
Real-time bowling pin detection
A complete edge-computer-vision system that detects a throw and counts standing pins across two bowling lanes.
Read case study ↗AI / ML
Published research, client systems and transparent work in progress.
Client applications
02
A complete edge-computer-vision system that detects a throw and counts standing pins across two bowling lanes.
Read case study ↗
An implementation of a split-and-merge method that recursively divides an image according to local variance to reveal homogeneous regions.
View project ↗Research
03
A neuro-symbolic framework that learns executable PDDL action models from raw visual traces—even when observations are noisy or incomplete.
Read case study ↗
A transparent experimental pipeline for isolating the price impact of large orders and discovering compact differential equations that describe it.
Read case study ↗
A neuro-symbolic framework for non-Markovian reinforcement learning that jointly learns symbol grounding from images and the temporal reward structure.
View project ↗