This study investigates the developmental interaction between top-down (TD) and bottom-up (BU) visual attention in robotic learning. Our goal is to understand how structured, human-like attentional behavior emerges through the mutual adaptation of TD and BU mechanisms over time. To this end, we propose a novel attention model $A^3 RNN$ that integrates predictive TD signals and saliency-based BU cues through a bi-directional attention architecture. We evaluate our model in robotic manipulation tasks using imitation learning. Experimental results show that attention behaviors evolve throughout training, from saliency-driven exploration to prediction-driven direction. Initially, BU attention highlights visually salient regions, which guide TD processes, while as learning progresses, TD attention stabilizes and begins to reshape what is perceived as salient. This trajectory reflects principles from cognitive science and the free-energy framework, suggesting the importance of self-organizing attention through interaction between perception and internal prediction. Although not explicitly optimized for stability, our model exhibits more coherent and interpretable attention patterns than baselines, supporting the idea that developmental mechanisms contribute to robust attention formation.

In recent years, studies have been actively conducted on combining large language models (LLM) and robotics; however, most have not considered end-to-end feedback in the robot-motion generation phase. The prediction of deep neural networks must contain errors, it is required to update the trained model to correspond to the real environment to generate robot motion adaptively. This study proposes an integration method that connects the robot-motion learning model and LLM using shared latent variables. When generating robot motion, the proposed method updates shared parameters based on prediction errors from both sensorimotor attention points and task language instructions given to the robot. This allows the model to search for latent parameters appropriate for the robot task efficiently. Through simulator experiments on multiple robot tasks, we demonstrated the effectiveness of our proposed method from two perspectives: position generalization and language instruction generalization abilities.

Anchor-bolt insertion is a peg-in-hole task performed in the construction field for holes in concrete. Efforts have been made to automate this task, but the variable lighting and hole surface conditions, as well as the requirements for short setup and task execution time make the automation challenging. In this study, we introduce a vision and proprioceptive data-driven robot control model for this task that is robust to challenging lighting and hole surface conditions. This model consists of a spatial attention point network (SAP) and a deep reinforcement learning (DRL) policy that are trained jointly end-to-end to control the robot. The model is trained in an offline manner, with a sample-efficient framework designed to reduce training time and minimize the reality gap when transferring the model to the physical world. Through evaluations with an industrial robot performing the task in 12 unknown holes, starting from 16 different initial positions, and under three different lighting conditions (two with misleading shadows), we demonstrate that SAP can generate relevant attention points of the image even in challenging lighting conditions. We also show that the proposed model enables task execution with higher success rate and shorter task completion time than various baselines. Due to the proposed model's high effectiveness even in severe lighting, initial positions, and hole conditions, and the offline training framework's high sample-efficiency and short training time, this approach can be easily applied to construction.

Decision-focused learning (DFL) has recently emerged as a powerful approach for predict-then-optimize problems by customizing a predictive model to a downstream optimization task. However, existing end-to-end DFL methods are hindered by three significant bottlenecks: model mismatch error, sample average approximation error, and gradient approximation error. Model mismatch error stems from the misalignment between the model's parameterized predictive distribution and the true probability distribution. Sample average approximation error arises when using finite samples to approximate the expected optimization objective. Gradient approximation error occurs as DFL relies on the KKT condition for exact gradient computation, while most methods approximate the gradient for backpropagation in non-convex objectives. In this paper, we present DF2 -- the first \textit{distribution-free} decision-focused learning method explicitly designed to address these three bottlenecks. Rather than depending on a task-specific forecaster that requires precise model assumptions, our method directly learns the expected optimization function during training. To efficiently learn the function in a data-driven manner, we devise an attention-based model architecture inspired by the distribution-based parameterization of the expected objective. Our method is, to the best of our knowledge, the first to address all three bottlenecks within a single model. We evaluate DF2 on a synthetic problem, a wind power bidding problem, and a non-convex vaccine distribution problem, demonstrating the effectiveness of DF2.

When you look at an image, what parts of an image do you pay attention to first? Would a machine be able to learn this? We provide a machine learning model that can be used to do just that. The latest generation image format (JPEG XL) supports serving the parts that you pay attention to first, which results in an improved user experience: images will appear to load faster. But the model not only works for encoding JPEG XL images, but can be used whenever we need to know where a human would look first.

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the dataset collection cost cannot be ignored. Existing visual attention models tackled the problem by employing a data efficient structure which learns to extract task relevant image areas. However, since the models cannot modify attention targets after training, it is difficult to apply to dynamically changing tasks. This paper proposed a novel Key-Query-Value formulated visual attention model. This model is capable of switching attention targets by externally modifying the Query representations, namely top-down attention. The proposed model is experimented on a simulator and a real-world environment. The model was compared to existing end-to-end robot vision models in the simulator experiments, showing higher performance and data efficiency. In the real-world robot experiments, the model showed high precision along with its scalability and extendibility.

Human pose estimation (HPE) for 3D skeleton reconstruction in telemedicine has long received attention. Although the development of deep learning has made HPE methods in telemedicine simpler and easier to use, addressing low accuracy and high latency remains a big challenge. In this paper, we propose a novel multi-view Attention Cube Regression Network (ACRNet), which regresses the 3D position of joints in real time by aggregating informative attention points on each cube surface. More specially, a cube whose each surface contains uniformly distributed attention points with specific coordinate values is first created to wrap the target from the main view. Then, our network regresses the 3D position of each joint by summing and averaging the coordinates of attention points on each surface after being weighted. To verify our method, we first tested ACRNet on the open-source ITOP dataset; meanwhile, we collected a new multi-view upper body movement dataset (UBM) on the trunk support trainer (TruST) to validate the capability of our model in real rehabilitation scenarios. Experimental results demonstrate the superiority of ACRNet compared with other state-of-the-art methods. We also validate the efficacy of each module in ACRNet. Furthermore, Our work analyzes the performance of ACRNet under the medical monitoring indicator. Because of the high accuracy and running speed, our model is suitable for real-time telemedicine settings. The source code is available at https://github.com/BoceHu/ACRNet