Luc Holzherr

Papers

Total Citations

H-Index

About

Luc Holzherr is a roboticist whose research lies at the intersection of decision-making under uncertainty and autonomous mobile manipulation. His primary contributions focus on developing computationally tractable solutions for complex, real-world robot tasks. His most notable work introduces an efficient multi-scale POMDP framework for robotic object search and delivery, a problem that is notoriously difficult due to the exponential growth of state spaces. By leveraging a hierarchical belief representation, Holzherr’s approach allows robots to reason about both coarse room-level and fine object-level locations simultaneously, drastically reducing the computational burden of traditional POMDP solvers. This work, published in 2021 and garnering 7 citations, is a critical step toward enabling robots to operate autonomously in large, unstructured environments like warehouses or homes. Holzherr’s research is particularly impactful for students and engineers working on long-horizon tasks, as it provides a principled method for balancing exploration and exploitation when the robot’s knowledge is incomplete. His work demonstrates a clear path from theoretical planning algorithms to practical deployment, making him a key figure in the ongoing effort to build robots that can search for and deliver objects efficiently.