Search Results for author: Roland Siegwart

Found 93 papers, 49 papers with code

WindSeer: Real-time volumetric wind prediction over complex terrain aboard a small UAV

no code implementations18 Jan 2024 Florian Achermann, Thomas Stastny, Bogdan Danciu, Andrey Kolobov, Jen Jen Chung, Roland Siegwart, Nicholas Lawrance

Real-time high-resolution wind predictions are beneficial for various applications including safe manned and unmanned aviation.


TULIP: Transformer for Upsampling of LiDAR Point Cloud

no code implementations11 Dec 2023 Bin Yang, Patrick Pfreundschuh, Roland Siegwart, Marco Hutter, Peyman Moghadam, Vaishakh Patil

In this paper, we propose TULIP, a new method to reconstruct high-resolution LiDAR point clouds from low-resolution LiDAR input.

Autonomous Vehicles Image Super-Resolution

ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification

no code implementations5 Nov 2023 Nicolas Gorlo, Kenneth Blomqvist, Francesco Milano, Roland Siegwart

To build spatial AI systems that can quickly be taught about new objects, we need to effectively solve the problem of single-shot object detection, instance segmentation and re-identification.

Instance Segmentation Multi-Object Tracking +7

Panoptic Vision-Language Feature Fields

2 code implementations11 Sep 2023 Haoran Chen, Kenneth Blomqvist, Francesco Milano, Roland Siegwart

In this paper, we propose to the best of our knowledge the first algorithm for open-vocabulary panoptic segmentation in 3D scenes.

Contrastive Learning Instance Segmentation +4

Local and Global Information in Obstacle Detection on Railway Tracks

no code implementations28 Jul 2023 Matthias Brucker, Andrei Cramariuc, Cornelius von Einem, Roland Siegwart, Cesar Cadena

We evaluate our method on a custom dataset featuring railway images with artificially augmented obstacles.

Unsupervised Continual Semantic Adaptation through Neural Rendering

1 code implementation CVPR 2023 Zhizheng Liu, Francesco Milano, Jonas Frey, Roland Siegwart, Hermann Blum, Cesar Cadena

Due to the mismatch between training and deployment data, adapting the model on the new scenes is often crucial to obtain good performance.

Neural Rendering Segmentation +3

Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps

no code implementations26 Sep 2022 Kenneth Blomqvist, Lionel Ott, Jen Jen Chung, Roland Siegwart

Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels.


3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs

1 code implementation16 Sep 2022 Samuel Looper, Javier Rodriguez-Puigvert, Roland Siegwart, Cesar Cadena, Lukas Schmid

In this work, we formalize the task of semantic scene variability estimation and identify three main varieties of semantic scene change: changes in the position of an object, its semantic state, or the composition of a scene as a whole.

Attribute Change Detection

SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning

1 code implementation17 Aug 2022 Lukas Schmid, Mansoor Nasir Cheema, Victor Reijgwart, Roland Siegwart, Federico Tombari, Cesar Cadena

We further present an informative path planning method, leveraging the capabilities of our mapping approach and a novel scene-completion-aware information gain.

Efficient Exploration

Learning Variable Impedance Control for Aerial Sliding on Uneven Heterogeneous Surfaces by Proprioceptive and Tactile Sensing

no code implementations28 Jun 2022 Weixuan Zhang, Lionel Ott, Marco Tognon, Roland Siegwart

The recent development of novel aerial vehicles capable of physically interacting with the environment leads to new applications such as contact-based inspection.


SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding

1 code implementation21 Jun 2022 Hermann Blum, Marcus G. Müller, Abel Gawel, Roland Siegwart, Cesar Cadena

In order to operate in human environments, a robot's semantic perception has to overcome open-world challenges such as novel objects and domain gaps.

Clustering Object Discovery +3

Sampling-free obstacle gradients and reactive planning in Neural Radiance Fields (NeRF)

no code implementations3 May 2022 Michael Pantic, Cesar Cadena, Roland Siegwart, Lionel Ott

This work investigates the use of Neural implicit representations, specifically Neural Radiance Fields (NeRF), for geometrical queries and motion planning.

