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.

Localization of emergency acoustic sources by micro aerial vehicles

  • Authors: Basiri, Meysam; Schill, Felix; Lima, Pedro; Floreano, Dario

For micro aerial vehicles (MAVs) involved in search and rescue missions, the ability to locate the source of a distress sound signal is significantly important and allows fast localization of victims and rescuers during nighttime, through foliage and in dust, fog, and smoke. Most emergency sound sources, such as safety whistles and personal alarms, generate a narrowband signal that is difficult to localize by human listeners or with the common localization methods suitable for broadband sounds. In this paper, we present three methods for MAV-based emergency sound localization system. The first method involves designing a new emergency source for immediate localization by the MAV using a common localization method. The other two novel methods allow localizing the currently available emergency sources, or other narrowband sounds in general, that are difficult to localize due to the periodicity in the sequence of sound samples. The second method exploits the Doppler shift in the sound frequency, caused due to the motion of the MAV and the dynamics of the MAV to assist with the localization. The third method involves active control of the robot’s attitude and fusing acoustic and attitude measurements for achieving accurate and robust estimates. We evaluate our methods in real-world experiments with real flying robots.

Posted on: July 12, 2017

One Constraint at a Time: Using Viability Principles in Integrative Modeling of Macromolecular Assemblies

  • Authors: Tamo, Giorgio E.; Maesani, Andrea; Traeger, Sylvain; Degiacomi, Matteo Thomas; Floreano, Dario; Dal Peraro, Matteo

Reference

Posted on: July 10, 2017

Brain-actuated gait trainer with visual and proprioceptive feedback

  • Authors: Liu, Dong; Chen, Weihai; Lee, Kyuhwa; Chavarriaga, Ricardo; Bouri, Mohamed; Pei, Zhongcai; Millán, José del R.

Objective. Brain-machine interfaces (BMIs) have been proposed in closed-loop applications for neuromodulation and neurorehabilitation. This study describes the impact of different feedback modalities on the performance of an EEG-based BMI that decodes motor imagery (MI) of leg flexion and extension. Approach. We executed experiments in a lower-limb gait trainer (the legoPress) where nine able-bodied subjects participated in three consecutive sessions based on a crossover design. A random forest classifier was trained from the offline session and tested online with visual and proprioceptive feedback, respectively. Post-hoc classification was conducted to assess the impact of feedback modalities and learning effect (an improvement over time) on the simulated trial-based performance. Finally, we performed feature analysis to investigate the discriminant power and brain pattern modulations across the subjects. Main Results. (i) For real-time classification, the average accuracy was 62.33 ± 4.95% and 63.89 ± 6.41% for the two online sessions. The results were significantly higher than chance level, demonstrating the feasibility to distinguish between MI of leg extension and flexion. (ii) For post-hoc classification, the performance with proprioceptive feedback (69.45 ± 9.95%) was significantly better than with visual feedback (62.89 ± 9.20%), while there was no significant learning effect. (iii) We reported individual discriminate features and brain patterns associated to each feedback modality, which exhibited differences between the two modalities although no general conclusion can be drawn. Significance. The study reported a closed-loop brain-controlled gait trainer, as a proof of concept for neurorehabilitation devices. We reported the feasibility of decoding lower-limb movement in an intuitive and natural way. As far as we know, this is the first online study discussing the role of feedback modalities in lower-limb MI decoding. Our results suggest that proprioceptive feedback has an advantage over visual feedback, which could be used to improve robot-assisted strategies for motor training and functional recovery.

Posted on: July 10, 2017

Learning Externally Modulated Dynamical Systems

  • Authors: Sommer, Nicolas; Kronander, Klas; Billard, Aude

Dynamical Systems (DS) are often used to represent motion, with the advantage of being easy to learn from demonstrations. We present a method to modulate DS depending on an external signal, extending our previous work on Locally Modulated DS (LMDS, Kronander 2017). We present two applications of our system, which would not have been possible to achieve without taking external sensing into account in the DS motion formulation. The first application is a task of localization and grasping of objects, using our previous work on compliant tactile exploration. We successfully localize and grasp objects whose position is unknown, using touch in a simulated environment. In the second application, we teach a robot how to react to collisions in order to navigate between obstacles while reaching.

Posted on: June 30, 2017

Classification of Children"s Handwriting Errors for the Design of an Educational Co-writer Robotic Peer

  • Authors: Chandra, Shruti; Dillenbourg, Pierre; Paiva, Ana

In this paper, we propose a taxonomy of handwriting errors exhibited by children as a way to build adequate strategies for integration with a co-writing peer. The exploration includes the collection of letters written by children in an initial study, which were then revised in a second study. The second study also analyses the "peer-learning" (PL) and "peer-tutoring" (PT) learning methods in an educational scenario, where a pair of children perform a collaborative writing activity in the presence of a robot facilitator. The data obtained in the first two studies allowed us to create a "taxonomy of handwriting errors". A set of writing errors were selected and implemented in an educational activity for validation. This activity constituted a third study, wherein we systematically induced the errors into a Nao robot’s handwriting using the {PT} method – A teacher-child corrects the handwriting errors of the learner-robot. The preliminary results suggest that the children in general showed awareness to the writing errors and were able to perceive the writing abilities of the robot.

