Archives: Publications

• Authors:
  Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 57
  Cardona, Jaiber; Caicedo, Eduardo; Alfonso, Wilfredo; Chavarriaga, Ricardo; Millán, José del R.

Steady State Visually Evoked Potentials (SSVEP) are signals produced in the occipital part of the brain when someone gaze a light flickering at a fixed frequency. These signals have been used for Brain Machine Interfacing (BMI), where one or more stimuli are presented and the system has to detect what is the stimulus the user is attending to. It has been proposed that the SSVEP signal is produced by superposition of Visually Evoked Potentials (VEP) but there is not a model that shows that. We propose a model for a SSVEP signal that is a superposition of the response to the rising and falling edges of the stimuli and that can be calculated for different frequencies. This model is based in the phase between the stimulus and the SSVEP signal considering that the phase is stable over the time. We fit the model for 4 volunteers that gazed stimuli in the frequencies of 9hz, 11hz, 13hz and 15hz, and duty-cycles of 20%, 35%, 50%, 65% and 80%. We found the parameters of the model for every volunteer using the data of Oz electrode and a genetic algorithm. The proposed model is useful for find the best duty-cycle of the stimulus and it can be useful for select a code in the stimuli different for a square signal, the model only consider one frequency at the same time, but the results showed that it could be possible to find a more generic model.

• Authors:
  Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 57
  Forster, Christian; Carlone, Luca; Dellaert, Frank; Scaramuzza, Davide

Current approaches for visual-inertial odometry (VIO) are able to attain highly accurate state estimation via nonlinear optimization. However, real-time optimization quickly becomes infeasible as the trajectory grows over time; this problem is further emphasized by the fact that inertial measurements come at high rate, hence leading to fast growth of the number of variables in the optimization. In this paper, we address this issue by preintegrating inertial measurements between selected keyframes into single relative motion constraints. Our first contribution is a preintegration theory that properly addresses the manifold structure of the rotation group. We formally discuss the generative measurement model as well as the nature of the rotation noise and derive the expression for the maximum a posteriori state estimator. Our theoretical development enables the computation of all necessary Jacobians for the optimization and a-posteriori bias correction in analytic form. The second contribution is to show that the preintegrated IMU model can be seamlessly integrated into a visual-inertial pipeline under the unifying framework of factor graphs. This enables the application of incremental-smoothing algorithms and the use of a structureless model for visual measurements, which avoids optimizing over the 3D points, further accelerating the computation. We perform an extensive evaluation of our monocular VIO pipeline on real and simulated datasets. The results confirm that our modelling effort leads to accurate state estimation in real-time, outperforming state-of-the-art approaches.

• Authors:
  Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 57
  Rebecq, Henri; Gallego, Guillermo; Scaramuzza, Davide

Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. They offer significant advantages over standard cameras, namely a very high dynamic range, no motion blur, and a latency in the order of microseconds. However, because the output is composed of a sequence of asynchronous events rather than actual intensity images, traditional vision algorithms cannot be applied, so that a paradigm shift is needed. We introduce the problem of Event-based Multi-View Stereo (EMVS) for event cameras and propose a solution to it. Unlike traditional MVS methods, which address the problem of estimating dense 3D structure from a set of known viewpoints, EMVS estimates semi-dense 3D structure from an event camera with known trajectory. Our EMVS solution elegantly exploits two inherent properties of an event camera: (i) its ability to respond to scene edges—which naturally provide semidense geometric information without any pre-processing operation—and (ii) the fact that it provides continuous measurements as the sensor moves. Despite its simplicity (it can be implemented in a few lines of code), our algorithm is able to produce accurate, semidense depth maps. We successfully validate our method on both synthetic and real data. Our method is computationally very efficient and runs in real-time on a CPU.

• Authors:
  Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 57
  Delmerico, Jeffrey; Giusti, Alessandro; Mueggler, Elias; Gambardella, Luca Maria; Scaramuzza, Davide

We consider the problem of performing rapid training of a terrain classier in the context of a collaborative robotic search and rescue system. Our system uses a vision-based flying robot to guide a ground robot through unknown terrain to a goal location by building a map of terrain class and elevation. However, due to the unknown environments present in search and rescue scenarios, our system requires a terrain classifier that can be trained and deployed quickly, based on data collected on the spot. We investigate the relationship of training set size and complexity on training time and accuracy, for both feature-based and convolutional neural network classifiers in this scenario. Our goal is to minimize the deployment time of the classifiers in our terrain mapping system within acceptable classifcation accuracy tolerances. So we are not concerned with training a classifier that generalizes well, only one that works well for this particular environment. We demonstrate that we can launch our aerial robot, gather data, train a classifier, and begin building a terrain map after only 60 seconds of flight.