Motion Planning

NavDreams: Towards Camera-Only RL Navigation Among Humans

1 code implementation23 Mar 2022 Daniel Dugas, Olov Andersson, Roland Siegwart, Jen Jen Chung

In order to successfully solve the navigation task from only images, algorithms must be able to model the scene and its dynamics using only this channel of information.

Atari Games Navigate

Descriptellation: Deep Learned Constellation Descriptors

no code implementations1 Mar 2022 Chunwei Xing, Xinyu Sun, Andrei Cramariuc, Samuel Gull, Jen Jen Chung, Cesar Cadena, Roland Siegwart, Florian Tschopp

However, handcrafted topological descriptors are hard to tune and not robust to environmental noise, drastic perspective changes, object occlusion or misdetections.

Simultaneous Localization and Mapping

Semi-automatic 3D Object Keypoint Annotation and Detection for the Masses

1 code implementation19 Jan 2022 Kenneth Blomqvist, Jen Jen Chung, Lionel Ott, Roland Siegwart

In this work, we present a full object keypoint tracking toolkit, encompassing the entire process from data collection, labeling, model learning and evaluation.

Object Object Tracking +1

NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping

1 code implementation18 Oct 2021 Stefan Lionar, Lukas Schmid, Cesar Cadena, Roland Siegwart, Andrei Cramariuc

We present a novel 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction.

3D Reconstruction

See Yourself in Others: Attending Multiple Tasks for Own Failure Detection

no code implementations6 Oct 2021 Boyang Sun, Jiaxu Xing, Hermann Blum, Roland Siegwart, Cesar Cadena

The proposed framework infers task failures by evaluating the individual prediction, across multiple visual perception tasks for different regions in an image.

Depth Estimation Semantic Segmentation

Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning

1 code implementation30 Sep 2021 Yunke Ao, Le Chen, Florian Tschopp, Michel Breyer, Andrei Cramariuc, Roland Siegwart

Our approach models the calibration process compactly using model-free deep reinforcement learning to derive a policy that guides the motions of a robotic arm holding the sensor to efficiently collect measurements that can be used for both camera intrinsic calibration and camera-IMU extrinsic calibration.

reinforcement-learning Reinforcement Learning (RL)

Superquadric Object Representation for Optimization-based Semantic SLAM

no code implementations20 Sep 2021 Florian Tschopp, Juan Nieto, Roland Siegwart, Cesar Cadena

Introducing semantically meaningful objects to visual Simultaneous Localization And Mapping (SLAM) has the potential to improve both the accuracy and reliability of pose estimates, especially in challenging scenarios with significant view-point and appearance changes.

Object Object Recognition +2

Fast Image-Anomaly Mitigation for Autonomous Mobile Robots

no code implementations4 Sep 2021 Gianmario Fumagalli, Yannick Huber, Marcin Dymczyk, Roland Siegwart, Renaud Dubé

Camera anomalies like rain or dust can severelydegrade image quality and its related tasks, such as localizationand segmentation.

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

1 code implementation16 May 2021 Margarita Grinvald, Federico Tombari, Roland Siegwart, Juan Nieto

The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction.

Autonomous Navigation Object +2

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

2 code implementations30 Apr 2021 Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Pascal Fua, Mathieu Salzmann, Matthias Rottmann

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes.

Instance Segmentation Object +2

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

no code implementations30 Mar 2021 Timo Hinzmann, Roland Siegwart

This paper introduces SD-6DoF-ICLK, a learning-based Inverse Compositional Lucas-Kanade (ICLK) pipeline that uses sparse depth information to optimize the relative pose that best aligns two images on SE(3).

Simultaneous Localization and Mapping

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

1 code implementation25 Mar 2021 Dominic Streiff, Lukas Bernreiter, Florian Tschopp, Marius Fehr, Roland Siegwart

Furthermore, 3D feature-based registration methods have never quite reached the robustness of 2D methods in visual SLAM.

