It is important for daily life support robots to detect changes in their environment and perform tasks. In the field of anomaly detection in computer vision, probabilistic and deep learning methods have been used to calculate the image distance. These methods calculate distances by focusing on image pixels. In contrast, this study aims to detect semantic changes in the daily life environment using the current development of large-scale vision-language models. Using its Visual Question Answering (VQA) model, we propose a method to detect semantic changes by applying multiple questions to a reference image and a current image and obtaining answers in the form of sentences. Unlike deep learning-based methods in anomaly detection, this method does not require any training or fine-tuning, is not affected by noise, and is sensitive to semantic state changes in the real world. In our experiments, we demonstrated the effectiveness of this method by applying it to a patrol task in a real-life environment using a mobile robot, Fetch Mobile Manipulator. In the future, it may be possible to add explanatory power to changes in the daily life environment through spoken language.

In the literature on object grasping, the robot often determines the grasp point and posture from visual information. They predict the grasping point uniquely from the object's shape characteristics. However, as a practical matter, there are cases where there are constraints on grasp point due to the object states, the limitation of the robot's hardware and the surrounding environment. In this study, we propose a neural network that can easily constrain the input. It determines the grasp pose from visual information and outputs the grasp success probability. The grasp pose is modified using backpropagation to increase the success rate of the grasp. As for the target object, we deal with some dirty tableware scattered on the table. We have developed a system that autonomously collects supervised data so that the robot can learn by itself whether it has succeeded in a grasp attempt. Finally, the robot can grasp an object which avoids dirty parts and find the suboptimal grasp pose.

Human environments are physically supported by floors, which prevent people and furniture from gravitational pull. Since our body motions continuously generate vibrations and loads that propagate into the ground, measurement of these expressive signals leads to unobtrusive activity sensing. In this study, we present Flexel, a modular floor interface for room-scale tactile sensing. By paving a room with floor interfaces, our system can immediately begin to infer touch locations, track user locations, recognize foot gestures, and detect object locations. Through a series of exploratory studies, we determined the preferable hardware design that adheres to construction conventions, as well as the optimal sensor density that mediates the trade-off between cost and performance. We summarize our findings into design guidelines that are generalizable to other floor interfaces. Finally, we provide example applications for room-scale tactile sensing enabled by our Flexel system.

Eating with others enhances our dining experience, improves socialization, and has some health benefits. Although many people do not want to eat alone, there is an increase in the number of people who eat alone in Japan due to difficulty in matching mealtimes and places with others.In this paper, we develop a mixed reality (MR) system for coeating with a robot. In this system, a robot and a MR headset are connected enabling users to observe a robot putting food image into its mouth, as if eating. We conducted an experiment to evaluate the developed system with users that are at least 13 years old. Experimental results show that the users enjoyed their meal and felt more delicious when the robot ate with them than when the robot only talked without eating. Furthermore, they eat more when a robot eats, suggesting that a robot could influence people's eating behavior.

Recent progress of deep learning improved the capability of a robot to find a proper grasp of a novel object for different grasp modalities (e.g., pinch and suction). While these previous studies consider multiple modalities separately, several studies develop multi-modal grippers that can achieve simultaneous pinch and suction grasp (multi-modal grasp fusion) for more capable and stable object manipulation. However, the previous studies with these grippers restrict the situations: simple object geometry and uncluttered environments. To overcome these difficulties, we propose a system that consists of: 1) object-class-agnostic grasp modality detection; 2) object-class-agnostic instance segmentation; and 3) grasp template matching for different modalities. The key idea of our work is the introduction of instance segmentation to fuse multiple modalities regarding each instance eluding a grasp of multiple objects at once. In the experiments, we evaluated the proposed system on the real-world picking task in clutter. The experimental results show that the effectiveness of modality detection, instance segmentation, and the integrated system as a whole.

Recently, self-supervised approach is common for robot grasping. Although this approach improves success rate, it requires a long time to execute a number of grasp trials, and single-arm grasping is only considered. However, robots can grasp more various objects with two arms, and dual-arm robots such as humanoid robots are expected to execute dual-arm manipulation and overcome the single-arm limitation. In this paper, we introduce dual-arm grasping as another possible strategy and propose a multi-stage learning method for selective dual-arm grasping using Convolutional Neural Networks (CNN)for grasping point prediction and semantic segmentation. In the first stage, the network learns grasping points with the automatic annotation. Although a robot learns both single-arm and dual-arm grasping efficiently with the annotation, the robot may not be able to grasp it because the annotation algorithm is designed by human. Therefore, for the second stage, the robot samples various grasping points with both grasping strategies and learns how to grasp in the real world. In this stage, the robot obtains new possible grasping points and prunes unsuccessful ones for both grasping strategies through the robot experience. In the experiments in the real world, the adapted network achieved high success rate 76.7% in 90 trials. Since the network trained with no adaptation stage resulted in lower success rate 56.7%, this result also shows the network was refined with less than 250 times of grasp sampling. As an application of our method, we demonstrated that our system worked well in warehouse picking task.

We present a robotic system for picking a target from a pile of objects that is capable of finding and grasping the target object by removing obstacles in the appropriate order. The fundamental idea is to segment instances with both visible and occluded masks, which we call `instance occlusion segmentation'. To achieve this, we extend an existing instance segmentation model with a novel `relook' architecture, in which the model explicitly learns the inter-instance relationship. Also, by using image synthesis, we make the system capable of handling new objects without human annotations. The experimental results show the effectiveness of the relook architecture when compared with a conventional model and of the image synthesis when compared to a human-annotated dataset. We also demonstrate the capability of our system to achieve picking a target in a cluttered environment with a real robot.