The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH offers a novel hierarchical mechanism by introducing Social Value Orientation (SVO) as a temporally extended latent variable that plays a central role in both policy generation and reward assignment. To support this hierarchical decision-making process, we introduce Social-aware Multi-Policy PPO (SMP3O), a reinforcement learning method that ensures stable and effective training through a mechanism for the cross-utilization of advantages. Moreover, we design an SVO-based learning tie-breaking algorithm, allowing agents to proactively avoid collisions, rather than relying solely on post-processing techniques. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. Our comparative experiments show that SYLPH achieves state-of-the-art performance, surpassing other learning-based MAPF planners in random, room-like, and maze-like maps, while our ablation studies demonstrate the advantages of each component in SYLPH. We finally experimentally validate our trained policies on hardware in three types of maps, showing how SYLPH allows agents to find high-quality paths under real-life conditions. Our code and videos are available at: marmotlab.github.io/mapf_sylph.

Teacher behavior description is an objective record of teachers’ behaviors in the teaching process, aiming to provide evidence for reflection on teaching behavior. Although video captioning technology can automatically generate behavior description, existing research on teacher behavior description is mostly limited to case studies due to the lack of relevant datasets. At the same time, existing video captioning methods cannot effectively capture the dynamic characteristics of teacher behavior in real classrooms. In this paper, we propose a novel spatio-temporal graph neural network (STGN), which represents teacher-student interactions in the spatial domain using action features and models the temporal relationships of teachers guided by contextual information. The model achieves satisfactory results on both the proprietary teacher behavior description (TBD) dataset and two public datasets, MSR-VTT and MSVD, demonstrating the effectiveness of our approach.

The Multi-Agent Path Finding (MAPF) problem aims to determine the shortest and collision-free paths for multiple agents in a known, potentially obstacle-ridden environment. It is the core challenge for robotic deployments in large-scale logistics and transportation. Decentralized learningbased approaches have shown great potential for addressing the MAPF problems, offering more reactive and scalable solutions. However, existing learning-based MAPF methods usually rely on agents making decisions based on a limited field of view (FOV), resulting in short-sighted policies and inefficient cooperation in complex scenarios. There, a critical challenge is to achieve consensus on potential movements between agents based on limited observations and communications. To tackle this challenge, we introduce a new framework that applies sheaf theory to decentralized deep reinforcement learning, enabling agents to learn geometric cross-dependencies between each other through local consensus and utilize them for tightly cooperative decision-making. In particular, sheaf theory provides a mathematical proof of conditions for achieving global consensus through local observation. Inspired by this, we incorporate a neural network to approximately model the consensus in latent space based on sheaf theory and train it through self-supervised learning. During the task, in addition to normal features for MAPF as in previous works, each agent distributedly reasons about a learned consensus feature, leading to efficient cooperation on pathfinding and collision avoidance. As a result, our proposed method demonstrates significant improvements over state-of-the-art learning-based MAPF planners, especially in relatively large and complex scenarios, demonstrating its superiority over baselines in various simulations and real-world robot experiments.

Teacher behavior description is crucial for improving teaching effectiveness and understanding classroom dynamics. Traditional methods rely on meticulous manual observation and recording, which is extremely complex and time-consuming when dealing with many teaching videos. Recently proposed video captioning technologies can automatically analyze and describe object behaviors, reducing manual intervention and providing powerful support for improving teaching effectiveness. Existing video captioning methods, however, fall short in describing teachers’ behaviors because they overlook the temporal progression of teachers’ actions, the background changes between frames, and the frequent interactions between teachers and students in real classroom environments. To address these issues, we propose a video captioning method leveraging a spatio-temporal graph interaction network (STGIN) to describe teachers’ behaviors in classroom scenes. Comprising the teacher–student spatial interaction module (TSI), teacher temporal context module (TTC), and description generator, STGIN captures spatial interaction relationships between teacher and students, extracts temporal dynamics features of the teachers’ behaviors, and precisely generates teacher behavior descriptions. To validate the proposed scheme, we collected a teacher behavioral description (TBD) dataset consisting of 2000 videos. Extensive experiments on our TBD dataset and two generic scene datasets confirm the effectiveness and robustness of the proposed STGIN in real classroom environments.