Keypoint Detection

Pixel-wise Anomaly Detection in Complex Driving Scenes

1 code implementation CVPR 2021 Giancarlo Di Biase, Hermann Blum, Roland Siegwart, Cesar Cadena

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving.

Ranked #3 on Anomaly Detection on Lost and Found (using extra training data)

Anomaly Detection Autonomous Driving +2

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

1 code implementation16 Feb 2021 Florian Tschopp, Cornelius von Einem, Andrei Cramariuc, David Hug, Andrew William Palmer, Roland Siegwart, Margarita Chli, Juan Nieto

As a basis for a localization system we propose a complete on-board mapping pipeline able to map robust meaningful landmarks, such as poles from power lines, in the vicinity of the vehicle.

Vocal Bursts Intensity Prediction

Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds

no code implementations8 Feb 2021 Joël Bachmann, Kenneth Blomqvist, Julian Förster, Roland Siegwart

This, despite the fact that the physical 3D spaces have a similar semantic structure to bodies of text: words are surrounded by words that are semantically related, just like objects are surrounded by other objects that are similar in concept and usage.

Clustering Learning Word Embeddings

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

no code implementations20 Jan 2021 Weixuan Zhang, Lionel Ott, Marco Tognon, Roland Siegwart, Juan Nieto

However, the efficient and effective data collection for such a data-driven system on real robots is still an open challenge.

Robotics Systems and Control Systems and Control

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

1 code implementation4 Jan 2021 Michel Breyer, Jen Jen Chung, Lionel Ott, Roland Siegwart, Juan Nieto

General robot grasping in clutter requires the ability to synthesize grasps that work for previously unseen objects and that are also robust to physical interactions, such as collisions with other objects in the scene.


The Hidden Uncertainty in a Neural Networks Activations

no code implementations5 Dec 2020 Janis Postels, Hermann Blum, Yannick Strümpler, Cesar Cadena, Roland Siegwart, Luc van Gool, Federico Tombari

We find that this leads to improved OOD detection of epistemic uncertainty at the cost of ambiguous calibration close to the data distribution.

Density Estimation Out of Distribution (OOD) Detection

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

1 code implementation26 Nov 2020 Mattia Segu, Margarita Grinvald, Roland Siegwart, Federico Tombari

Transferring the style from one image onto another is a popular and widely studied task in computer vision.

Style Transfer

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

1 code implementation4 Nov 2020 Le Chen, Yunke Ao, Florian Tschopp, Andrei Cramariuc, Michel Breyer, Jen Jen Chung, Roland Siegwart, Cesar Cadena

Visual-inertial systems rely on precise calibrations of both camera intrinsics and inter-sensor extrinsics, which typically require manually performing complex motions in front of a calibration target.

reinforcement-learning Reinforcement Learning (RL)

Out-of-Distribution Detection for Automotive Perception

no code implementations3 Nov 2020 Julia Nitsch, Masha Itkina, Ransalu Senanayake, Juan Nieto, Max Schmidt, Roland Siegwart, Mykel J. Kochenderfer, Cesar Cadena

A mechanism to detect OOD samples is important for safety-critical applications, such as automotive perception, to trigger a safe fallback mode.

Autonomous Driving Object Recognition +1

LCD -- Line Clustering and Description for Place Recognition

1 code implementation21 Oct 2020 Felix Taubner, Florian Tschopp, Tonci Novkovic, Roland Siegwart, Fadri Furrer

In this paper, we introduce a novel learning-based approach to place recognition, using RGB-D cameras and line clusters as visual and geometric features.

Clustering Image Retrieval +3

Freetures: Localization in Signed Distance Function Maps

no code implementations19 Oct 2020 Alexander Millane, Helen Oleynikova, Christian Lanegger, Jeff Delmerico, Juan Nieto, Roland Siegwart, Marc Pollefeys, Cesar Cadena

Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps.


