--Recent developments of low cost off-the-shelf programmable components, their modularity, and also rapid prototyping made educational robotics flourish, as it is accessible in most schools today. They allow to illustrate and embody theoretical problems in practical and tangible applications, and gather multidisciplinary skills. They also give a rich natural context for project-oriented pedagogy. However, most current robot kits all are limited to egocentric aspect of the robots perception. This makes it difficult to access more high-level problems involving e.g. In this paper we introduce an educational holonomous robot kit that comes with an external tracking system, which lightens the constraint on embedded systems, but allows in the same time to discover high-level aspects of robotics, otherwise unreachable. Educational robotics is a field promoting the use of robots as tools to engage learners on practical applications, problems, and sometime competitions. This approach can be backed up by constructionist and experimental learning theories. A lot of educational robotics platforms recently emerged and are now used in classrooms.

Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling). Motivated by our findings on the preliminary investigation, we propose a novel tuning strategy, PATCH, to mitigate hallucinations in LVLMs. This plug-and-play method can be integrated into various LVLMs, utilizing adaptive virtual tokens to extract object features from bounding boxes, thereby addressing hallucinations caused by insufficient decoupling of visual features. PATCH achieves state-of-the-art performance on multiple multi-modal hallucination datasets. We hope this approach provides researchers with deeper insights into the underlying causes of hallucinations in LVLMs, fostering further advancements and innovation in this field. Large vision-language models (LVLMs) have demonstrated remarkable performance across a broad range of tasks, even surpassing human capabilities in specific scenarios (Xu et al., 2023; Li et al., 2023a; Zhang et al., 2024a). However, their practical applications are hindered by multi-modal hallucinations, where models generate factually incorrect, inconsistent, or entirely fictitious outputs when interpreting visual features.

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. This paper presents an empirical study on enhancing MLLMs with state-of-the-art (SOTA) object detection and Optical Character Recognition models to improve fine-grained image understanding and reduce hallucination in responses. Our research investigates the embedding-based infusion of detection information, the impact of such infusion on the MLLMs' original abilities, and the interchangeability of detection models. We conduct systematic experiments with models such as LLaVA-1.5, DINO, and PaddleOCRv2, revealing that our approach not only refines MLLMs' performance in specific visual tasks but also maintains their original strengths. The resulting enhanced MLLMs outperform SOTA models on 9 out of 10 benchmarks, achieving an improvement of up to 12.99% on the normalized average score, marking a notable advancement in multimodal understanding. We release our codes to facilitate further exploration into the fine-grained multimodal dialogue capabilities of MLLMs.

This paper investigates the zero-shot object goal visual navigation problem. In the object goal visual navigation task, the agent needs to locate navigation targets from its egocentric visual input. "Zero-shot" means that the target the agent needs to find is not trained during the training phase. To address the issue of coupling navigation ability with target features during training, we propose the Class-Independent Relationship Network (CIRN). This method combines target detection information with the relative semantic similarity between the target and the navigation target, and constructs a brand new state representation based on similarity ranking, this state representation does not include target feature or environment feature, effectively decoupling the agent's navigation ability from target features. And a Graph Convolutional Network (GCN) is employed to learn the relationships between different objects based on their similarities. During testing, our approach demonstrates strong generalization capabilities, including zero-shot navigation tasks with different targets and environments. Through extensive experiments in the AI2-THOR virtual environment, our method outperforms the current state-of-the-art approaches in the zero-shot object goal visual navigation task. Furthermore, we conducted experiments in more challenging cross-target and cross-scene settings, which further validate the robustness and generalization ability of our method. Our code is available at: https://github.com/SmartAndCleverRobot/ICRA-CIRN.

This paper systematically studies the cooperative area coverage and target tracking problem of multiple-unmanned aerial vehicles (multi-UAVs). The problem is solved by decomposing into three sub-problems: information fusion, task assignment, and multi-UAV behavior decision-making. Specifically, in the information fusion process, we use the maximum consistency protocol to update the joint estimation states of multi-targets (JESMT) and the area detection information. The area detection information is represented by the equivalent visiting time map (EVTM), which is built based on the detection probability and the actual visiting time of the area. Then, we model the task assignment problem of multi-UAV searching and tracking multi-targets as a network flow model with upper and lower flow bounds. An algorithm named task assignment minimum-cost maximum-flow (TAMM) is proposed. Cooperative behavior decision-making uses Fisher information as the mission reward to obtain the optimal tracking action of the UAV. Furthermore, a coverage behavior decision-making algorithm based on the anti-flocking method is designed for those UAVs assigned the coverage task. Finally, a distributed multi-UAV cooperative area coverage and target tracking algorithm is designed, which integrates information fusion, task assignment, and behavioral decision-making. Numerical and hardware-in-the-loop simulation results show that the proposed method can achieve persistent area coverage and cooperative target tracking.