Looking for publications? All our latest publications are listed here, and you can also use our search functions to help find what you are looking for. Power users might also want to consider searching on the EPFL Infoscience site which provides advanced publication search capabilities.

A computer science and robotics integration model for primary school: evaluation of a large-scale in-service K-4 teacher-training program

Authors: El-Hamamsy, Laila; Chessel-Lazzarotto, Frédérique; Bruno, Barbara; Roy, Didier; Cahlikova, Tereza; Chevalier, Morgane; Parriaux, Gabriel; Pellet, Jean-Philippe; Lanarès, Jacques; Dehler Zufferey, Jessica & Mondada, Francesco

 

Abstract

Integrating computer science (CS) into school curricula has become a worldwide preoccupation. Therefore, we present a CS and Robotics integration model and its validation through a large-scale pilot study in the administrative region of the Canton Vaud in Switzerland. Approximately 350 primary school teachers followed a mandatory CS continuing professional development program (CPD) of adapted format with a curriculum scaffolded by instruction modality. This included CS Unplugged activities that aim to teach CS concepts without the use of screens, and Robotics Unplugged activities that employed physical robots, without screens, to learn about robotics and CS concepts. Teachers evaluated positively the CPD and their representation of CS improved. Voluntary adoption rates reached 97% during the CPD and 80% the following year. These results combined with the underpinning literature support the generalisability of the model to other contexts.

Reference

  • Published in: Education and Information Technologies
  • DOI: 10.1007/s10639-020-10355-5
  • Read paper
  • Date: 2020
Posted on: January 4, 2021

How fast is too fast? The role of perception latency in high-speed sense and avoid.

Authors: Davide Falanga, Suseong Kim, & Davide Scaramuzza

 

Abstract

In this letter, we study the effects that perception latency has on the maximum speed a robot can reach to safely navigate through an unknown cluttered environment. We provide a general analysis that can serve as a baseline for future quantitative reasoning for design tradeoffs in autonomous robot navigation. We consider the case where the robot is modeled as a linear secondorder system with bounded input and navigates through static obstacles. Also, we focus on a scenario where the robot wants to reach a target destination in as little time as possible, and therefore cannot change its longitudinal velocity to avoid obstacles. We show how the maximum latency that the robot can tolerate to guarantee safety is related to the desired speed, the range of its sensing pipeline, and the actuation limitations of the platform (i.e., the maximum acceleration it can produce). As a particular case study, we compare monocular and stereo frame-based cameras against novel, low-latency sensors, such as event cameras, in the case of quadrotor flight. To validate our analysis, we conduct experiments on a quadrotor platform equipped with an event camera to detect and avoid obstacles thrown towards the robot. To the best of our knowledge, this is the first theoretical work in which perception and actuation limitations are jointly considered to study the performance of a robotic platform in high-speed navigation.

Reference

  • Published in: IEEE Robotics and Automation Letters
  • DOI: 10.1109/LRA.2019.2898117
  • Read paper
  • Date: 2019
Posted on: December 17, 2020

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

Authors: Karen Bodie, Maximilian Brunner, Michael Pantic, Stefan Walser, Patrick Pfändler, Ueli Angst, Roland Siegwart & Juan Nieto

 

Abstract

This paper presents and validates active interaction force control and planning for fully actuated and omnidirectional aerial manipulation platforms, with the goal of aerial contact inspection in unstructured environments. We present a variable axis-selective impedance control which integrates direct force control for intentional interaction, using feedback from an onboard force sensor. The control approach aims to reject disturbances in free flight, while handling unintentional interaction, and actively controlling desired interaction forces. A fully actuated and omnidirectional tilt-rotor aerial system is used to show capabilities of the control and planning methods. Experiments demonstrate disturbance rejection, push-and-slide interaction, and force controlled interaction in different flight orientations. The system is validated as a tool for non-destructive testing of concrete infrastructure, and statistical results of interaction control performance are presented and discussed.

