Picture for Jürgen Leitner

Jürgen Leitner

Deep Learning Approaches to Grasp Synthesis: A Review

Jul 06, 2022
Rhys Newbury, Morris Gu, Lachlan Chumbley, Arsalan Mousavian, Clemens Eppner, Jürgen Leitner, Jeannette Bohg, Antonio Morales, Tamim Asfour, Danica Kragic, Dieter Fox, Akansel Cosgun

Figure 1 for Deep Learning Approaches to Grasp Synthesis: A Review

Figure 2 for Deep Learning Approaches to Grasp Synthesis: A Review

Figure 3 for Deep Learning Approaches to Grasp Synthesis: A Review

Figure 4 for Deep Learning Approaches to Grasp Synthesis: A Review

* 21 pages. Submitted to T-RO

Access Paper or Ask Questions

EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation

Mar 03, 2020
Douglas Morrison, Peter Corke, Jürgen Leitner

Figure 1 for EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation

Figure 2 for EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation

Figure 3 for EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation

Figure 4 for EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation

* Submitted to RA-L & IROS 2020. 8 pages. The dataset, code and videos can be found at https://dougsm.github.io/egad/

Access Paper or Ask Questions

Benchmarking Simulated Robotic Manipulation through a Real World Dataset

Nov 27, 2019
Jack Collins, Jessie McVicar, David Wedlock, Ross Brown, David Howard, Jürgen Leitner

Figure 1 for Benchmarking Simulated Robotic Manipulation through a Real World Dataset

Figure 2 for Benchmarking Simulated Robotic Manipulation through a Real World Dataset

Figure 3 for Benchmarking Simulated Robotic Manipulation through a Real World Dataset

Figure 4 for Benchmarking Simulated Robotic Manipulation through a Real World Dataset

* Accepted to the IEEE Robotics and Automation Letters (RA-L) Special Issue: Benchmarking Protocols for Robotic Manipulation (2019)

Access Paper or Ask Questions

A Perceived Environment Design using a Multi-Modal Variational Autoencoder for learning Active-Sensing

Nov 01, 2019
Timo Korthals, Malte Schilling, Jürgen Leitner

Figure 1 for A Perceived Environment Design using a Multi-Modal Variational Autoencoder for learning Active-Sensing

* Extended Abstract for the IROS 2019 Workshop on Deep Probabilistic Generative Models for Cognitive Architecture in Robotics

Access Paper or Ask Questions

Ctrl-Z: Recovering from Instability in Reinforcement Learning

Oct 09, 2019
Vibhavari Dasagi, Jake Bruce, Thierry Peynot, Jürgen Leitner

Figure 1 for Ctrl-Z: Recovering from Instability in Reinforcement Learning

Figure 2 for Ctrl-Z: Recovering from Instability in Reinforcement Learning

Figure 3 for Ctrl-Z: Recovering from Instability in Reinforcement Learning

Figure 4 for Ctrl-Z: Recovering from Instability in Reinforcement Learning

* Submitted to ICRA2020, under review

Access Paper or Ask Questions

Quantifying the Reality Gap in Robotic Manipulation Tasks

Nov 08, 2018
Jack Collins, David Howard, Jürgen Leitner

Figure 1 for Quantifying the Reality Gap in Robotic Manipulation Tasks

Figure 2 for Quantifying the Reality Gap in Robotic Manipulation Tasks

Figure 3 for Quantifying the Reality Gap in Robotic Manipulation Tasks

Figure 4 for Quantifying the Reality Gap in Robotic Manipulation Tasks

* Submitted to ICRA 2019 (Under Review)

Access Paper or Ask Questions

Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter

Sep 23, 2018
Douglas Morrison, Peter Corke, Jürgen Leitner

Figure 1 for Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter

Figure 2 for Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter

Figure 3 for Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter

Figure 4 for Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter

* Submitted to ICRA 2019 (Under Review) Video: https://youtu.be/Vn3vSPKlaEk

Access Paper or Ask Questions