Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Roland Siegwart

Roland Siegwart

ETH ZĂŒrich

Under the Sand: Navigation and Localization of a Small Unmanned Aerial Vehicle for Landmine Detection with Ground Penetrating Synthetic Aperture Radar


Jun 18, 2021
Rik BĂ€hnemann, Nicholas Lawrance, Lucas Streichenberg, Jen Jen Chung, Michael Pantic, Alexander Grathwohl, Christian Waldschmidt, Roland Siegwart

* Submitted to Field Robotics journal in June 2021 

  Access Paper or Ask Questions

TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction


May 16, 2021
Margarita Grinvald, Federico Tombari, Roland Siegwart, Juan Nieto

* 7 pages, 3 figures. To be published in the 2021 IEEE International Conference on Robotics and Automation (ICRA). Code is available at https://github.com/ethz-asl/tsdf-plusplus and the accompanying video material can be found at https://youtu.be/dSJmoeVasI0 

  Access Paper or Ask Questions

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation


Apr 30, 2021
Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Mathieu Salzmann, Pascal Fua, Matthias Rottmann

* 10 pages, 13 figures, website http://www.segmentmeifyoucan.com/ 

  Access Paper or Ask Questions

Crowd against the machine: A simulation-based benchmark tool to evaluate and compare robot capabilities to navigate a human crowd


Apr 29, 2021
Fabien Grzeskowiak, David Gonon, Daniel Dugas, Diego Paez-Granados, Jen Chung, Juan Nieto, Roland Siegwart, Aude Billard, Marie Babel, Julien Pettré

* ICRA 2021 - IEEE International Conference on Robotics and Automation, May 2021, Xian, China 

  Access Paper or Ask Questions

Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems


Apr 17, 2021
Lukas Bernreiter, Lionel Ott, Juan Nieto, Roland Siegwart, Cesar Cadena

* Accepted for IEEE International Conference on Robotics and Automation, 2021 

  Access Paper or Ask Questions

3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs


Apr 12, 2021
Dominic Streiff, Lukas Bernreiter, Florian Tschopp, Marius Fehr, Roland Siegwart

* Accepted for IEEE International Conference on Robotics and Automation, 2021 

  Access Paper or Ask Questions

CalQNet -- Detection of Calibration Quality for Life-Long Stereo Camera Setups


Apr 10, 2021
Jiapeng Zhong, Zheyu Ye, Andrei Cramariuc, Florian Tschopp, Jen Jen Chung, Roland Siegwart, Cesar Cadena


  Access Paper or Ask Questions

Dynamic Object Aware LiDAR SLAM based on Automatic Generation of Training Data


Apr 08, 2021
Patrick Pfreundschuh, Hubertus Franciscus Cornelis Hendrikx, Victor Reijgwart, Renaud Dubé, Roland Siegwart, Andrei Cramariuc

* 6 pages, 11 figures, Accepted to the 2021 IEEE International Conference on Robotics and Automation (ICRA 2021) 

  Access Paper or Ask Questions

Dynamic-Aware Autonomous Exploration in Populated Environments


Apr 06, 2021
Valentina Cavinato, Thomas Eppenberger, Dina Youakim, Roland Siegwart, Renaud Dubé

* 7 pages, 5 figures, Accepted to the 2021 IEEE International Conference on Robotics and Automation (ICRA 2021) 

  Access Paper or Ask Questions

SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)


Mar 30, 2021
Timo Hinzmann, Roland Siegwart

* Initial submission; 7 pages, 3 figures, 2 tables 

  Access Paper or Ask Questions

Online Informative Path Planning for Active Information Gathering of a 3D Surface


Mar 17, 2021
Hai Zhu, Jen Jen Chung, Nicholas R. J. Lawrance, Roland Siegwart, Javier Alonso-Mora

* 7 pages, 7 figures, to be published in 2021 IEEE International Conference on Robotics and Automation (ICRA) 

  Access Paper or Ask Questions

Pixel-wise Anomaly Detection in Complex Driving Scenes


Mar 09, 2021
Giancarlo Di Biase, Hermann Blum, Roland Siegwart, Cesar Cadena


  Access Paper or Ask Questions

Mesh Manifold based Riemannian Motion Planning for Omnidirectional Micro Aerial Vehicles


Feb 20, 2021
Michael Pantic, Lionel Ott, Cesar Cadena, Roland Siegwart, Juan Nieto

* Accepted to RA-L 2021. Video available at https://youtu.be/S9gRr_ryREo 

  Access Paper or Ask Questions

Hough2Map -- Iterative Event-based Hough Transform for High-Speed Railway Mapping


