Search for: All records

Human-Robot Collaboration (HRC) aims to create environments where robots can understand workspace dynamics and actively assist humans in operations, with the human intention recognition being fundamental to efficient and safe task fulfillment. Language-based control and communication is a natural and convenient way to convey human intentions. However, traditional language models require instructions to be articulated following a rigid, predefined syntax, which can be unnatural, inefficient, and prone to errors. This paper investigates the reasoning abilities that emerged from the recent advancement of Large Language Models (LLMs) to overcome these limitations, allowing for human instructions to be used to enhance human-robot communication. For this purpose, a generic GPT 3.5 model has been fine-tuned to interpret and translate varied human instructions into essential attributes, such as task relevancy and tools and/or parts required for the task. These attributes are then fused with perceived on-going robot action to generate a sequence of relevant actions. The developed technique is evaluated in a case study where robots initially misinterpreted human actions and picked up wrong tools and parts for assembly. It is shown that the fine-tuned LLM can effectively identify corrective actions across a diverse range of instructional human inputs, thereby enhancing the robustness of human-robot collaborative assembly for smart manufacturing. 

This study reported the process of developing and evaluating a student-facing learning analytics dashboard (LAD) for an online STEM skill practice system from a user experience approach. A usability survey was administered to 19 LAD users to gather information on what the learners believed were the most important features and what needed to be done to further improve the design of the LAD. Our findings showed that the most important LAD feature to students was showing the accuracy level of their practice and providing the option to redo the practice. These findings informed the revisions of the preliminary design of the LAD and provided insights into future development of student-facing LADs in online learning environments. 

Though many studies suggest the positive effects of gamification on participants’ learning and motivation, limited research has examined the basic psychological needs satisfaction in gamified learning. Based on self-determination theory (SDT), this study examined students’ actual competence, perceived competence, perceived autonomy, and perceived relatedness in a gamified math practice. The results showed that students had varied degree of needs satisfaction in perceived competence, perceived autonomy, and perceived relatedness. The implications and significance of the study provide practical teaching implementation suggestions and research insights for gamification research. 

Despite the potential of learning analytics dashboards (LADs) to support learners’ needs for autonomy, little research has been conducted on designing LADs to support student autonomy. In this paper, we reported the process of designing a student-facing LAD that offers students’ autonomy support by providing necessary information for students to set their own goals and choose learning activities that are aligned with their goals. A leaderboard was also integrated into the LAD to promote student motivation. Reeves’s (2006) design-based research model was adopted to develop the LAD. The final version of the LAD was presented, and the significance of the work was discussed. 

Outside-knowledge visual question answering (OKVQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question. Most previous works address the problem by first fusing the image and question in the multi-modal space, which is inflexible for further fusion with a vast amount of external knowledge. In this paper, we call for an alternative paradigm for the OK-VQA task, which transforms the image into plain text, so that we can enable knowledge passage retrieval, and generative question-answering in the natural language space. This paradigm takes advantage of the sheer volume of gigantic knowledge bases and the richness of pretrained language models. A Transform-Retrieve-Generate framework (TRiG) framework is proposed, which can be plug-and-played with alternative image-to-text models and textual knowledge bases. Experimental results show that our TRiG framework outperforms all state-of-the-art supervised methods by at least 11.1% absolute margin. 

We present a deep learning-based method for estimating the neutrino energy of charged-current neutrino-argon interactions. We employ a recurrent neural network (RNN) architecture for neutrino energy estimation in the MicroBooNE experiment, utilizing liquid argon time projection chamber (LArTPC) detector technology. Traditional energy estimation approaches in LArTPCs, which largely rely on reconstructing and summing visible energies, often experience sizable biases and resolution smearing because of the complex nature of neutrino interactions and the detector response. The estimation of neutrino energy can be improved after considering the kinematics information of reconstructed final-state particles. Utilizing kinematic information of reconstructed particles, the deep learning-based approach shows improved resolution and reduced bias for the muon neutrino Monte Carlo simulation sample compared to the traditional approach. In order to address the common concern about the effectiveness of this method on experimental data, the RNN-based energy estimator is further examined and validated with dedicated data-simulation consistency tests using MicroBooNE data. We also assess its potential impact on a neutrino oscillation study after accounting for all statistical and systematic uncertainties and show that it enhances physics sensitivity. This method has good potential to improve the performance of other physics analyses.

Published by the American Physical Society2024