Search

The process of industrial box-packing, which involves the accurate placement of multiple objects, requires high-accuracy positioning and sequential actions. When a robot is tasked with placing an object at a specific location with high accuracy, it is important not only to have information about the location of the object to be placed, but also the posture of the object grasped by the robotic hand. Often, industrial box-packing requires the sequential placement of identically shaped objects into a single box. The robot's action should be determined by the same learned model. In factories, new kinds of products often appear and there is a need for a model that can easily adapt to them. Therefore, it should be easy to collect data to train the model. In this study, we designed a robotic system to automate real-world industrial tasks, employing a vision-based learning control model. We propose in-hand-view-sensitive Newtonian variational autoencoder (ihVS-NVAE), which employs an RGB camera to obtain in-hand postures of objects. We demonstrate that our model, trained for a single object-placement task, can handle sequential tasks without additional training. To evaluate efficacy of the proposed model, we employed a real robot to perform sequential industrial box-packing of multiple objects. Results showed that the proposed model achieved a 100% success rate in industrial box-packing tasks, thereby outperforming the state-of-the-art and conventional approaches, underscoring its superior effectiveness and potential in industrial tasks., Comment: 7 pages, 8 figures

Rather than traditional position control, impedance control is preferred to ensure the safe operation of industrial robots programmed from demonstrations. However, variable stiffness learning studies have focused on task performance rather than safety (or compliance). Thus, this paper proposes a novel stiffness learning method to satisfy both task performance and compliance requirements. The proposed method optimizes the task and compliance objectives (T/C objectives) simultaneously via multi-objective Bayesian optimization. We define the stiffness search space by segmenting a demonstration into task phases, each with constant responsible stiffness. The segmentation is performed by identifying impedance control-aware switching linear dynamics (IC-SLD) from the demonstration. We also utilize the stiffness obtained by proposed IC-SLD as priors for efficient optimization. Experiments on simulated tasks and a real robot demonstrate that IC-SLD-based segmentation and the use of priors improve the optimization efficiency compared to existing baseline methods., Comment: Accepted to IROS2023

In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method assumes a single-view observation space, and this imposes limitations on the observed data, such as lack of spatial information and occlusions. This makes obtaining ideal observational information from the environment difficult and is a bottleneck for real-world robotics applications. In this paper, we use contrastive learning to train a shared latent space between different viewpoints, and show how the Products of Experts approach can be used to integrate and control the probability distributions of latent states for multiple viewpoints. We also propose Multi-View DreamingV2, a variant of Multi-View Dreaming that uses a categorical distribution to model the latent state instead of the Gaussian distribution. Experiments show that the proposed method outperforms simple extensions of existing methods in a realistic robot control task., Comment: 7 pages, 8 figures

An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug. Thus, highly accurate estimation of the relative pose between a plug and socket is fundamental for achieving the task. World models are promising technologies for visuomotor control because they obtain appropriate state representation to jointly optimize feature extraction and latent dynamics model. Recent studies show that the NewtonianVAE, a type of the world model, acquires latent space equivalent to mapping from images to physical coordinates. Proportional control can be achieved in the latent space of NewtonianVAE. However, applying NewtonianVAE to high-accuracy industrial tasks in physical environments is an open problem. Moreover, the existing framework does not consider the grasp pose compensation in the obtained latent space. In this work, we proposed tactile-sensitive NewtonianVAE and applied it to a USB connector insertion with grasp pose variation in the physical environments. We adopted a GelSight-type tactile sensor and estimated the insertion position compensated by the grasp pose of the plug. Our method trains the latent space in an end-to-end manner, and no additional engineering and annotation are required. Simple proportional control is available in the obtained latent space. Moreover, we showed that the original NewtonianVAE fails in some situations, and demonstrated that domain knowledge induction improves model accuracy. This domain knowledge can be easily obtained using robot specification and grasp pose error measurement. We demonstrated that our proposed method achieved a 100\% success rate and 0.3 mm positioning accuracy in the USB connector insertion task in the physical environment. It outperformed SOTA CNN-based two-stage goal pose regression with grasp pose compensation using coordinate transformation., Comment: 7 pages, 4 figures

In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos. We build upon prior work in video prediction via an autoregressive transformer over the discrete latent space of compressed videos, with an added modification to model object-centric information via bounding boxes. Due to better compressibility of object-centric representations, we can improve training efficiency by allowing the model to only access object information for longer horizon temporal information. When evaluated on various difficult object-centric datasets, our method achieves better or equal performance to other video generation models, while remaining computationally more efficient and scalable. In addition, we show that our method is able to perform object-centric controllability through bounding box manipulation, which may aid downstream tasks such as video editing, or visual planning. Samples are available at https://sites.google.com/view/povt-public, Comment: Project Website: https://sites.google.com/view/povt-public

State representation learning (SRL) in partially observable Markov decision processes has been studied to learn abstract features of data useful for robot control tasks. For SRL, acquiring domain-agnostic states is essential for achieving efficient imitation learning. Without these states, imitation learning is hampered by domain-dependent information useless for control. However, existing methods fail to remove such disturbances from the states when the data from experts and agents show large domain shifts. To overcome this issue, we propose a domain-adversarial and conditional state space model (DAC-SSM) that enables control systems to obtain domain-agnostic and task- and dynamics-aware states. DAC-SSM jointly optimizes the state inference, observation reconstruction, forward dynamics, and reward models. To remove domain-dependent information from the states, the model is trained with domain discriminators in an adversarial manner, and the reconstruction is conditioned on domain labels. We experimentally evaluated the model predictive control performance via imitation learning for continuous control of sparse reward tasks in simulators and compared it with the performance of the existing SRL method. The agents from DAC-SSM achieved performance comparable to experts and more than twice the baselines. We conclude domain-agnostic states are essential for imitation learning that has large domain shifts and can be obtained using DAC-SSM., Comment: Published at IROS 2020

