Robotics + GPU
Action, language, and acceleration
PhD work connecting iCub humanoid learning, action structure, neural networks, CUDA, Aquila, and ESA rover-control research.
Robotics workPersonal legacy archive
Robots, cameras, coordinates, and place.
A life spent making ideas answer to the physical world.
What began as a stubborn dream of robots became a life in embodied AI, GPU computing, cameras, mapped space, and finally a place shaped by return.
I made this so the life, the work, and the places would stay together.
Robots, cameras, coordinates, and place. This archive keeps the work close to the lived life: Plymouth, iCub, ESA, NVIDIA, TEDx Bratislava, applied vision, spatial systems, and Tao.
TEDx Bratislava
The first public telling of the whole route: leaving Slovakia, rebuilding through study in Plymouth, entering robotics, discovering GPU computing, and keeping hold of the dream that intelligence must answer to the physical world.
Watch TEDxBegin here
Work
ESA rover simulation, iCub learning, CUDA experiments, edge cameras, spatial calibration, and Tao: each period tests perception against something physical.
Robotics + GPU
PhD work connecting iCub humanoid learning, action structure, neural networks, CUDA, Aquila, and ESA rover-control research.
Robotics work
Applied vision
Camera-as-computer prototypes, edge inference, synthetic worlds, and the pressure of making ideas work outside the lab.
Camera work
Spatial intelligence
Multi-camera calibration, floorplane reasoning, uncertainty, topology, and the work of making observations belong to the same world.
Spatial workTao
Tao is where the work becomes land, water, paths, structures, gardens, seasons, memory, and care.
Over years, rough land became water, paths, planting, structures, and care.
Lineage
The tools changed from rover simulators and humanoid robots to camera systems, mapped spaces, and land. The recurring question stayed concrete: what is here, where is it, and what still works after contact with the world?
Autonomy and sensing against terrain, uncertainty, and planetary-robotics constraints.
Action, language, neural dynamics, body constraints, and GPU-accelerated experiments.
Early large-scale GPU robotics work made visible through CUDA, GTC, and public talks.
Perception systems moved outside the lab into edge devices, workflows, and real-world pressure.
Cameras become more useful when observations share coordinates, topology, and uncertainty.
Land, water, paths, structures, seasons, repair, and memory.