IDOL: A Framework for IMU-DVS Odometry using Lines

no code implementations13 Aug 2020 Cedric Le Gentil, Florian Tschopp, Ignacio Alzugaray, Teresa Vidal-Calleja, Roland Siegwart, Juan Nieto

The method's front-end extracts event clusters that belong to line segments in the environment whereas the back-end estimates the system's trajectory alongside the lines' 3D position by minimizing point-to-line distances between individual events and the lines' projection in the image space.


Deep UAV Localization with Reference View Rendering

no code implementations11 Aug 2020 Timo Hinzmann, Roland Siegwart

This paper presents a framework for the localization of Unmanned Aerial Vehicles (UAVs) in unstructured environments with the help of deep learning.

Deep Learning-based Human Detection for UAVs with Optical and Infrared Cameras: System and Experiments

no code implementations10 Aug 2020 Timo Hinzmann, Tobias Stegemann, Cesar Cadena, Roland Siegwart

In this paper, we present our deep learning-based human detection system that uses optical (RGB) and long-wave infrared (LWIR) cameras to detect, track, localize, and re-identify humans from UAVs flying at high altitude.

Human Detection

Learning Camera Miscalibration Detection

1 code implementation24 May 2020 Andrei Cramariuc, Aleksandar Petrov, Rohit Suri, Mayank Mittal, Roland Siegwart, Cesar Cadena

Self-diagnosis and self-repair are some of the key challenges in deploying robotic platforms for long-term real-world applications.

Go Fetch: Mobile Manipulation in Unstructured Environments

no code implementations2 Apr 2020 Kenneth Blomqvist, Michel Breyer, Andrei Cramariuc, Julian Förster, Margarita Grinvald, Florian Tschopp, Jen Jen Chung, Lionel Ott, Juan Nieto, Roland Siegwart

With humankind facing new and increasingly large-scale challenges in the medical and domestic spheres, automation of the service sector carries a tremendous potential for improved efficiency, quality, and safety of operations.

Motion Planning

Active Interaction Force Control for Contact-Based Inspection with a Fully Actuated Aerial Vehicle

no code implementations20 Mar 2020 Karen Bodie, Maximilian Brunner, Michael Pantic, Stefan Walser, Patrick Pfändler, Ueli Angst, Roland Siegwart, Juan Nieto

A fully actuated and omnidirectional tilt-rotor aerial system is used to show capabilities of the control and planning methods.


End-to-End Velocity Estimation For Autonomous Racing

no code implementations15 Mar 2020 Sirish Srinivasan, Inkyu Sa, Alex Zyner, Victor Reijgwart, Miguel I. Valls, Roland Siegwart

Velocity estimation plays a central role in driverless vehicles, but standard and affordable methods struggle to cope with extreme scenarios like aggressive maneuvers due to the presence of high sideslip.

A Fully-Integrated Sensing and Control System for High-Accuracy Mobile Robotic Building Construction

no code implementations4 Dec 2019 Abel Gawel, Hermann Blum, Johannes Pankert, Koen Krämer, Luca Bartolomei, Selen Ercan, Farbod Farshidian, Margarita Chli, Fabio Gramazio, Roland Siegwart, Marco Hutter, Timothy Sandy

We present a fully-integrated sensing and control system which enables mobile manipulator robots to execute building tasks with millimeter-scale accuracy on building construction sites.

Trajectory Planning

SegMap: Segment-based mapping and localization using data-driven descriptors

2 code implementations27 Sep 2019 Renaud Dubé, Andrei Cramariuc, Daniel Dugas, Hannes Sommer, Marcin Dymczyk, Juan Nieto, Roland Siegwart, Cesar Cadena

We therefore present SegMap: a map representation solution for localization and mapping based on the extraction of segments in 3D point clouds.

Autonomous Driving Retrieval

An Efficient Sampling-based Method for Online Informative Path Planning in Unknown Environments

2 code implementations20 Sep 2019 Lukas Schmid, Michael Pantic, Raghav Khanna, Lionel Ott, Roland Siegwart, Juan Nieto

However, they are prone to local minima, resulting in sub-optimal trajectories, and sometimes do not reach global coverage.

