RePAIR - Reconstructing the Past: Artificial Intelligence and Robotics Meet Cultural Heritage

The 'RePAIR' project combines Artificial Intelligence and Robotics with Cultural Heritage to create technology that simplifies the reconstruction of shattered artworks. This innovation aims to address the challenge of piecing together damaged or incomplete ancient artifacts like vases, amphorae, and frescoes, often found in fragments at excavation sites worldwide.

RePAIR - Reconstructing the Past: Artificial Intelligence and Robotics Meet Cultural Heritage
RePAIR - Reconstructing the Past: Artificial Intelligence and Robotics Meet Cultural Heritage

Funding:

The project has received funding from the Horizon 2020 research and innovation program of the European Union, under Grant Agreement no. 964854.

Start:

2021-09-01

End:

2025-10-31

Project Abstract:

The main goal of the RePAIR project is to develop innovative technology to virtually eliminate one of the most laborious and frustrating steps in archaeological research, namely the physical reconstruction of shattered works of art. In fact, countless vases, amphorae, frescoes and other ancient artifacts, around the world, have not survived intact and have been extracted from excavation sites as large collections of fragments, many of which are damaged, worn out or entirely missing.

We are responsible for the Integration and evaluation of the robotic system and will provide techniques for planning of bi-manual arm motions and planning algorithms to place the fresco pieces at the desired poses.

Links:

Project Website

Associated Researchers:

Associated Student Assistants:

Related Topics:

Intelligent Manipulation

Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection

Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection

Nils Dengler, Jesper Mücke, Rohit Menon, Maren Bennewitz

IEEE/RAS International Conference on Humanoid Robots (Humanoids), 2025

Pre-PrintCodeVideo
Interactive Shaping of Granular Media Using Reinforcement Learning

Interactive Shaping of Granular Media Using Reinforcement Learning

Benedikt Kreis, Malte Mosbach, Anny Ripke, Muhammad Ehsan Ullah, Sven Behnke, Maren Bennewitz

IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2025

Pre-PrintPublicationWebsiteCode
Learning Goal-Directed Object Pushing in Cluttered Scenes with Location-Based Attention

Learning Goal-Directed Object Pushing in Cluttered Scenes with Location-Based Attention

Nils Dengler, Juan Del Aguila Ferrandis, João Moura, Sethu Vijayakumar, Maren Bennewitz

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

Pre-PrintCodeVideo
Map Space Belief Prediction for Manipulation-Enhanced Mapping

Map Space Belief Prediction for Manipulation-Enhanced Mapping

Joao Marcos Correia Marques, Nils Dengler, Tobias Zaenker, Jesper Mücke, Shenlong Wang, Maren Bennewitz, Kris Hauser

Robotics: Science and Systems (RSS), 2025

Pre-PrintPublicationCodeVideo
DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction

DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction

Sicong Pan, Liren Jin, Xuying Huang, Cyrill Stachniss, Marija Popović, Maren Bennewitz

Arxiv Pre-print, 2025

Pre-Print
Compact Multi-Object Placement Using Adjacency-Aware Reinforcement Learning

Compact Multi-Object Placement Using Adjacency-Aware Reinforcement Learning

Benedikt Kreis, Nils Dengler, Jorge de Heuvel, Rohit Menon, Hamsa Datta Perur, Maren Bennewitz

IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2024

Pre-PrintPublicationCodeVideo
DawnIK: Decentralized Collision-Aware Inverse Kinematics Solver for Heterogeneous Multi-Arm Systems

DawnIK: Decentralized Collision-Aware Inverse Kinematics Solver for Heterogeneous Multi-Arm Systems

Salih Marangoz, Rohit Menon, Nils Dengler, Maren Bennewitz

IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2023

Pre-PrintPublicationCodeVideo
Viewpoint Push Planning for Mapping of Unknown Confined Spaces

Viewpoint Push Planning for Mapping of Unknown Confined Spaces

Nils Dengler, Sicong Pan, Vamsi Kalagaturu, Rohit Menon, Murad Dawood, Maren Bennewitz

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

Pre-PrintPublicationCodeVideo
Reactive Correction of Object Placement Errors for Robotic Arrangement Tasks

Reactive Correction of Object Placement Errors for Robotic Arrangement Tasks

Benedikt Kreis, Rohit Menon, Bharath Kumar Adinarayan, Jorge de Heuvel, Maren Bennewitz

International Conference on Intelligent Autonomous Systems (IAS-18), 2023

Pre-PrintPublicationVideo
Learning Goal-Directed Non-Prehensile Pushing in Cluttered Scenes

Learning Goal-Directed Non-Prehensile Pushing in Cluttered Scenes

Nils Dengler, David Großklaus, Maren Bennewitz

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022

Pre-PrintPublicationCodeVideo