Home
About
News
Partners & People
Research
Gallery
Contact
Events
University of Hamburg
Comparing Apples to Oranges: LLM-Powered Multimodal Intention Prediction in an Object Categorization Task
Human intention-based systems enable robots to perceive and interpret user actions to interact with humans and adapt to their behavior …
Hassan Ali
,
Philipp Allgeuer
,
Stefan Wermter
Cite
DOI
Diffusing in Someone Else’s Shoes: Robotic Perspective-Taking with Diffusion
Humanoid robots can benefit from their similarity to the human shape by learning from humans. When humans teach other humans how to …
Josua Spisak
,
Matthias Kerzel
,
Stefan Wermter
Cite
DOI
Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation
Large Language Models (LLMs) have been recently used in robot applications for grounding LLM commonsense reasoning with the robot’s …
Hassan Ali
,
Philipp Allgeuer
,
Carlo Mazzola
,
Guilia Belgiovine
,
Burak Can Kaplan
,
Lukáš Gajdošech
,
Stefan Wermter
Cite
DOI
When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration
We investigate the use of Large Language Models (LLMs) to equip neural robotic agents with human-like social and cognitive …
Philipp Allgeuer
,
Hassan Ali
,
Stefan Wermter
Cite
DOI
Robotic Imitation of Human Actions
Imitation can allow us to quickly gain an understanding of a new task. Through a demonstration, we can gain direct knowledge about …
Josua Spisak
,
Matthias Kenzel
,
Stefan Wermter
Cite
DOI
NICOL: A Neuro-inspired Collaborative Semi-humanoid Robot that Bridges Social Interaction and Reliable Manipulation
Robotic platforms that can efficiently collaborate with humans in physical tasks constitute a major goal in robotics. However, many …
Matthias Kerzel
,
Philipp Allgeuer
,
Erik Strahl
,
Nicolas Frick
,
Jan-Gerrit Habekost
,
Manfred Eppe
,
Stefan Wermter
PDF
Cite
DOI
IEEE Xplore
Clarifying the Half Full or Half Empty Question: Multimodal Container Classification
Multimodal integration is a key component of allowing robots to perceive the world. Multimodality comes with multiple challenges that …
Josua Spisak
,
Matthias Kerzel
,
Stefan Wermter
PDF
DOI
ICANN 2023
CycleIK: Neuro-inspired Inverse Kinematics
The paper introduces CycleIK, a neuro-robotic approach that wraps two novel neuro-inspired methods for the inverse kinematics (IK) …
Jan-Gerrit Habekost
,
Erik Strahl
,
Philipp Allgeuer
,
Matthias Kerzel
,
Stefan Wermter
PDF
DOI
ICANN 2023
Neural Field Conditioning Strategies for 2D Semantic Segmentation
Neural fields are neural networks which map coordinates to a desired signal. When a neural field should jointly model multiple signals, …
Martin Gromniak
,
Sven Magg
,
Stefan Wermter
PDF
DOI
ICANN 2023
Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition
While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or …
Theresa Pekarek Rosin
,
Stefan Wermter
PDF
DOI
ICANN 2023
Cite
×