Piotr Polatowski
Papers
1
Total Citations
6
H-Index
1
About
Piotr Polatowski is a robotics researcher whose work centers on advancing robotic manipulation through deep learning, with a particular focus on grasp planning for unknown objects. His most notable contribution, the 2018 paper "Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps," builds upon the foundational Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset. By refining this architecture, Polatowski enhances the model’s ability to predict successful grasps, directly improving grasp success rates in unstructured environments—a critical challenge for autonomous robotics. Though his work has accumulated a modest 6 citations, it represents a targeted and meaningful step forward in a competitive field, demonstrating a keen ability to optimize existing frameworks for real-world applicability. Polatowski’s research sits at the intersection of computer vision, deep learning, and robotic control, offering practical solutions for industrial automation and service robotics. His focus on robust, data-driven grasp planning underscores a commitment to bridging the gap between simulation and physical deployment, making his contributions valuable for researchers and engineers seeking to improve robot dexterity and reliability in dynamic settings.
Research Focus
Key Achievements
Top Papers
- 1Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps6 citations · 2018