Reference

  • Published in: IEEE Transactions on Robotics
  • DOI: 10.1109/TRO.2020.3036623
  • Video
  • Date: 2020
Posted on: December 1, 2020

An Open‐Source System for Vision‐Based Micro‐Aerial Vehicle Mapping, Planning, and Flight in Cluttered Environments

Authors: Helen Oleynikova, Christian Lanegger, Zachary Taylor, Michael Pantic, Alexander Millane, Roland Siegwart & Juan Nieto

 

Abstract

We present an open‐source system for Micro‐Aerial Vehicle (MAV) autonomous navigation from vision‐based sensing. Our system focuses on dense mapping, safe local planning, and global trajectory generation, especially when using narrow field‐of‐view sensors in very cluttered environments. In addition, details about other necessary parts of the system and special considerations for applications in real‐world scenarios are presented. We focus our experiments on evaluating global planning, path smoothing, and local planning methods on real maps made on MAVs in realistic search‐and‐rescue and industrial inspection scenarios. We also perform thousands of simulations in cluttered synthetic environments, and finally validate the complete system in real‐world experiments.

Reference

  • Published in: Journal of Field Robotics
  • DOI: 10.1002/rob.21950
  • Read paper
  • Video
  • Date: 2020
Posted on: November 27, 2020

Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps

Authors: Victor Reijgwart*, Alexander Millane*, Helen Oleynikova, Roland Siegwart, Cesar Cadena, Juan Nieto

 

Abstract

Globally consistent dense maps are a key requirement for long-term robot navigation in complex environments. While previous works have addressed the challenges of dense mapping and global consistency, most require more computational resources than may be available on-board small robots. We propose a framework that creates globally consistent volumetric maps on a CPU and is lightweight enough to run on computationally constrained platforms.
Our approach represents the environment as a collection of overlapping Signed Distance Function (SDF) submaps, and maintains global consistency by computing an optimal alignment of the submap collection. By exploiting the underlying SDF representation, we generate correspondence-free constraints between submap pairs that are computationally efficient enough to optimize the global problem each time a new submap is added. We deploy the proposed system on a hexacopter MAV with an Intel i7-8650U CPU in two realistic scenarios: mapping a large-scale area using a 3D LiDAR, and mapping an industrial space using an RGB-D camera. In the large-scale outdoor experiments, the system optimizes a 120x80m map in less than 4s and produces absolute trajectory RMSE of less than 1m over 400m trajectories. Our complete system, called voxgraph, is available as open source (https://github.com/ethz-asl/voxgraph).

Reference

  • Published in: IEEE Robotics and Automation Letters (Volume: 5, Issue: 1, Jan. 2020)
  • DOI: 10.1109/LRA.2019.2953859
  • Read paper
  • Date: 2019
Posted on: November 27, 2020

Bioinspired wing and tail morphing extends drone flight capabilities

Authors: Ajanic, Enrico ; Feroskhan, Mir ; Mintchev, Stefano ; Noca, Flavio ; Floreano, Dario

 

Abstract

The aerodynamic designs of winged drones are optimized for specific flight regimes. Large lifting surfaces provide maneuverability and agility but result in larger power consumption, and thus lower range, when flying fast compared with small lifting surfaces. Birds like the northern goshawk meet these opposing aerodynamic requirements of aggressive flight in dense forests and fast cruising in the open terrain by adapting wing and tail areas. Here, we show that this morphing strategy and the synergy of the two morphing surfaces can notably improve the agility, maneuverability, stability, flight speed range, and required power of a drone in different flight regimes by means of an avian-inspired drone. We characterize the drone’s flight capabilities for different morphing configurations in wind tunnel tests, optimization studies, and outdoor flight tests. These results shed light on the avian use of wings and tails and offer an alternative design principle for drones with adaptive flight capabilities.

Reference

  • Published in: Science Robotics, 5(47)
  • DOI: 10.1126/scirobotics.abc2897
  • Read paper
  • Date: 2020
Posted on: November 10, 2020

Biomechanical effects of passive hip springs during walking

Authors: Haufe, F. L. ; Wolf, P. ; Riener, R. ; Grimmer, M.