Feb 18, 2021
Florian Tschopp, Cornelius von Einem, Andrei Cramariuc, David Hug, Andrew William Palmer, Roland Siegwart, Margarita Chli, Juan Nieto

* Florian Tschopp, Cornelius von Einem, and Andrei Cramariuc contributed equally to this work 

  Access Paper or Ask Questions

Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds


Feb 08, 2021
Joël Bachmann, Kenneth Blomqvist, Julian Förster, Roland Siegwart


  Access Paper or Ask Questions

PHASER: a Robust and Correspondence-free Global Pointcloud Registration


Feb 03, 2021
Lukas Bernreiter, Lionel Ott, Juan Nieto, Roland Siegwart, Cesar Cadena

* IEEE Robotics and Automation Letters ( Volume: 6, Issue: 2, April 2021) 

  Access Paper or Ask Questions

Active Model Learning using Informative Trajectories for Improved Closed-Loop Control on Real Robots


Jan 20, 2021
Weixuan Zhang, Lionel Ott, Marco Tognon, Roland Siegwart, Juan Nieto


  Access Paper or Ask Questions

Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter


Jan 04, 2021
Michel Breyer, Jen Jen Chung, Lionel Ott, Roland Siegwart, Juan Nieto

* Conference on Robot Learning (CoRL), 2020 

  Access Paper or Ask Questions

Multiple Hypothesis Semantic Mapping for Robust Data Association


Dec 08, 2020
Lukas Bernreiter, Abel Gawel, Hannes Sommer, Juan Nieto, Roland Siegwart, Cesar Cadena

* IEEE Robotics and Automation Letters ( Volume: 4, Issue: 4, Oct. 2019) 

  Access Paper or Ask Questions

NavRep: Unsupervised Representations for Reinforcement Learning of Robot Navigation in Dynamic Human Environments


Dec 08, 2020
Daniel Dugas, Juan Nieto, Roland Siegwart, Jen Jen Chung

* Pre-print, submitted to ICRA 2021 

  Access Paper or Ask Questions

Quantifying Aleatoric and Epistemic Uncertainty Using Density Estimation in Latent Space


Dec 05, 2020
Janis Postels, Hermann Blum, Cesar Cadena, Roland Siegwart, Luc Van Gool, Federico Tombari


  Access Paper or Ask Questions

3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer


Nov 30, 2020
Mattia Segu, Margarita Grinvald, Roland Siegwart, Federico Tombari


  Access Paper or Ask Questions

Model Predictive Control for Micro Aerial Vehicles: A Survey


Nov 22, 2020
Huan Nguyen, Mina Kamel, Kostas Alexis, Roland Siegwart


  Access Paper or Ask Questions

Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning


Nov 04, 2020
Le Chen, Yunke Ao, Florian Tschopp, Andrei Cramariuc, Michel Breyer, Jen Jen Chung, Roland Siegwart, Cesar Cadena


  Access Paper or Ask Questions

Out-of-Distribution Detection for Automotive Perception


Nov 03, 2020
Julia Nitsch, Masha Itkina, Ransalu Senanayake, Juan Nieto, Max Schmidt, Roland Siegwart, Mykel J. Kochenderfer, Cesar Cadena

* 7 pages, 7 figures 

  Access Paper or Ask Questions

LCD -- Line Clustering and Description for Place Recognition


Oct 21, 2020
Felix Taubner, Florian Tschopp, Tonci Novkovic, Roland Siegwart, Fadri Furrer

* Accepted for International Conference on 3D Vision (3DV) 2020 

  Access Paper or Ask Questions

Freetures: Localization in Signed Distance Function Maps


Oct 21, 2020
Alexander Millane, Helen Oleynikova, Christian Lanegger, Jeff Delmerico, Juan Nieto, Roland Siegwart, Marc Pollefeys, Cesar Cadena


  Access Paper or Ask Questions

Autonomous Extension of a Symbolic Mobile Manipulation Skill Set


Oct 20, 2020
Julian Förster, Juan Nieto, Lionel Ott, Roland Siegwart, Jen Jen Chung

* An accompanying video is available here: https://youtu.be/Dm1I82moJuY. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

A Unified Approach for Autonomous Volumetric Exploration of Large Scale Environments under Severe Odometry Drift


Oct 19, 2020
Lukas Schmid, Victor Reijgwart, Lionel Ott, Juan Nieto, Roland Siegwart, Cesar Cadena


  Access Paper or Ask Questions