AviSense is proud to announce a significant milestone: the successful completion of our participation in the ESA BIC Greece incubation program. This week, we officially received our ESA BIC Greece Graduation Certificate, marking the conclusion of an important chapter in our growth and the beginning of an even more ambitious one.

The support, mentorship, and resources provided by ESA BIC Greece have been instrumental in accelerating our progress in the field of intelligent and trustworthy autonomous mobility solutions. Their guidance has empowered our team to push technological boundaries and strengthen our innovation roadmap.

As part of the graduation activities, AviSense participated in the ESA BIC Greece Networking Event—an exceptional opportunity to engage with pioneering startups, industry leaders, and strategic partners who are shaping the future of space-related technologies. The exchange of ideas and the collaborative spirit present at the event were both energizing and inspiring.

We extend our sincere appreciation to the ESA BIC Greece team for cultivating a dynamic innovation ecosystem, and we thank everyone who has supported AviSense throughout this journey. We look forward to the next phase of our mission, with new initiatives and advancements already underway.

Between 15 and 17 October, our team from AviSense.ai traveled to Madrid to participate in field trials at the 5TONIC testbed, as part of the 6G-XR project.
Within the framework of SafeDriveXR – “Robotic Autonomous Agents with Cognitive Enhancements over 6G”, we successfully tested and validated key components of our 5G/6G-enabled system, which integrates Cooperative Intelligent Transport Systems (C-ITS) with Extended Reality (XR) interfaces for Connected and Automated Vehicles (CAVs).

Our objective is to enhance road safety by enabling real-time XR visualizations of traffic, road conditions, and potential hazards — improving driver awareness, decision-making, and response times.

The 5TONIC trials (South Node of the 6G-XR Facilities) represent a major milestone in demonstrating low-latency communication, edge-cloud coordination, and adaptive XR interfaces responsive to user context.

We’re proud to contribute to Europe’s vision for Cooperative, Connected, and Automated Mobility (CCAM), and deeply grateful to our partners and the 6G-XR community for their collaboration and support throughout this phase of the project.

We are proud to announce that our research paper, “Integrated Simulation Framework for Adversarial Attacks on Autonomous Vehicles,” was presented at the IEEE International Smart Cities Conference (ISC² 2025) — https://isc2-2025.org/.

The paper introduces an integrated simulation framework designed to evaluate the robustness of autonomous vehicles against adversarial attacks targeting perception, control, and communication layers. As autonomous driving technologies rapidly evolve, understanding how malicious interventions can affect their behavior becomes critical to ensuring the safety, reliability, and trustworthiness of AI-driven mobility systems.
Our framework bridges simulation environments, AI models, and cybersecurity analysis tools to enable reproducible experiments and stress testing under realistic conditions.
This multidisciplinary approach provides researchers and developers with a flexible testbed to explore vulnerabilities, mitigation strategies, and adaptive defense mechanisms for connected and autonomous vehicles (CAVs).

This research has been developed within the Horizon Europe project GuardAI, which focuses on building trustworthy, secure, and human-aligned AI systems for critical applications across Europe.

Presenting at ISC² 2025 provided an excellent opportunity to share our findings with the international smart cities and AI safety community, and to discuss how adversarial resilience can be integrated into next-generation mobility infrastructures.

We would like to thank our collaborators and project partners for their valuable contributions and continued support. Together, we are moving toward a safer and more resilient AI ecosystem for autonomous transportation.

Conference: IEEE International Smart Cities Conference (ISC² 2025)
Paper: Integrated Simulation Framework for Adversarial Attacks on Autonomous Vehicles
Funding: Horizon Europe Project GuardAI
More information: https://isc2-2025.org/

We’re excited to unveil our latest NavMap prototype, a cutting-edge solution that brings real-time Cross-View Localization to a new level of accuracy and accessibility. By fusing satellite imagery, HD maps, and ground-view sensor data, NavMap enables vehicles and mobile platforms to pinpoint their location with centimeter-level precision—even where traditional GPS fails. NavMap is built to address today’s toughest localization challenges: urban canyons, tunnels, indoor environments, and GNSS-denied zones. Whether you’re an OEM, ADAS developer, or surveyor, our flexible, AI-powered platform is designed to deliver performance, speed, and reliability at scale.

