Jens Lundell

I am Jens Lundell, a Postdoctoral researcher working with Danica Kragic in the Robotics, Perception and Learning Lab (RPL) at KTH in Stockholm, Sweden. My research interests is data-driven methods for robotic manipulation and grasping. I am currently working on in-hand manipulation of rigid objects, also known as intrinsic dexterity, deformable object manipulation, and constrained robotic grasping.

I did my Ph.D. in the Intelligent Robotics group at Aalto University (Finland) with Prof. Ville Kyrki and Ph.D. Francesco Verdoja. My Ph.D. thesis addressed the problem of probabilistic 6-degree-of-freedom multi-finger grasping of objects in clutter. My solution to those problems was to explicitly shape-complete each object in the scene using deep learning, and plan grasps on those reconstructions. I also focused on using physics simulators to gather synthetic data for training deep networks.

I hold a Master’s degree in Space Science and Technology and a Bachelor’s degree in Automation and Systems Technology, both from Aalto University.

My main research interests:

Robotic Grasping
Robotic Manipulation
Deep Learning

selected publications

2024

CAPGrasp: An $\mathbbR^3\times\mathrmSO(2)$-equivariant Continuous Approach-Constrained Generative Grasp Sampler

Zehang Weng, Haofei Lu, Jens Lundell, and 1 more author

IEEE Robotics and Automation Letters, 2024

PDF Code
Dexdiffuser: Generating dexterous grasps with diffusion models

Zehang Weng, Haofei Lu, Danica Kragic, and 1 more author

arXiv preprint arXiv:2402.02989, 2024

PDF

2021

DDGC: Generative deep dexterous grasping in clutter

Jens Lundell, Francesco Verdoja, and Ville Kyrki

IEEE Robotics and Automation Letters, 2021

Bib PDF Code

@article{lundell2021ddgc,
  title = {DDGC: Generative deep dexterous grasping in clutter},
  author = {Lundell, Jens and Verdoja, Francesco and Kyrki, Ville},
  journal = {IEEE Robotics and Automation Letters},
  volume = {6},
  number = {4},
  pages = {6899--6906},
  year = {2021},
  publisher = {IEEE},
}