Abstract

Passive spring-like structures can store and return energy during cyclic movements and thereby reduce the energetic cost of locomotion. That makes them important components of the human body and wearable assistive devices alike. This study investigates how springs placed anteriorly across the hip joint affect leg joint angles and powers, and leg muscle activities during level walking at 0.5 to 2.1 m/s. We hypothesized that the anterior hip springs (I) load hip extension, (II) support hip flexion and (III) affect ankle muscle activity and dynamics during walking. Effects at the ankle were expected because hip and ankle redistribute segmental power in concert to achieve forward progression. We observed that the participants’ contribution to hip power did not increase during hip extension as the spring stored energy. Simultaneously, the activities of plantarflexor muscles that modulate energy storage in the Achilles tendon were reduced by 28% (gastrocnemius medialis) and 9% (soleus). As the spring returned energy with the onset of hip flexion, the participants’ contribution to hip power was reduced by as much as 23%. Soleus activity before push-off increased by up to 9%. Instead of loading hip extension, anterior hip springs seem to store and return parts of the energy normally exchanged with the Achilles tendon. Thereby, the springs support hip flexion but may reduce elastic energy storage in and hence recoil from the Achilles tendon. This interaction should be considered during the design and simulation of wearable assistive devices as it might – depending on user characteristics – enhance or diminish their overall functionality.

Reference

  • Published in: Journal of Biomechanics (Volume 98, 2. January 2020, 109432)
  • DOI: 10.1016/j.jbiomech.2019.109432
  • Read paper
  • Date: 2020
Posted on: May 10, 2020

Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches

Authors: Mantegazza, D. ; Guzzi, J.; Gambardella, L. M.; Giusti, A.

Abstract

We consider the task of controlling a quadrotor to hover in front of a freely moving user, using input data from an onboard camera. On this specific task we compare two widespread learning paradigms: a mediated approach, which learns a high-level state from the input and then uses it for deriving control signals; and an end-to-end approach, which skips high-level state estimation altogether. We show that despite their fundamental difference, both approaches yield equivalent performance on this task. We finally qualitatively analyze the behavior of a quadrotor implementing such approaches.

Reference

  • Published in: 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 6489-6495
  • DOI: doi: 10.1109/ICRA.2019.8794377
  • Read paper
  • Date: 2019
Posted on: May 10, 2020

Matching Features without Descriptors:Implicitly Matched Interest Points

Authors: Cieslewski, T. ; Bloesch, M. ; Scaramuzza, D.

Abstract

The extraction and matching of interest points is a prerequisite for many geomet-ric computer vision problems. Traditionally, matching has been achieved by assigningdescriptors to interest points and matching points that have similar descriptors. In this pa-per, we propose a method by which interest points are instead already implicitly matchedat detection time. With this, descriptors do not need to be calculated, stored, commu-nicated, or matched any more. This is achieved by a convolutional neural network withmultiple output channels and can be thought of as a collection of a variety of detec-tors, each specialised to specific visual features. This paper describes how to design andtrain such a network in a way that results in successful relative pose estimation perfor-mance despite the limitation on interest point count. While the overall matching score isslightly lower than with traditional methods, the approach is descriptor free and thus en-ables localization systems with a significantly smaller memory footprint and multi-agentlocalization systems with lower bandwidth requirements. The network also outputs theconfidence for a specific interest point resulting in a valid match. We evaluate perfor-mance relative to state-of-the-art alternatives.

Reference

  • Presented at: British Machine Vision Conference (BMVC), Cardiff, UK, 2019
  • Read paper
  • Date: 2019
Posted on: May 10, 2020

Trajectory features estimation for legged robots

Authors: Chavez-Garcia, R. O. ; Guzzi, J. ; Giusti, A. ; Gambardella, L. M.

Reference

  • Presented at: IEEE International Conference on Robotics and Automation (ICRA) 2019, Montreal, QC, Canada, May 20-24, 2019
  • Date: 2019
Posted on: May 10, 2020