Biblio

Peer review is a widely utilized pedagogical feedback mechanism for engaging students, which has been shown to improve educational outcomes. However, we find limited discussion and empirical measurement of peer review in visualization coursework. In addition to engagement, peer review provides direct and diverse feedback and reinforces recently-learned course concepts through critical evaluation of others’ work. In this paper, we discuss the construction and application of peer review in a computer science visualization course, including: projects that reuse code and visualizations in a feedback-guided, continual improvement process and a peer review rubric to reinforce key course concepts. To measure the effectiveness of the approach, we evaluate student projects, peer review text, and a post-course questionnaire from 3 semesters of mixed undergraduate and graduate courses. The results indicate that course concepts are reinforced with peer review—82% reported learning more because of peer review, and 75% of students recommended continuing it. Finally, we provide a road-map for adapting peer review to other visualization courses to produce more highly engaged students.

Amount and variety of training data drastically affect the performance of CNNs. Thus, annotation methods are becoming more and more critical to collect data efficiently. In this paper, we propose a simple yet efficient Interactive Self-Annotation framework to cut down both time and human labor cost for video object bounding box annotation. Our method is based on recurrent self-supervised learning and consists of two processes: automatic process and interactive process, where the automatic process aims to build a supported detector to speed up the interactive process. In the Automatic Recurrent Annotation, we let an off-the-shelf detector watch unlabeled videos repeatedly to reinforce itself automatically. At each iteration, we utilize the trained model from the previous iteration to generate better pseudo ground-truth bounding boxes than those at the previous iteration, recurrently improving self-supervised training the detector. In the Interactive Recurrent Annotation, we tackle the human-in-the-loop annotation scenario where the detector receives feedback from the human annotator. To this end, we propose a novel Hierarchical Correction module, where the annotated frame-distance binarizedly decreases at each time step, to utilize the strength of CNN for neighbor frames. Experimental results on various video datasets demonstrate the advantages of the proposed framework in generating high-quality annotations while reducing annotation time and human labor costs.

Recent years have witnessed several educational innovations to provide effective and engaging classroom instruction with the integration of immersive interactions based on augmented reality and virtual reality (AR/VR). This paper outlines the development of an ARCore-based application (app) that can impart interactive experiences for hands-on learning in engineering laboratories. The ARCore technology enables a smartphone to sense its environment and detect horizontal and vertical surfaces, thus allowing the smartphone to estimate any position in its workspace. In this mobile app, with touch-based interaction and AR feedback, the user can interact with a wheeled mobile robot and reinforce the concepts of kinematics for a differential drive mobile robot. The user experience is evaluated and system performance is validated through a user study with participants. The assessment shows that the proposed AR interface for interacting with the experimental setup is intuitive, easy to use, exciting, and recommendable.

Trip planning, which targets at planning a trip consisting of several ordered Points of Interest (POIs) under user-provided constraints, has long been treated as an important application for location-based services. The goal of trip planning is to maximize the chance that the users will follow the planned trip while it is difficult to directly quantify and optimize the chance. Conventional methods either leverage statistical analysis to rank POIs to form a trip or generate trips following pre-defined objectives based on constraint programming to bypass such a problem. However, these methods may fail to reflect the complex latent patterns hidden in the human mobility data. On the other hand, though there are a few deep learning-based trip recommendation methods, these methods still cannot handle the time budget constraint so far. To this end, we propose a TIme-aware Neural Trip Planning (TINT) framework to tackle the above challenges. First of all, we devise a novel attention-based encoder-decoder trip generator that can learn the correlations among POIs and generate trips under given constraints. Then, we propose a specially-designed reinforcement learning (RL) paradigm to directly optimize the objective to obtain an optimal trip generator. For this purpose, we introduce a discriminator, which distinguishes the generated trips from real-life trips taken by users, to provide reward signals to optimize the generator. Subsequently, to ensure the feedback from the discriminator is always instructive, we integrate an adversarial learning strategy into the RL paradigm to update the trip generator and the discriminator alternately. Moreover, we devise a novel pre-training schema to speed up the convergence for an efficient training process. Extensive experiments on four real-world datasets validate the effectiveness and efficiency of our framework, which shows that TINT could remarkably outperform the state-of-the-art baselines within short response time.

In this paper, an implementation of a human in the loop (HITL) technique for robot navigation in an indoor environment is described. The HITL technique is integrated into the reinforcement learning algorithms for mobile robot navigation. Reinforcement algorithms, specifically Q-learning and SARSA, are used combined with HITL since these algorithms are good in exploration and navigation. Turtlebot3 has been used as the robot for validating the algorithms by implementing the system using Robot Operating System and Gazebo. The robot-assisted with human feedback was found to be better in navigation task execution when compared to standard algorithms without using human in the loop. This is a work in progress and the next step of this research is exploring other reinforced learning methods and implementing them on a physical robot.

In present research, an empirical model for building and maintaining students' intrinsic motivation to learn is proposed. Unlike many other models of motivation, this model is not based on psychological theories but is derived directly from empirical observations made by experienced learners and educators. Thanks to empirical nature of the proposed model, its application to educational practice may be more straightforward in comparison with assumptions-based motivation theories. Interestingly, the structure of the proposed model resembles to some extent the structure of the oscillator circuit containing an amplifier and a positive feedback loop.

Learning movement control is a fundamental process integral to infant development. However, it is still unclear how infants learn to control leg movement. This work explores the potential of using socially assistive robots to provide real-time adaptive reinforcement learning for infants. Ten 6 to 8-month old typically-developing infants participated in a study where a robot provided reinforcement when the infant’s right leg acceleration fell within the range of 9 to 20 m/s2. If infants increased the proportion of leg accelerations in this band, they were categorized as "performers". Six of the ten participating infants were categorized as performers; the performer subgroup increased the magnitude of acceleration, proportion of target acceleration for right leg, and ratio of right/left leg acceleration peaks within the target acceleration band and their right legs increased movement intensity from the baseline to the contingency session. The results showed infants specifically adjusted their right leg acceleration in response to a robot- provided reward. Further study is needed to understand how to improve human-robot interaction policies for personalized interventions for young infants.

Recent scientific results show that audio feedback associated with body movements can be fundamental during the development to learn new spatial concepts [1], [2]. Within the weDraw project [3], [4], we have investigated how this link can be useful to learn mathematical concepts. Here we present a study investigating how mathematical skills changes after multisensory training based on human-computer interaction (RobotAngle and BodyFraction activities). We show that embodied angle and fractions exploration associated with audio and visual feedback can be used in typical children to improve cognition of spatial mathematical concepts. We finally present the exploitation of our results: an online, optimized version of one of the tested activity to be used at school. The training result suggests that audio and visual feedback associated with body movements is informative for spatial learning and reinforces the idea that spatial representation development is based on sensory-motor interactions.