The CAIESA workshop, addresses a timely cross-disciplinary topic at the intersection of artificial intelligence, embedded systems, and cyber-physical systems (CPS). The increasing integration of AI into embedded and edge platforms enables new levels of autonomy and intelligence but also introduces fundamental challenges that require a joint hardware/software and system-level perspective.
The workshop focuses on challenges arising from integrating AI into embedded and cyber-physical systems, combining methodological advances with application-driven requirements.
Application perspectives span key domains such as autonomous systems and autonomous driving, industrial automation and Industry 4.0 (including digital twins), smart farming, robotics, smart infrastructure and IoT, and medical devices. The workshop encourages interdisciplinary contributions, including research papers, industrial experience reports, and position papers linking application requirements with system-level challenges.
The rapid deployment of AI in embedded and cyber-physical systems across domains such as autonomous systems, industrial automation, robotics, and healthcare is transforming system design. However, this shift introduces challenges not fully addressed by existing methodologies, including the integration of data-driven AI with deterministic system behavior, ensuring safety and certification, operating under strict resource constraints, and guaranteeing robustness and security in real-world environments. Addressing these challenges is essential for the next generation of intelligent embedded systems and directly aligns with ESWeek’s focus. The workshop will identify open research problems, promote interdisciplinary collaboration, and strengthen connections between academia and industry.
The workshop is planned as a full-day event on October 9th, 2026. The workshop aims to balance technical presentations with interactive discussion to foster exchange between academia and industry and to identify open research challenges.
The workshop is organized as an IFIP-sponsored workshop, with proceedings published in the Springer IFIP Advances in Information and Communication Technology (AICT) series. All submissions will undergo peer review, and accepted papers will be included in the official proceedings, organized independently from ESWeek.
09:15 - 09:30 Opening remarks by workshop organizers
09:30 - 10:30 Keynote "Functional Safety of AI-enabled Edge Systems" given by Francisco J. Cazorla Almeida
and Enrico Mezzetti from Barcelona Supercomputing Center
10:30 - 11:00 Coffee Break
11:00 - 12:35 Session 1, "Embedded Systems", Session Chair: Kristian Rother
- Static Pessimistic Execution-Time Estimation for CUDA Kernels on NVIDIA Ampere GPUs, Ali
Alhalabi, Stefan Henkler, Domenic Drechsel and Achim Rettberg
- A Timing Observability approach for Conventional and AI-Based Autonomous Driving
Applications, Saran Deepak Elumalai Vijaya Nirmala Devi, Niklas Rahenbrock and Gregor
Nitsche
- PPO-Based PID Gain Scheduling for Hexapod-Leg Control under Varying Gravity, Ashton
Mitchell, Aditya A. Krishnan and Hokeun Kim
- Deep Learning--Based Prediction of Communication Latency and Temporal Anomalies in ROS 2
Systems, Leticia Pinto, Marco Wehrmeister and André Lazzaretti
- Evaluating Saliency Methods for Selective Tile Processing on Embedded Object Detectors,
Andreas Vasiliou and Theocharis Theocharides (short paper)
12:30 - 13:30 Lunch Break
13:30 - 15:00 Session 2, "Analysis", Session Chair: Fatima Idrees
- Resource-Efficient Embedded Radar-Based Elderly-care Activity Recognition via Dual-Branch
Receptive-Field Learning, Xiangbo Kong, Akari Takebayashi, Kenshi Saho and Kazuhide Kamiya
- Multi-Resolution Semantic Region Discovery in Embedded Operating-System Repositories,
Kristian Rother
- Toward Tamper-Resistant Traffic-Sign Recognition: A Concept for Multi-Channel Redundant Sign
Coding in Safety-Critical AI-Based Embedded Vehicle Systems, Samer Telawi
- Prompt-to-Drive: Closed-Loop AI-Driven Scenario Synthesis and Verifier-Sensitive Semantic
Alignment for Autonomous Driving Simulation, Narmada Ambigapathy, Fatima Idrees, John
Abah, Ali Alhalabi and Achim Rettberg (short paper)
- Property Refinement in Computation Tree Logic, Luca Brodo, Giuseppe Scalora and Stefan
Henkler (short paper)
15:00 - 15:30 Coffee Break
15:30 - 16:45 Session 3, "AI", Session Chair: Ali Alhalabi
- Multi-Tool Selection for Robotic Systems: Comparing Semantic Retrieval and Large Language
Models, Miguel Sousa, Luis Ramos Pinto and João Carvalho
- Quantized U-Net for Low-Latency Sugar Beet Segmentation in 5G-Enabled Edge Cyber-Physical
Systems, Viktoria Sorokina, Dzmitry Yablonski and Dmitry Dementiev
- Towards Safety and Validation of Virtualized Automotive Controllers via a Modular Testbed with
Supervisory Monitoring and Standards-Aligned Fault Injection, Fatima Idrees, Naved Afridi
Rashiq, Moiz Zaheer Malik, Narmada Ambigapathy and Achim Rettberg
- Application and Evaluation of Machine Learning on Embedded Devices: A Case Study on Solid
Waste Classification Using TinyML, Maxwell Rodrigues da Silva, Fatima Idrees, Marcelo Götz and
Achim Rettberg (short paper)
16:45 - 17:00 Closing by workshop organizers
AI Website Software