Efficiently and accurately retrieving specific information from healthcare datasets, such as the Vaccine Adverse Event Reporting System (VAERS)1, presents significant challenges. A promising solution to this problem is the Text-to-ESQ approach, which is akin to Text-to-SQL tasks but leverages NoSQL database Elasticsearch, to thoroughly explore VAERS data. Non-relational databases are particularly adept at managing complex and dynamic data formats, thereby enabling the extraction of more valuable insights. However, generating executable NoSQL queries is still challenging due to the limited availability of NoSQL query datasets, which constrains model training. One potential remedy involves the use of large language models (LLMs), which can be applied in few-shot and even zero-shot learning scenarios. Nonetheless, the lack of prior evaluation for this novel task, coupled with the absence of a comprehensive, unbiased assessment of existing LLMs and prompting strategies, impedes the development of a robust architecture. Motivated by these challenges, we introduce a new Instruction-Enhanced Explainable (InstructEx) Chain-of-Thought (CoT) prompting by integrating existing CoT prompts and conducting a comprehensive investigation of LLMs and CoT prompting. The extensive experimental analysis demonstrates the effectiveness of using LLMs for Text-to-ESQ when combined with the InstructExCoT prompting. It also sheds light on the strengths and weaknesses of these methods from multiple perspectives.

Mental health support in colleges is vital in educating students by offering counseling services and organizing supportive events. However, evaluating its effectiveness faces challenges like data collection difficulties and lack of standardized metrics, limiting research scope. Student feedback is crucial for evaluation but often relies on qualitative analysis without systematic investigation using advanced machine learning methods. This paper uses public Student Voice Survey data to analyze student sentiments on mental health support with large language models (LLMs). We created a sentiment analysis dataset, SMILE-College, with human-machine collaboration. The investigation of both traditional machine learning methods and state-of-the-art LLMs showed the best performance of GPT-3.5 and BERT on this new dataset. The analysis highlights challenges in accurately predicting response sentiments and offers practical insights on how LLMs can enhance mental health-related research and improve college mental health services. This data-driven approach will facilitate efficient and informed mental health support evaluation, management, and decision-making.

The study of classroom teachers’ teaching behavior aims to track the development process of teacher behavior, which provides evidence for teachers’ reflection on classroom teaching. Although the recent attempts propose several promising directions for the analysis of teaching behavior, the existing public datasets are still insufficient to meet the need for these potential solutions due to lacking of varied classroom environment, fine-grained teaching scene behavior data. In this paper, we construct a large-scale, diverse, scenario-specific, and multi-task teacher behavior dataset named TBU. On top of it, we systematically investigate representative methods on multiple tasks on TBU, which can serve as a benchmark for the research towards a more comprehensive understanding of teaching video data. The dataset can be available at: https://github.com/cai-KU/TBU.

The multi-agent pathfinding (MAPF) problem seeks collision-free paths for a team of agents from their current positions to their pre-set goals in a known environment, and is an essential problem found at the core of many logistics, transportation, and general robotics applications. Existing learning-based MAPF approaches typically only let each agent make decisions based on a limited field-of-view (FOV) around its position, as a natural means to fix the input dimensions of its policy network. However, this often makes policies shortsighted, since agents lack the ability to perceive and plan for obstacles/agents beyond their FOV. To address this challenge, we propose ALPHA, a new framework combining the use of ground truth proximal (local) information and fuzzy distal (global) information to let agents sequence local decisions based on the full current state of the system, and avoid such myopicity. We further allow agents to make short-term predictions about each others’ paths, as a means to reason about each others’ path intentions, thereby enhancing the level of cooperation among agents at the whole system level. Our neural structure relies on a Graph Transformer architecture to allow agents to selectively combine these different sources of information and reason about their inter-dependencies at different spatial scales. Our simulation experiments demonstrate that ALPHA outperforms both globally-guided MAPF solvers and communication-learning based ones, showcasing its potential towards scalability in realistic deployments.

This paper proposes a multi-hop distributed sensor network localization method based on UWB ranging measurements. Different from the positioning algorithm suitable for known indoor environments, this algorithm is designed for the exploration needs of unknown areas. Based on the barycentric coordinates of the tetrahedron, the expansion of the sensor network is realized through the multi-hop of the UWB sensor. The proposed algorithm can be applied for three-dimensional space. By designing time-varying weight coefficients and combining Taylor expansion, the localization performance is enhanced. Finally, a numerical simulation is given to verify the effectiveness of the proposed algorithm.