Posted on: June 30, 2017

Affect of Robot’s Competencies on Children’s Perception

  • Authors: Chandra, Shruti; Paradeda, Raul; Yin, Hang; Dillenbourg, Pierre; Prada, Rui; Paiva, Ana

The focus of the research described in this paper is to explore children’s perception of a social robot’s learning abilities and behavior in an educational context. With this purpose, we conducted a long-term study with children in a school by adopting the learning-by-teaching learning method. The scenario involves a ”learner-agent” (a robot) which seeks help from a child (a teacher) in correcting the shapes of a few letters it writes. Two versions of the robot were built: one where it learns and another where it does not improve over time. The results of the study suggest that children’s social relationship with the robot was not affected by the learning abilities of the agent.

Posted on: June 30, 2017

Developing Learning Scenarios to Foster Children"s Handwriting Skills with the Help of Social Robots

  • Authors: Chandra, Shruti; Dillenbourg, Pierre; Paiva, Ana

Social robots are being used to create better educationalscenarios, boosting children’s motivation and engagement.The focus of the research is to explore new ways to supportchildren in acquisition of their handwriting skills with thehelp of a social robot. With this perspective, three studiesare discussed to investigate aspects related to the learningmodes of child-robot interaction, children’s impression of asocial robot and classification of children’s common hand-writing difficulties

Posted on: June 29, 2017

Children’s Peer Assessment and Self-disclosure in the Presence of an Educational Robot

  • Authors: Chandra, Shruti; Alves-Oliveira, Patr´ıcia; Lemaignan, Severin; Sequeira, Pedro; Paiva, Ana; Dillenbourg, Pierre

Research in education has long established how children mutually influence and support each other’s learning trajectories, eventually leading to the development and widespread use of learning methods based on peer activities. In order to explore children’s learning behavior in the presence of a robotic facilitator during a collaborative writing activity, we investigated how they assess their peers in two specific group learning situations: peer-tutoring and peer-learning. Our scenario comprises of a pair of children performing a collaborative activity involving the act of writing a word/letter on a tactile tablet. In the peer-tutoring condition, one child acts as the teacher and the other as the learner, while in the peer-learning condition, both children are learners without the attribution of any specific role. Our experiment includes 40 children in total (between 6 and 8 years old) over the two conditions, each time in the presence of a robot facilitator. Our results suggest that the peer-tutoring situation leads to significantly more corrective feedback being provided, as well as the children more disposed to self-disclosure to the robot.

Posted on: June 29, 2017

Can a Child Feel Responsible for Another in the Presence of a Robot in a Collaborative Learning Activity?

  • Authors: Chandra, Shruti; Oliveira, Patricia; Lemaignan, Severin; Sequeira, Pedro; Paiva, Ana; Dillenbourg, Pierre

In order to explore the impact of integrating a robot as a facilitator in a collaborative activity, we examined interpersonal distancing of children both with a human adult and a robot facilitator. Our scenario involves two children performing a collaborative learning activity, which included the writing of a word/letter on a tactile tablet. Based on the learning-by-teaching paradigm, one of the children acted as a teacher when the other acted as a learner. Our study involved 40 children between 6 and 8 years old, in two conditions(robot or human facilitator). The results suggest first that the child acting as a teacher feel more responsible when the facilitator is a robot, compared to a human ; they show then that the interaction between a (teacher) child and a robot facilitator can be characterized as being a reciprocity-based interaction, whereas a human presence fosters a compensation-based interaction.

Posted on: June 29, 2017

Classification of Children"s Handwriting Errors for the Design of an Educational Co-writer Robotic Peer

  • Authors: Chandra, Shruti; Dillenbourg, Pierre; Paiva, Ana

In this paper, we propose a taxonomy of handwriting errors exhibited by children as a way to build adequate strategies for integration with a co-writing peer. The exploration includes the collection of letters written by children in an initial study, which were then revised in a second study. The second study also analyses the "peer-learning" (PL) and "peer-tutoring" (PT) learning methods in an educational scenario, where a pair of children perform a collaborative writing activity in the presence of a robot facilitator. The data obtained in the first two studies allowed us to create a "taxonomy of handwriting errors". A set of writing errors were selected and implemented in an educational activity for validation. This activity constituted a third study, wherein we systematically induced the errors into a Nao robot’s handwriting using the {PT} method – A teacher-child corrects the handwriting errors of the learner-robot. The preliminary results suggest that the children in general showed awareness to the writing errors and were able to perceive the writing abilities of the robot.

Posted on: June 29, 2017