3D Reconstruction

Long-Duration Fully Autonomous Operation of Rotorcraft Unmanned Aerial Systems for Remote-Sensing Data Acquisition

no code implementations18 Aug 2019 Danylo Malyuta, Christian Brommer, Daniel Hentzen, Thomas Stastny, Roland Siegwart, Roland Brockers

Vision-based precision landing is enabled by estimating the landing pad's pose using a bundle of AprilTag fiducials configured for detection from a wide range of altitudes.

Decision Making Pose Estimation

Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes

no code implementations1 Aug 2019 Nicolas Marchal, Charlotte Moraldo, Roland Siegwart, Hermann Blum, Cesar Cadena, Abel Gawel

Foreground objects are therefore detected as areas in an image for which the descriptors are unlikely given the background distribution.

Scene Understanding Semantic Segmentation

Revisiting Boustrophedon Coverage Path Planning as a Generalized Traveling Salesman Problem

1 code implementation22 Jul 2019 Rik Bähnemann, Nicholas Lawrance, Jen Jen Chung, Michael Pantic, Roland Siegwart, Juan Nieto

In this paper, we present a path planner for low-altitude terrain coverage in known environments with unmanned rotary-wing micro aerial vehicles (MAVs).


3D Multi-Robot Patrolling with a Two-Level Coordination Strategy

1 code implementation23 Jun 2019 Luigi Freda, Mario Gianni, Fiora Pirri, Abel Gawel, Renaud Dube, Roland Siegwart, Cesar Cadena

This target selection relies on a shared idleness representation and a coordination mechanism preventing topological conflicts.

Vocal Bursts Valence Prediction

OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios

no code implementations19 Mar 2019 Lukas Schaupp, Mathias Bürki, Renaud Dubé, Roland Siegwart, Cesar Cadena

We introduce a novel method for oriented place recognition with 3D LiDAR scans.


Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

2 code implementations IEEE ROBOTICS AND AUTOMATION LETTERS 2019 Margarita Grinvald, Fadri Furrer, Tonci Novkovic, Jen Jen Chung, Cesar Cadena, Roland Siegwart, Juan Nieto

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes.


VIZARD: Reliable Visual Localization for Autonomous Vehicles in Urban Outdoor Environments

no code implementations12 Feb 2019 Mathias Bürki, Lukas Schaupp, Marcin Dymczyk, Renaud Dubé, Cesar Cadena, Roland Siegwart, Juan Nieto

Changes in appearance is one of the main sources of failure in visual localization systems in outdoor environments.


From Coarse to Fine: Robust Hierarchical Localization at Large Scale

3 code implementations CVPR 2019 Paul-Edouard Sarlin, Cesar Cadena, Roland Siegwart, Marcin Dymczyk

In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization.

Autonomous Driving Retrieval +2

AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming

1 code implementation30 Sep 2018 Ciro Potena, Raghav Khanna, Juan Nieto, Roland Siegwart, Daniele Nardi, Alberto Pretto

The combination of aerial survey capabilities of Unmanned Aerial Vehicles with targeted intervention abilities of agricultural Unmanned Ground Vehicles can significantly improve the effectiveness of robotic systems applied to precision agriculture.

Optical Flow Estimation

Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space

1 code implementation20 Sep 2018 Berta Bescos, José Neira, Roland Siegwart, Cesar Cadena

In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames.

Image Inpainting Semantic Segmentation +1

An informative path planning framework for UAV-based terrain monitoring

1 code implementation8 Sep 2018 Marija Popovic, Teresa Vidal-Calleja, Gregory Hitz, Jen Jen Chung, Inkyu Sa, Roland Siegwart, Juan Nieto

Unmanned Aerial Vehicles (UAVs) represent a new frontier in a wide range of monitoring and research applications.


