an auto-maker, a supplier, a high-tech company, and a start-up will meet together, describe their roles in the connected and edge-computing environment, and discuss potential integration or competition.

Session Chair: Dirk Ziegenbein, Robert Bosch GmbH

Agenda of Talks and Speakers/Panelists:

• 15:10 - 15:25: "Video Uberization Using Edge AI and Mobile Video", Chun-Ting Chou, OmniEyes, TW
• 15:25 - 15:40: "Connected Applications as Driver for Automation", Frank Hofmann, Bosch, DE
• 15:40 - 15:55: "Environmental parity between cloud and embedded edge as a foundation for software-defined vehicles", Stefano Marzani, Amazon, US
• 15:55 - 16:10: "Mobility Digital Twin with Connected Vehicles and Cloud Computing", Ziran Wang, Toyota Motor North America R&D, US
• 16:10 - 16:50: Interactive panel discussion on V2X, Edge Computing, and Connected Applications

 

---

 

Information from Call for Contributions

 

Areas of Interest

We welcome your contributions within the scope of the event. The main areas of interest include but are not limited to the following:

• Concepts, Algorithms and Formal Methods for Autonomy

• Platforms for Autonomous Systems
  •  Architectures (from Chip Level to System Level) for Autonomous Systems
  • Middleware and Frameworks (e.g. ROS) for Autonomous Systems
  • Models and HW/SW Mechanisms for Self-Awareness and Self-Adaptation

• Design of Autonomous Systems
  • Mastering Emergent and Evolving Behavior (Goals, Constraints, ...)
  • Design, Verification and Test of High-Assurance Learning-Enabled Systems
  • Design Automation and Methodologies for Autonomous Systems

• Dependability and Trustworthy Autonomy
  • Functional Safety and Assurance Cases for Evolving and Learning-Enabled Systems
  • HW/SW Mechanisms for Resilient Systems
  • Autonomous Systems Security

• Applications and Case Studies of Autonomous Systems

 

Types of Contributions

 

Conference Papers:

The special initiative features regular sessions for presenting novel technical contributions. Submitted papers will undergo a peer-review process and accepted papers will appear in the DATE conference proceedings. All manuscripts should be submitted in pdf format not exceeding 6 pages for standard oral presentation and 4 pages for interactive presentation, following the DATE submission instructions.

Abstract Submission:  12 September 2021

Full Paper Submission:  19 September 2021

Acceptance Notification:  11 November 2021 

 

Special Sessions / Panels:

We additionally solicit proposals for special sessions, panel discussions and invited talks, targeting emerging challenges in the field of autonomous systems, especially that are of interest to the DATE conference participants. Special Session proposals must consist of an extended summary of up to 1,500 words in a PDF file, describing the topic, the authors/speakers, and the intended format. Submission deadline is 21 September 2021.

 

Submission Instructions

All submissions should follow the DATE proceedings submission instructions.

Please submit your contribution at: https://www.softconf.com/date22/special_ASD/

 

Friday Interactive Day  Contributions 

The Friday Interactive Day will feature highly interactive sessions on emerging or controversial hot topics in the scope of the ASD initiative.

We also encourage sessions on business trends or public policies. The form of a session can be a special session with invited talks and panel discussions, leaving enough room for interaction among the participants. Sessions on industrial perspectives, prototypes and demos are also highly welcome. Please send the proposals via email with the subject #ASD2021 to the organizers Chung-Wei Lin (cwlincsie [dot] ntu [dot] edu [dot] tw) and Sebastian Steinhorst (sebastian [dot] steinhorsttum [dot] de).

 

Thursday Chairs:

• X. Sharon Hu, University of Notre Dame, USA
• Selma Saidi, Technical University Dortmund, Germany

 

Friday Chairs:

• Chung-Wei Lin, National Taiwan University, Taiwan
• Sebastian Steinhorst, Technical University Munich, Germany

  

Organizing Committee:

• Rolf Ernst, Technical University of Braunschweig, Germany
• Dirk Ziegenbein, Robert Bosch GmbH, Germany
• Selma Saidi, Technical University Dortmund, Germany
• Sebastian Steinhorst, Technical University Munich, Germany