Projects

Nodalsys has a portfolio of applied AI projects built around one central idea: intelligent systems should not merely recognize data — they should help interpret situations, reduce uncertainty, and improve outcomes.

Our projects explore how AI, computer vision, and contextual analysis can be applied to real-world problems. The projects presented below are diverse: vehicle-system integrity, road-surface assessment, intersection awareness, nutrition guidance, conversational support, and quality grading. Their domains differ, but their underlying logic is the same: observe the situation, extract meaningful signals, assess context, and support better decisions.

In mobility and safety, this includes systems such as onboard steering-integrity awareness, AI-assisted road-surface assessment, and high-level intersection context analysis.

These concepts show how visual and sensor-based information can be transformed into practical awareness: detecting abnormal conditions, identifying risk factors, helping operators respond before a problem becomes critical, and reducing the risk of catastrophic outcomes.

System diagram :

System diagram:

System diagram:

System diagram:

System diagram:

System diagram:

System diagram:

AI-Driven Road Surface Assessment

AI for interpreting road conditions, surface risks, and adaptive driving context.

This project focuses on AI-assisted systems capable of analyzing road surfaces and surrounding driving conditions in real time. Instead of only detecting visible objects, the system evaluates surface state, traction risk, debris, weather influence, road geometry, and the relationship between the vehicle and its immediate environment.

The goal is to move beyond basic road recognition toward structured surface awareness. An AI-driven road surface assessment system can help identify when driving conditions are stable, when grip is becoming uncertain, and when the driver or vehicle-control system may need additional support.

By interpreting wet surfaces, reduced traction zones, debris, and evolving road context, the system creates a higher-level awareness layer that can support safer decision-making, adaptive alerts, fleet monitoring, or future intelligent driving systems.

Core value: transforming changing road-surface conditions into usable driving intelligence.

System diagram:

Onboard Steering Integrity Awareness System

AI-assisted monitoring for vehicle steering-system integrity.

This project explores how AI can support the detection of potential issues in critical vehicle steering components. The system concept is to learn from the systems vibrations, identify the risk zones, and correctly link them to the components physical states. The system sructured risk interpretation and treshold enforcement helps identify abnormal patterns before they become serious mechanical or safety problems and enable the driver/ operator to act on the situation.

The objective is to monitor states in real time , to create an intelligent awareness layer around steering integrity. Such a system could support fleet operators, maintenance teams, or safety-critical vehicle applications by creating more precise profiles of actually hidden mechanical risks thus making them more visible, traceable, and therefore drive and priorise design changes. that reinforce vehicule safety though the products complete lifespans.

Core value: turning mechanical condition signals into earlier, clearer safety awareness.

System diagram:

System Diagram:

System diagram:

AI-Powered Quality Grading

Computer vision and structured assessment for consistent product evaluation.

This project explores how AI can support quality grading by analyzing visible product characteristics such as size, shape, color, condition, defects, maturity, or consistency. The concept is especially relevant for food systems, agriculture, manufacturing, and inspection environments where visual variation must be evaluated reliably.

The system is designed to reduce subjectivity and improve traceability in quality assessment. Rather than relying only on manual judgment, AI can help organize visual evidence, apply consistent criteria, and support better decisions in sorting, grading, pricing, or process control.

Core value: making quality assessment more consistent, explainable, and scalable.

 Vegan Nutrition Adviser

AI-assisted nutritional guidance based on user context and dietary structure.

The Vegan Nutrition Adviser explores how conversational AI can help users understand food choices, nutritional balance, meal structure, and potential dietary gaps. The system is designed around guidance, not generic advice: it considers user preferences, dietary patterns, goals, and practical constraints.

This project demonstrates how AI can support health-oriented decision-making in a calm, structured, and accessible way. It can help users ask better questions, organize food information, and receive clearer explanations about nutrition without being overwhelmed by fragmented online content.

Core value: Making nutritional reasoning clearer, more personalized, and easier to apply.

High-Level Context Awareness Agent

AI for interpreting complex scenes, risks, and operational context.

This project focuses on context-aware AI systems capable of analyzing dynamic environments such as intersections, traffic zones, public spaces, or operational areas. Instead of only detecting isolated objects, the system evaluates relationships between elements: movement, position, risk level, timing, and situational meaning.

The goal is to move beyond basic recognition toward structured situational understanding. A context awareness agent can help identify when a scene is normal, when risk is increasing, and when a human or automated system may need additional support.

Core value: transforming visual complexity into usable situational intelligence.

System diagram:

Website created in the WebWave website builder