Its key features include:

• Locate where others can’t – high accuracy in GNSS-denied or degraded environments
• Save time and cost with minimal sensor setup, no complex cabling or calibration
• Precision localization directly on mobile phones and tablets – no bulky setups
• User-friendly interface for effortless operation in the field
• Advanced situational awareness and real-time collaboration between users

NavMap in Action – Real-World Applications:

• Urban Navigation for Autonomous Vehicles:
  Navigate confidently through city streets, tunnels, or parking garages where GPS signals are weak or blocked.
• Ground-Truth Data Collection for ADAS Testing:
  Generate highly accurate reference data during on-road or indoor tests, helping development teams validate and improve autonomous functions.
• Survey Mapping & Infrastructure Inspection:
  Enhance the accuracy of drone or ground-based surveys by integrating cross-view data for better geo-referencing and scene understanding.
• Emergency Response & Defense Applications:
  Enable reliable positioning for first responders and field units in GPS-compromised areas, such as disaster zones or contested terrains.
• Fleet Management in Complex Environments:
  Support logistics and utility vehicle fleets in ports, warehouses, or dense urban areas where traditional tracking solutions fall short.
• Research & Academic Pilots:
  Accelerate the development and testing of localization algorithms using a plug-and-play, scalable platform.

Whether you’re developing smart mobility solutions, building autonomous systems, or mapping uncharted environments—NavMap is your foundation for precise positioning!

We are proud to announce that Avisense.AI participated in the prestigious IEEE International Conference on Multimedia & Expo (ICME) 2025, held in Nantes, France, from June 29 to July 4. Our team had the honor of presenting two peer-reviewed papers at the 3D Multimedia Analytics, Search and Generation Workshop, both accepted for oral presentation a significant milestone that highlights the impact of our research in the field of autonomous systems and multimodal analytics.

Advancing Multi-Object Tracking with Graph Signal Processing

Maria Damanaki presented our work titled
“Optimizing Cooperative Multi-Object Tracking using Graph Signal Processing”,
co-authored by Nikos Piperigkos, Alexandros Gkillas, and Aris Lalos.

In this paper, we propose a novel cooperative multi-object tracking (MOT) framework for 3D LiDAR scenes. The approach formulates and solves a graph topology-aware optimization problem to intelligently fuse data from multiple vehicles. Leveraging a fully connected graph topology defined over detected bounding boxes, we apply Graph Laplacian Processing to smooth positional errors and enhance detection fusion.

This results in robust object association and improved tracking accuracy across agents. The framework was rigorously evaluated on the V2V4Real dataset, significantly outperforming baseline and state-of-the-art methods, including DMSTrack and V2V4Real’s internal baselines.

Redefining LiDAR Efficiency with Guided Super-Resolution

Nikos Piperigkos presented the second paper, titled
“Guided Model-based LiDAR Super-Resolution for Resource-Efficient Automotive Scene Segmentation”,
co-authored by Alexandros Gkillas and Aris Lalos.

This work introduces the first end-to-end framework that integrates LiDAR super-resolution (SR) with scene segmentation. By jointly optimizing both tasks during training, our method ensures that the SR network is guided semantically by the segmentation process, preserving important structural details—especially for smaller object classes.

Key innovations include a lightweight, model-based SR architecture with a novel loss function focused on regions of interest. The framework achieves segmentation performance comparable to high-resolution 64-channel LiDAR setups, but with dramatically lower computational cost and fewer parameters.

Best Presentation Award

We are especially proud to share that Nikos Piperigkos received the Best Presentation Award for his excellent delivery and impactful research contribution.

A heartfelt thank you to the ICME 2025 organizers and the vibrant research community that continues to push the boundaries of AI, multimedia processing, and autonomous systems. Events like ICME foster collaboration, innovation, and the exchange of ideas that shape the future of intelligent perception.

Stay tuned as we continue our mission at Avisense.AI to transform advanced research into scalable, real-world solutions.