Discover the tracks of BrabantHack_26​​​​​​​​

At BrabantHack_26, you’ll take on real AI challenges from leading companies and societal organizations.

In a short time, participants build AI solutions that can make an impact in a varienty of sectors.

All tracks are live. Pick your challenge and start building.

TRACK DEEP TECH

Detecting early movement with AI-powered shadow analysis

Traditional detection systems only respond once a person physically enters the frame, losing precious reaction time in moments where every second counts. This challenge flips that limitation into possibility by pushing computer vision to work with indirect evidence: the shadow. By decoding these subtle traces of movement, AI is pushed to predict a person’s presence and intent before they appear on camera, marking an important step toward proactive safety in autonomous vehicles and intelligent surveillance systems.

Challenge

You’ll dive into synthetic shadow-only data and push AI to turn shadows into precise early warning signals: how can we use AI and synthetic data to detect people based on their shadows, even before they appear in view? 

TRACK DEFENCE

AI for advanced malware reconstruction

Python‑based malware is becoming more common because it’s easy to develop, works across platforms, and can be heavily obfuscated. This makes the underlying logic difficult to analyze. AI offers new opportunities to recognize patterns in distorted code and uncover hidden behavior, raising the question of how far these capabilities can really go.

Challenge

In this track, you’ll step into the complexity of modern cyber defense: How can AI models assist in analyzing and reconstructing obfuscated Python malware, so threats can be understood and neutralized more quickly?

TRACK MED TECH & LIFE SCIENCES

AI for smarter acces to cancer information

People increasingly turn to general AI systems for cancer information because they are quick and easy to use, but the results are not always reliable. At the same time, trusted cancer knowledge is spread across different platforms, which makes it harder for patients, professionals, and policymakers to find accurate and consistent information when they need it.

Challenge

In this track, you’ll explore how AI can connect and unlock trusted knowledge sources: How can we make reliable cancer information faster and smarter to access by using AI to connect different sources of knowledge?

TRACK AI-TECH

Creating impactful robotics with AI for risk-reducing work

Every day, people go to work in environments that are dangerous, physically demanding, or repetitive. They perform tasks for hours on end that wear them down, mentally, physically, and sometimes at the cost of their health and safety. This track is built around one clear mission: leave it to the robot. With integrated AI, autonomous robots can take over tasks that no human should have to perform anymore.

Challenge

In this track, you’ll design and build a solution for the challenge: how can autonomous robots powered by AI take over tasks that are dangerous, physically demanding, or repetitive, and help create safer working environments?

TRACK PLANT-BASED 1

Developing an intelligent warning system to prevent invasive weed spread

Invasive weed spread has a major impact on agricultural fields. Once these weeds take hold, they can damage crops, disrupt ecosystems, and drive up costs for people in the area. This track challenges you to rethink how we detect and respond to early signs of infestation by using AI as the digital eyes and ears of the landscape. Building something that helps farmers and contractors get timely alerts so they can act before the problem grows.

Challenge

In this track, you’ll design and prototype a smart, area-based alerting system: how can we use AI to detect and prevent the spread of invasive weeds by turning local observations into a smart, real-time warning system for farmers and other stakeholders? 

TRACK PLANT-BASED 2

Building a real-time detection system for potato harvest damage

During potato harvesting, damage, soil clumps, and stones often pass unnoticed as they move through the machine. By the time these issues surface, quality has already dropped, yields are affected, and costs are rising. Without real-time insight on the harvester, growers and contractors have no clear view of where problems originate in the field or how to adjust operations when it matters.

Challenge

Put an end to the ‘black box’ of potato harvest by designing an AI-driven detection system that brings clarity to the harvesting process: how can AI help improve potato harvesting by detecting damage, soil clumps and stones in real time, and linking this to location data for better decision-making?

Less Talk. More Hack.

Pick a challenge and register for BrabantHack_26!