Stéphane Magnenat

Candli is a web-based educational game creation app in which children acquire STEAM skills by creating video games based on their own drawings. Candli allows children to program games using an accessible visual programming language inspired by established research traditions such as Scratch and Thymio VPL. While such languages are highly expressive, enabling rapid creation of dynamic and engaging agent behaviors, this very efficiency can pose challenges in classroom settings. In particular, children often encounter non-trivial problems quickly, leading to teacher overload and hindering learning. To mitigate this issue, Candli integrates technical scaffolding features designed to support children’s autonomous learning. In this workshop, we explore two such features: linting and adaptive program completion hints. The linting feature draws inspiration from software engineering practices, providing immediate feedback to students about potential errors in their code – a feature rarely utilized in educational contexts. Adaptive program completion hints employ classical AI reasoning to incrementally guide students based on their existing code structure. This method involves comparing the current student code with predefined Prolog-like solution rules and suggesting minimal, targeted corrections that do not compromise other program functionalities. These features assist learners in developing accurate notional machines for understanding code execution while preserving opportunities for free exploration and playful tinkering. Collectively, these tools offer a concrete realization of constructionist learning principles.

Background: Digital technologies have expanded the options for delivering psychotherapy, permitting for example, the treatment of schizophrenia using Avatar Therapy. Despite its considerable potential, this treatment method has not been widely disseminated. As a result, its operability and functionality remain largely unknown. Objective: We aimed to study the usability of a therapeutic virtual reality human–human interface, created in a game engine. Methods: Participants were psychiatric hospital staff who were introduced to the therapeutic platform in a hands-on session. The System Usability Scale (SUS) was employed for evaluation purposes. Statistical evaluation was conducted using descriptive statistics, the chi-square test, analysis of variance, and multilevel factor analysis. Results: In total, 109 staff members were introduced to the therapeutic tool and completed the SUS. The mean SUS global score was 81.49 (SD 11.1). Psychotherapists (mean 86.44, SD 8.79) scored significantly higher (F2,106=6.136; P=.003) than nursing staff (mean 79.01, SD 13.30) and administrative personnel (mean 77.98, SD 10.72). A multilevel factor analysis demonstrates a different factor structure for each profession. Conclusions: In all professional groups in this study, the usability of a digital psychotherapeutic tool developed using a game engine achieved the benchmark for an excellent system, scoring highest among the professional target group (psychotherapists). The usability of the system seems, to some extent, to be dependent on the professional background of the user. It is possible to create and customize novel psychotherapeutic approaches with gaming technologies and platforms. Trial Registration: Clinicaltrials.gov NCT04099940; http://clinicaltrials.gov/ct2/show/NCT04099940

BACKGROUND Digital technologies have expanded the options for delivering psychotherapy, permitting for example, the treatment of schizophrenia using Avatar Therapy. Despite its considerable potential, this treatment method has not been widely disseminated. As a result, its operability and functionality remain largely unknown. OBJECTIVE We aimed to study the usability of a therapeutic virtual reality human–human interface, created in a game engine. METHODS Participants were psychiatric hospital staff who were introduced to the therapeutic platform in a hands-on session. The System Usability Scale (SUS) was employed for evaluation purposes. Statistical evaluation was conducted using descriptive statistics, the chi-square test, analysis of variance, and multilevel factor analysis. RESULTS In total, 109 staff members were introduced to the therapeutic tool and completed the SUS. The mean SUS global score was 81.49 (SD 11.1). Psychotherapists (mean 86.44, SD 8.79) scored significantly higher (F2,106=6.136; P=.003) than nursing staff (mean 79.01, SD 13.30) and administrative personnel (mean 77.98, SD 10.72). A multilevel factor analysis demonstrates a different factor structure for each profession. CONCLUSIONS In all professional groups in this study, the usability of a digital psychotherapeutic tool developed using a game engine achieved the benchmark for an excellent system, scoring highest among the professional target group (psychotherapists). The usability of the system seems, to some extent, to be dependent on the professional background of the user. It is possible to create and customize novel psychotherapeutic approaches with gaming technologies and platforms. CLINICALTRIAL Clinicaltrials.gov NCT04099940; http://clinicaltrials.gov/ct2/show/NCT04099940

The strong interest children show for mobile robots makes these devices potentially powerful to teach programming. Moreover, the tangibility of physical objects and the sociability of interacting with them are added benefits. A key skill that novices in programming have to acquire is the ability to mentally trace program execution. However, because of their embodied and real-time nature, robots make the mental tracing of program execution difficult. To address this difficulty, in this paper we propose an automatic program evaluation framework based on a robot simulator. We describe a real-time implementation providing feedback and gamified hints to students. In a user study, we demonstrate that our hint system increases the percentage of students writing correct programs from 50% to 96%, and decreases the average time to write a correct program by 30%. However, we could not show any correlation between the use of the system and the performance of students on a questionnaire testing concept acquisition. This suggests that programming skills and concept understanding are different abilities. Overall, the clear performance gain shows the value of our approach for programming education using robots.