Modular Sensor Fusion for Semantic Segmentation

1 code implementation30 Jul 2018 Hermann Blum, Abel Gawel, Roland Siegwart, Cesar Cadena

Sensor fusion is a fundamental process in robotic systems as it extends the perceptual range and increases robustness in real-world operations.

Segmentation Semantic Segmentation +1

LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization

no code implementations12 Jul 2018 Marcin Dymczyk, Igor Gilitschenski, Juan Nieto, Simon Lynen, Bernhard Zeisl, Roland Siegwart

We propose LandmarkBoost - an approach that, in contrast to the conventional 2D-3D matching methods, casts the search problem as a landmark classification task.

Pose Retrieval Retrieval

Dynamic Objects Segmentation for Visual Localization in Urban Environments

no code implementations9 Jul 2018 Guoxiang Zhou, Berta Bescos, Marcin Dymczyk, Mark Pfeiffer, José Neira, Roland Siegwart

Yet, in highly dynamic environments, like crowded city streets, problems arise as major parts of the image can be covered by dynamic objects.

Pose Estimation Visual Localization +1

Long-term Large-scale Mapping and Localization Using maplab

1 code implementation28 May 2018 Marcin Dymczyk, Marius Fehr, Thomas Schneider, Roland Siegwart

This paper discusses a large-scale and long-term mapping and localization scenario using the maplab open-source framework.

SegMap: 3D Segment Mapping using Data-Driven Descriptors

1 code implementation25 Apr 2018 Renaud Dubé, Andrei Cramariuc, Daniel Dugas, Juan Nieto, Roland Siegwart, Cesar Cadena

While current methods extract descriptors for the single task of localization, SegMap leverages a data-driven descriptor in order to extract meaningful features that can also be used for reconstructing a dense 3D map of the environment and for extracting semantic information.

Data Compression

Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning

1 code implementation13 Mar 2018 Michel Breyer, Fadri Furrer, Tonci Novkovic, Roland Siegwart, Juan Nieto

We learn closed-loop policies mapping depth camera inputs to motion commands and compare different approaches to keep the problem tractable, including reward shaping, curriculum learning and using a policy pre-trained on a task with a reduced action set to warm-start the full problem.


Sparse 3D Topological Graphs for Micro-Aerial Vehicle Planning

2 code implementations12 Mar 2018 Helen Oleynikova, Zachary Taylor, Roland Siegwart, Juan Nieto

Micro-Aerial Vehicles (MAVs) have the advantage of moving freely in 3D space.


Cubic Range Error Model for Stereo Vision with Illuminators

no code implementations11 Mar 2018 Marius Huber, Timo Hinzmann, Roland Siegwart, Larry H. Matthies

In this work, we propose that the range error is cubic in range for stereo systems with integrated illuminators.


Flexible Stereo: Constrained, Non-rigid, Wide-baseline Stereo Vision for Fixed-wing Aerial Platforms

no code implementations19 Dec 2017 Timo Hinzmann, Tim Taubner, Roland Siegwart

This paper proposes a computationally efficient method to estimate the time-varying relative pose between two visual-inertial sensor rigs mounted on the flexible wings of a fixed-wing unmanned aerial vehicle (UAV).

Meteorology-Aware Multi-Goal Path Planning for Large-Scale Inspection Missions with Long-Endurance Solar-Powered Aircraft

no code implementations28 Nov 2017 Philipp Oettershagen, Julian Förster, Lukas Wirth, Jacques Ambühl, Roland Siegwart

While this makes them promising candidates for large-scale aerial inspection missions, their structural fragility necessitates that adverse weather is avoided using appropriate path planning methods.

maplab: An Open Framework for Research in Visual-inertial Mapping and Localization

1 code implementation28 Nov 2017 Thomas Schneider, Marcin Dymczyk, Marius Fehr, Kevin Egger, Simon Lynen, Igor Gilitschenski, Roland Siegwart

On the other hand, maplab provides the research community with a collection of multisession mapping tools that include map merging, visual-inertial batch optimization, and loop closure.