Emergence of antimicrobial resistance in Neisseria gonorrhoeae is a major public health concern globally, and new antimicrobials for treatment of gonorrhea are imperative. In this study, the in vitro activity of sitafloxacin, a fluoroquinolone mainly used for respiratory tract or urogenital infections in Japan, and additional newer generation fluoroquinolones were determined against ciprofloxacin-resistant N. gonorrhoeae isolates. Minimum inhibitory concentrations (MICs) of ciprofloxacin, levofloxacin, moxifloxacin, sitafloxacin, pazufloxacin, and tosufloxacin against 47 N. gonorrhoeae isolates cultured in 2009 in Japan were determined by agar dilution method. The quinolone resistance-determining region (QRDR) of gyrA and parC was sequenced. The in vitro potency of sitafloxacin was substantially higher compared with all other tested fluoroquinolones. The MICs of sitafloxacin ranged from 0.03 to 0.5 mg/L for 35 ciprofloxacin-resistant N. gonorrhoeae isolates (ciprofloxacin MICs from 2 to 32 mg/L). No identified mutations in GyrA and ParC QRDR resulted in higher sitafloxacin MIC than 0.5 mg/L. Sitafloxacin had a high activity against N. gonorrhoeae isolates, including strains with mutations in DNA gyrase and topoisomerase IV, resulting in high-level resistance to ciprofloxacin and all other newer generation fluoroquinolones examined. However, it was still to a lower extent affected by GyrA and ParC QRDR mutations resulting in sitafloxacin MICs of up to 0.5 mg/L. This indicates that sitafloxacin should not be considered for empirical first-line monotherapy of gonorrhea. However, sitafloxacin could be valuable in a dual antimicrobial therapy and for cases with ceftriaxone resistance or allergy., Funding Agency:Japan Society for the Promotion of Science (JSPS) KAKENHI Grant 25293337 Research Program on Emerging and Re-emerging Infectious Diseases from Japan Agency for Medical Research and development, AMED 15fk0108014h0001

[Objective] Lifestyle changes may play an important role in the incidence reduction and delay of onset age of amyotrophic lateral sclerosis (ALS) in the Koza/Kozagawa/Kushimoto (K) area. The aim of this study was to evaluate recent lifestyle changes in the K area and to investigate the relationships between lifestyle and oxidative stress among the residents. [Methods] We conducted a medical checkup for elderly residents in the K area and the control area and evaluated the urinary 8-OHdG levels, cognitive function test scores and metal contents in serum and scalp hair, coupled with a lifestyle questionnaire survey between 2010 and 2015. [Results] Recent lifestyle changes among the K residents, including a decrease in the Japanese pickle consumption, increase in fresh vegetable consumption and decrease in farm work, were evaluated in this study. Low consumption of Japanese pickles, high consumption of fresh vegetables, rare farm work and low levels of 8-OHdG/creatinine were all associated with high scores in the cognitive function tests. Frequent farm work and consumption of Japanese pickles was associated with high contents of transition metals, such as Mn, Al and V, in the scalp hair. [Conclusion] These lifestyle changes among residents in the K area may be associated with their oxidative stress.

東京電力福島第一原子力発電所事故後における広域の詳細な空間線量率マップを作成するために、原子力機構は走行サーベイシステムKURAMA-IIを用いた測定を文部科学省の委託を受けて実施した。KURAMAは、一般乗用車に多数搭載して広範囲の空間線量率を詳細かつ短期間に把握することを目的として京都大学原子炉実験所で開発されたシステムである。KURAMAは、エネルギー補償型gamma線検出器で測定した線量率をGPSの測位データでタグ付けしながら記録する測定器、データを受け取り可視化のための処理や解析を行うサーバ、エンドユーザがデータを閲覧するためのクライアントから構成される。第2世代のKURAMA-IIでは更なる小型化、堅牢性の向上、データ送信の完全自動化等の機能が強化されたことによって、100台の同時測定が可能となり、広域の詳細な線量率マッピングをより短期間で実施することが可能になった。本報告では、KURAMA-IIによる測定データの信頼性を確保するために実施した基盤整備と、KURAMA-IIを空間線量率マッピング事業に適用した結果について述べるとともに、多数のKURAMA-IIを使用した走行サーベイの精度を保証するための効率的なKURAMA-IIの管理方法を提案した。, JAEA has been performing dose rate mapping in air using a car-borne survey system KURAMA-II. The KURAMA system is a GPS-aided mobile radiation monitoring system that has been newly developed by Kyoto University Research Reactor Institute in response to the nuclear disaster. The KURAMA system is composed of an energy-compensated scintillation survey meter for measuring dose rate, electric device for controlling both the dose rates and the position data from a GPS module, a computer server for processing and analyzing data from KURAMA, and client PCs for providing for end users. The KURAMA-II has been improved in small-packaging, durability, and automated data transmission. In consequence, dose rate mapping in wide area has become possible in shorter period of time. This report describes the construction of KURAMA-II, its application and a suggestion of how to manage a large number of KURAMA-II., 著者所属: 日本原子力研究開発機構(JAEA), JAEA-Technology 2013-037