Sigmund Hennum Høeg
About
I am a Ph.D. candidate in the Robotics and Automation Group at the Department of Mechanical and Industrial Engineering. I am interested in how we can make robots that are more intelligent and can help us.
To advance this field, I have focused on Imitation Learning, as it provides a highly general framework for endowing robots with human-like skills. On the other hand, generative modeling has emerged as a compelling direction, as models for image, text, and video have proven capable of consuming and generalizing from large quantities of data. However, there remains a significant gap between these modeling tasks and the challenge of controlling a robot in an ever-changing, chaotic world. The main motivation of my research is to bridge this gap.
Also, check out my fireside chat with Sergey Levine for the Workshop on Learning from Diverse, Offline Data at RSS 2022.
Publications
2024
-
Høeg, Sigmund Hennum;
Du, Yilun;
Egeland, Olav.
(2024)
Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models.
arXiv.org
Academic article
2022
-
Høeg, Sigmund Hennum;
Tingelstad, Lars;
Njaastad, Eirik B.
(2022)
Learning to grasp: A study of learning-based methods for robotic grasping.
NTNU
Masters thesis
Journal publications
-
Høeg, Sigmund Hennum;
Du, Yilun;
Egeland, Olav.
(2024)
Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models.
arXiv.org
Academic article
Report
-
Høeg, Sigmund Hennum;
Tingelstad, Lars;
Njaastad, Eirik B.
(2022)
Learning to grasp: A study of learning-based methods for robotic grasping.
NTNU
Masters thesis
Outreach
2024
-
PosterHøeg, Sigmund Hennum; Lars, Tingelstad. (2024) Temporally Entangled Diffusion Models for Fast Robotic Control. Generative Modeling meets HRI, RSS 2024 Workshop 2024-07-15 -
2022
-
PosterHøeg, Sigmund Hennum; Tingelstad, Lars. (2022) More Than Eleven Thousand Words: Towards Using Language Models for Robotic Sorting of Unseen Objects into Arbitrary Categories. Workshop on Language and Robot Learning, CoRL 2022 , Auckland 2022-12-14 - 2022-12-18