C-blox: A Scalable and Consistent TSDF-based Dense Mapping Approach

1 code implementation19 Oct 2017 Alexander Millane, Zachary Taylor, Helen Oleynikova, Juan Nieto, Roland Siegwart, César Cadena

Central to our approach is the representation of the environment as a collection of overlapping TSDF subvolumes.


Safe Local Exploration for Replanning in Cluttered Unknown Environments for Micro-Aerial Vehicles

2 code implementations2 Oct 2017 Helen Oleynikova, Zachary Taylor, Roland Siegwart, Juan Nieto

We perform extensive simulations to show that this system performs better than the standard approach of using an optimistic global planner, and also outperforms doing a single exploration step when the local planner is stuck.


X-View: Graph-Based Semantic Multi-View Localization

no code implementations28 Sep 2017 Abel Gawel, Carlo Del Don, Roland Siegwart, Juan Nieto, Cesar Cadena

Our findings show that X-View is able to globally localize aerial-to-ground, and ground-to-ground robot data of drastically different view-points.

A Data-driven Model for Interaction-aware Pedestrian Motion Prediction in Object Cluttered Environments

no code implementations25 Sep 2017 Mark Pfeiffer, Giuseppe Paolo, Hannes Sommer, Juan Nieto, Roland Siegwart, Cesar Cadena

This paper reports on a data-driven, interaction-aware motion prediction approach for pedestrians in environments cluttered with static obstacles.


Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps

no code implementations16 Sep 2017 Fabian Blöchliger, Marius Fehr, Marcin Dymczyk, Thomas Schneider, Roland Siegwart

Then, we create a set of convex free-space clusters, which are the vertices of the topological map.


weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming

1 code implementation11 Sep 2017 Inkyu Sa, Zetao Chen, Marija Popovic, Raghav Khanna, Frank Liebisch, Juan Nieto, Roland Siegwart

In this paper, we present an approach for dense semantic weed classification with multispectral images collected by a micro aerial vehicle (MAV).

General Classification Management

Control of a Quadrotor with Reinforcement Learning

1 code implementation17 Jul 2017 Jemin Hwangbo, Inkyu Sa, Roland Siegwart, Marco Hutter

In this paper, we present a method to control a quadrotor with a neural network trained using reinforcement learning techniques.


Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning

3 code implementations11 Nov 2016 Helen Oleynikova, Zachary Taylor, Marius Fehr, Juan Nieto, Roland Siegwart

We show that we can build TSDFs faster than Octomaps, and that it is more accurate to build ESDFs out of TSDFs than occupancy maps.


Visual Place Recognition with Probabilistic Vertex Voting

no code implementations11 Oct 2016 Mathias Gehrig, Elena Stumm, Timo Hinzmann, Roland Siegwart

We propose a novel scoring concept for visual place recognition based on nearest neighbor descriptor voting and demonstrate how the algorithm naturally emerges from the problem formulation.

Retrieval Visual Place Recognition

SegMatch: Segment based loop-closure for 3D point clouds

2 code implementations25 Sep 2016 Renaud Dubé, Daniel Dugas, Elena Stumm, Juan Nieto, Roland Siegwart, Cesar Cadena

We propose SegMatch, a reliable loop-closure detection algorithm based on the matching of 3D segments.


Robust Visual Place Recognition With Graph Kernels

no code implementations CVPR 2016 Elena Stumm, Christopher Mei, Simon Lacroix, Juan Nieto, Marco Hutter, Roland Siegwart

A novel method for visual place recognition is introduced and evaluated, demonstrating robustness to perceptual aliasing and observation noise.

Visual Place Recognition

Rolling Shutter Camera Calibration

no code implementations CVPR 2013 Luc Oth, Paul Furgale, Laurent Kneip, Roland Siegwart

Rolling Shutter (RS) cameras are used across a wide range of consumer electronic devices--from smart-phones to high-end cameras.

Camera Calibration

Cannot find the paper you are looking for? You can Submit a new open access paper.