62 citations · 148 across the 29 of their papers we have counts for
30 papers
Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search
Imen Mahdi, Matteo Cassinelli, Fabien Despinoy +2
Open-world interactive object search in household environments requires understanding semantic relationships between objects and their surrounding context to guide exploration effi…
Articulated 3D Scene Graphs for Open-World Mobile Manipulation
Martin Büchner, Adrian Röfer, Tim Engelbracht +5
Semantic scene understanding has enabled robots to reason and perform affordance-driven object interaction. Despite this, real-world manipulation remains fundamentally limited by t…
DiWA: Diffusion Policy Adaptation with World Models
Akshay L Chandra, Iman Nematollahi, Chenguang Huang +3
Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward pro…
MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
Mohammad Mohammadi, Daniel Honerkamp, Martin Büchner +5
Autonomous long-horizon mobile manipulation encompasses a multitude of challenges, including scene dynamics, unexplored areas, and error recovery. Recent works have leveraged found…
Task-Driven Co-Design of Mobile Manipulators
Raphael Schneider, Daniel Honerkamp, Tim Welschehold +1
Recent interest in mobile manipulation has resulted in a wide range of new robot designs. A large family of these designs focuses on modular platforms that combine existing mobile…
Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching
Eugenio Chisari, Nick Heppert, Max Argus +3
Learning from expert demonstrations is a promising approach for training robotic manipulation policies from limited data. However, imitation learning algorithms require a number of…
Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost
Daniel Honerkamp, Harsh Mahesheka, Jan Ole von Hartz +2
Demonstration data plays a key role in learning complex behaviors and training robotic foundation models. While effective control interfaces exist for static manipulators, data col…
Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation
Sai Prasanna, Daniel Honerkamp, Kshitij Sirohi +3
Embodied AI has made significant progress acting in unexplored environments. However, tasks such as object search have largely focused on efficient policy learning. In this work, w…
The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations
Jan Ole von Hartz, Tim Welschehold, Abhinav Valada +1
Task Parametrized Gaussian Mixture Models (TP-GMM) are a sample-efficient method for learning object-centric robot manipulation tasks. However, there are several open challenges to…
DITTO: Demonstration Imitation by Trajectory Transformation
Nick Heppert, Max Argus, Tim Welschehold +2
Teaching robots new skills quickly and conveniently is crucial for the broader adoption of robotic systems. In this work, we address the problem of one-shot imitation from a single…
Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation
Adrian Röfer, Iman Nematollahi, Tim Welschehold +2
Sample efficient learning of manipulation skills poses a major challenge in robotics. While recent approaches demonstrate impressive advances in the type of task that can be addres…
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation
Daniel Honerkamp, Martin Büchner, Fabien Despinoy +2
To fully leverage the capabilities of mobile manipulation robots, it is imperative that they are able to autonomously execute long-horizon tasks in large unexplored environments. W…
CenterGrasp: Object-Aware Implicit Representation Learning for Simultaneous Shape Reconstruction and 6-DoF Grasp Estimation
Eugenio Chisari, Nick Heppert, Tim Welschehold +2
Reliable object grasping is a crucial capability for autonomous robots. However, many existing grasping approaches focus on general clutter removal without explicitly modeling obje…
Robot Skill Generalization via Keypoint Integrated Soft Actor-Critic Gaussian Mixture Models
Iman Nematollahi, Kirill Yankov, Wolfram Burgard +1
A long-standing challenge for a robotic manipulation system operating in real-world scenarios is adapting and generalizing its acquired motor skills to unseen environments. We tack…
Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation
Fabian Schmalstieg, Daniel Honerkamp, Tim Welschehold +1
Existing object-search approaches enable robots to search through free pathways, however, robots operating in unstructured human-centered environments frequently also have to manip…
The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation
Jan Ole von Hartz, Eugenio Chisari, Tim Welschehold +3
In policy learning for robotic manipulation, sample efficiency is of paramount importance. Thus, learning and extracting more compact representations from camera observations is a…
Improving Deep Dynamics Models for Autonomous Vehicles with Multimodal Latent Mapping of Surfaces
Johan Vertens, Nicolai Dorka, Tim Welschehold +2
The safe deployment of autonomous vehicles relies on their ability to effectively react to environmental changes. This can require maneuvering on varying surfaces which is still a…
Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
Nicolai Dorka, Tim Welschehold, Wolfram Burgard
Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However…
NM: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments
Daniel Honerkamp, Tim Welschehold, Abhinav Valada
Despite its importance in both industrial and service robotics, mobile manipulation remains a significant challenge as it requires a seamless integration of end-effector trajectory…
Learning Long-Horizon Robot Exploration Strategies for Multi-Object Search in Continuous Action Spaces
Fabian Schmalstieg, Daniel Honerkamp, Tim Welschehold +1
Recent advances in vision-based navigation and exploration have shown impressive capabilities in photorealistic indoor environments. However, these methods still struggle with long…
Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation
Jan Ole von Hartz, Eugenio Chisari, Tim Welschehold +1
In recent years, policy learning methods using either reinforcement or imitation have made significant progress. However, both techniques still suffer from being computationally ex…
Doing Right by Not Doing Wrong in Human-Robot Collaboration
Laura Londoño, Adrian Röfer, Tim Welschehold +1
As robotic systems become more and more capable of assisting humans in their everyday lives, we must consider the opportunities for these artificial agents to make their human coll…
Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds
Abdelrahman Younes, Daniel Honerkamp, Tim Welschehold +1
Audio-visual navigation combines sight and hearing to navigate to a sound-emitting source in an unmapped environment. While recent approaches have demonstrated the benefits of audi…
Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models
Iman Nematollahi, Erick Rosete-Beas, Adrian Röfer +3
A core challenge for an autonomous agent acting in the real world is to adapt its repertoire of skills to cope with its noisy perception and dynamics. To scale learning of skills t…