Patrik Zips

TU Wien, Austrian Institute of Technology

Papers

Total Citations

H-Index

About

Patrik Zips is a researcher working at the intersection of autonomous systems, robotics, and artificial intelligence, with particular expertise in motion planning, computer vision, and neurosymbolic learning. His most influential contribution, "Optimisation based path planning for car parking in narrow environments" (2016), has garnered 73 citations and remains a landmark work in autonomous vehicle navigation, demonstrating elegant solutions to the geometrically complex problem of maneuvering in constrained spaces — a challenge central to real-world deployment of self-driving systems. Building on this foundation, Zips has expanded his research into robotic automation and perception, developing vision-based methods for pallet recognition that leverage synthetic training data to overcome occlusion challenges in industrial workflows. His more recent work ventures into neurosymbolic AI, where he proposes architectures that fuse symbolic planning with reinforcement learning to enable continual task-and-motion planning in unpredictable open-world environments — a frontier problem in achieving truly adaptive autonomous agents. Across his career, Zips has consistently tackled practical, high-stakes challenges in autonomous systems, bridging classical optimization approaches with modern machine learning. His work appeals to researchers in robotics, autonomous vehicles, and AI planning who seek principled, deployable solutions to real-world complexity.