Explainability of Real-Time Systems and their Analysis (ERSA)

2nd International Workshop on Explainability of Real-time Systems and their Analysis at the IEEE Real-Time Systems Symposium (RTSS 2023) in Taipei, Taiwan

Today, almost all verification techniques provide answers to questions but do not provide explanations. We will address that.

Important dates

Program Chairs

Program Committee


Location: Room CR-405 on the 4th floor at Howard Plaza Hotel. Details from RTSS about the venue are here.

Link to workshop proceeding is here.

09:00am Welcome
Bjorn Andersson
Chi-Sheng (Daniel) Shih
09:05am Keynote
(Remote) George Romanski, "Use of compelling safety arguments for Integrated Modular Avionics systems"
09:50am Update from ASERT working group
Dionisio de Niz
09:55am Summary of previous year
Bjorn Andersson
10:00am Coffee break
10:30am Session 1: Certificates
Session chair: Bjorn Andersson
Sanjoy Baruah and Pontus Ekberg, "Efficient Explainability of Real-Time Schedulability"
Raffaele Romagnoli, "Explaining Quadratic Boundedness for Latency Mitigation and Safety Assurance in Edge-Cloud Computing"
11:15am Session 2: Understanding
Session chair: Chi-Sheng (Daniel) Shih
Ruben Martins, "Transforming Logic into Language Bridging the Gap with Large Language Models"
Muhammad Tanveer Ali Ahmad, Jesus Pestana, Leandro Batista Ribeiro, and Marcel Baunach, "Budget-Based Explainable Schedulability Analysis for Automotive Applications"
11:59am Lunch
01:30pm - 03:00pm Session 3: Safety, certification, and explainability of autonomous cars
Session chair: Bjorn Andersson
Invited talks
Paul Yeh, "Testing Self-Driving cars and its difficulties," Tier IV Inc.
Chi-Sheng (Daniel) Shih, "The Art of Open Source - Reimagines Intelligent Vehicles"
Huei-Ru Tseng, "Bus ODD and Autonomous Bus projects in Taiwan," ITRI
Panelist: Paul Yeh, Chi-Sheng (Daniel) Shih, and Huei-Ru Tseng 

Paper submission

Workshop website: https://sites.google.com/view/ersa23

Format: Extended abstract or position papers to define the area, up to 4 pages, IEEE Manuscript Template Conference Proceedings

Online submission: https://easychair.org/conferences/?conf=ersa23

If your travel to the workshop requires visa and you need a letter and the schedule for this is tight, please indicate that as a keyword in Easychair during your submission.

Motivation, Goal, and Topics

Background: Many software-intensive systems of current and future application domains require (or will require) approval from a certification authority before being deployed. Examples of such application domains include: aircraft, medical devices, spacecraft, autonomous ground vehicles, autonomous air vehicles. Examples of current certification authorities include: Federal Aviation Administration, European Union Aviation Safety Agency, Food and Drug Administration.

Current pain: Today, each established application domain has a set of guidance documents. These tend to be process-oriented; i.e., (i) prescribe how the development of the system should proceed, (ii) how the applicant (the organization that develops the system) should communicate with the certification authority, (iii) state high-level objectives, and (iv) state pitfalls that should be avoided. This mindset has been successful in many domains. For example, among US air carriers, the safety record today is much better than it was decades ago. Unfortunately, this mindset also has some limitations. These include: (i) limitations for future application domains, (ii) limitations on permitting frequent and late changes, (iii) limitations on being process-driven rather than focusing on direct evidence of the safety of the software, and (iv) not taking full advantage of the research within the real-time systems research community: the knowledge of the real-time systems community is not present in these documents and these documents do not cite papers from the real-time systems research community. Achieving safety through extensive testing appears to be problematic because it precludes frequent and late changes. Achieving safety through models fed into verification techniques requires tool qualification. Thus, it is worth exploring alternatives, specifically exploring (i) whether explainability can help, (ii) what explainability means, and (iii) how it can be achieved for real-time systems. 

Goal: The goal of this workshop is to understand the role, meaning, and value of explanation in critical systems—in particular real-time systems.

Past Edition: https://sites.google.com/view/ersa22

Non-Exhaustive List of Topics