In recent years, floating debris in the sea has damaged the environment and harmed wildlife. Systems for collecting floating marine debris in the open ocean by installing a huge net or using a vacuum device have been proposed. However, to the best of our knowledge, there is no system for collecting marine debris in complex topographies, such as ports wherein marine debris tends to accumulate, and large vessels cannot enter. This study proposes a system to locate and collect floating marine debris by jointly using an unmanned aerial vehicle (UAV) and an unmanned underwater vehicle (UUV). The UAV discovers marine debris that cannot be observed by the UUV owing to its limited view, and the UUV is used for collection. However, for application of such a system, problems related to target detection, UUV navigation, and target collection must be solved. In the proposed system, the following components are developed: a graphical user interface to select the collection target, controller for the UUV to navigate to the target, and a collecting motion generator. We tested and evaluated the proposed cooperative system using a dynamic simulator and physical robots. As a result, we confirm that our system can achieve efficient debris collection in complex topographies, is easy to use, will reduced workload, and can be applied practically.
In recent years, floating debris on the sea damages the environment and wildlife. The current solution to this problem is manually collecting by ships or divers, but this is inefficient and time-consuming. For an efficient collection of marine debris, we propose a semi-autonomous collection system by collaborating an unmanned aerial vehicle (UAV) and an unmanned underwater vehicle (UUV). Since the field of view of a UUV is very limited, a UAV widely surveys the debris from birds-eye-view. The view from the UAV is provided to the user and the user designates the target debris on the view. By converting the position on the view to it in UUV coordinates, the UUV collects debris automatically. We tested the proposed system using a dynamics simulator and real robots to evaluate the effectiveness of the collaborativesystem. Videos are available at https://naoki-sh.github.io/uuv_project/home.
With the rapid technological advancements in wearable devices, motion and health management have significantly improved, enabling the measurement of various biometric data with compact equipment. Our research focuses on motion measurement but, in general, full-body motion estimation requires motion capture systems or multiple inertial sensors, making it necessary to directly measure movement itself. In this study, we propose estimating full-body posture using inverse kinematics based on trunk posture and limb-end information collected through wearable devices. To enhance estimation accuracy in this underdetermined problem, we employ Physics-Informed Neural Networks (PINNs), which efficiently learn using physical laws as a loss function, along with a high-precision inverse kinematics model of a digital human. Through this approach, we enable high-accuracy full-body posture estimation even with wearable devices in underdetermined scenarios.
Training deep-learning-based vision systems requires the manual annotation of a significant number of images. Such manual annotation is highly time-consuming and labor-intensive. Although previous studies attempted to eliminate the effort required for annotation, the effort required for image collection was retained. To address this issue, we propose a human-in-the-loop dataset-collection method using a web application. To counterbalance workload and performance by encouraging the collection of multi-view object image datasets enjoyably, thereby amplifying motivation, we propose three types of online visual feedback features to track the progress of the collection status. Our experiments thoroughly investigated the influence of each feature on the collection performance and quality of operation. These results indicate the feasibility of annotation and object detection.
This paper proposes a feedback framework that adjusts human workload and productivity by instructing work tempo and personalizes work according to individual differences. For feedback of optimal work tempo, this study proposes a human worker state transition model to investigate the effects of work tempo instructions on workload and productivity. Based on the results obtained, we proposed a feedback policy using our proposed worker state transition model. By testing our proposed framework in a picking task, we showed the possibility to balance productivity and workload.