Mobile robots are valuable tools for education because of both the enthusiasm they raise and the multidisciplinary nature of robotics technology. Mobile robots give access to a wide range of fields, such as complex mechanics, sensors, wireless transmission, mathematics, and computer science. However, despite their potential as educational tools, robots are still not as widespread in schools as they could be. In this article, we identify five key reasons: lack of diversity, high cost, noninclusive design, lack of educational material, and lack of stability over time. Then, we describe our answers to these problems, as we implemented them in the Thymio project: a mature mass-produced open-hardware robot, at a low price, with a multiage and gender-neutral feature set, and with a design promoting creativity, facilitating learning, and providing a wide range of interaction possibilities from built-in behaviors to text programming, passing through different visual programming environments. We highlight some neglected key issues that differentiate open-source hardware from open-source software, for instance the legal uncertainty of designing open hardware using professional computer-aided design (CAD) tools and the difficulty to distribute the development. Our solution to these being to increase the awareness of CAD editors to open-source hardware and to provide a two-layer development model for hardware.

Coloring books capture the imagination of children and provide them with one of their earliest opportunities for creative expression. However, given the proliferation and popularity of digital devices, real-world activities like coloring can seem unexciting, and children become less engaged in them. Augmented reality holds unique potential to impact this situation by providing a bridge between real-world activities and digital enhancements. In this paper, we present an augmented reality coloring book App in which children color characters in a printed coloring book and inspect their work using a mobile device. The drawing is detected and tracked, and the video stream is augmented with an animated 3-D version of the character that is textured according to the child's coloring. This is possible thanks to several novel technical contributions. We present a texturing process that applies the captured texture from a 2-D colored drawing to both the visible and occluded regions of a 3-D character in real time. We develop a deformable surface tracking method designed for colored drawings that uses a new outlier rejection algorithm for real-time tracking and surface deformation recovery. We present a content creation pipeline to efficiently create the 2-D and 3-D content. And, finally, we validate our work with two user studies that examine the quality of our texturing algorithm and the overall App experience.

In our previous research, we showed that students using the educational robot Thymio and its visual programming environment were able to learn the important computer-science concept of event-handling. This paper extends that work by integrating augmented reality (AR) into the activities. Students used a tablet that displays in real time the event executed on the robot. The event is overlaid on the tablet over the image from a camera, which shows the location of the robot when the event was executed. In addition, visual feedback (FB) was implemented in the software. We developed a novel video questionnaire to investigate the performance of the students on robotics tasks. Data were collected comparing four groups: AR+FB, AR+non-FB, non-AR+FB, non-AR+non-FB. The results showed that students receiving feedback made significantly fewer errors on the tasks. Those using AR made fewer errors, but this improvement was not significant, although their performance improved. Technical problems with the AR hardware and software showed where improvements are needed.

Large scale, long-term, distributed mapping is a core challenge to modern field robotics. Using the sensory output of multiple robots and fusing it in an efficient way enables the creation of globally accurate and consistent metric maps. To combine data from multiple agents into a global map, most existing approaches use a central entity that collects and manages the information from all agents. Often, the raw sensor data of one robot needs to be made available to processing algorithms on other agents due to the lack of computational resources on that robot. Unfortunately, network latency and low bandwidth in the field limit the generality of such an approach and make multi-robot map building a tedious task. In this paper, we present a distributed and decentralized back-end for concurrent and consistent robotic mapping. We propose a set of novel approaches that reduce the bandwidth usage and increase the effectiveness of inter-robot communication for distributed mapping. Instead of locking access to the map during operations, we define a version control system which allows concurrent and consistent access to the map data. Updates to the map are then shared asynchronously with agents which previously registered notifications. A technique for data lookup is provided by state-of-the-art algorithms from distributed computing. We validate our approach on real-world datasets and demonstrate the effectiveness of the proposed algorithms.