Search

This paper introduces TRACE-GPT, which stands for Time-seRies Anomaly-detection with Convolutional Embedding and Generative Pre-trained Transformers. TRACE-GPT is designed to pre-train univariate time-series sensor data and detect faults on unlabeled datasets in semiconductor manufacturing. In semiconductor industry, classifying abnormal time-series sensor data from normal data is important because it is directly related to wafer defect. However, small, unlabeled, and even mixed training data without enough anomalies make classification tasks difficult. In this research, we capture features of time-series data with temporal convolutional embedding and Generative Pre-trained Transformer (GPT) to classify abnormal sequences from normal sequences using cross entropy loss. We prove that our model shows better performance than previous unsupervised models with both an open dataset, the University of California Riverside (UCR) time-series classification archive, and the process log of our Chemical Vapor Deposition (CVD) equipment. Our model has the highest F1 score at Equal Error Rate (EER) across all datasets and is only 0.026 below the supervised state-of-the-art baseline on the open dataset.

Although bipedal locomotion provides the ability to traverse unstructured environments, it requires careful planning and control to safely walk across without falling. This poses an integrated challenge for the robot to perceive, plan, and control its movements, especially with dynamic motions where the robot may have to adapt its swing-leg trajectory onthe-fly in order to safely place its foot on the uneven terrain. In this paper we present an efficient geometric footstep planner and the corresponding walking controller that enables a humanoid robot to dynamically walk across uneven terrain at speeds up to 0.3 m/s. As dynamic locomotion, we refer first to the continuous walking motion without stopping, and second to the on-the-fly replanning of the landing footstep position in middle of the swing phase during the robot gait cycle. This is mainly achieved through the streamlined integration between an efficient sampling-based planner and robust walking controller. The footstep planner is able to generate feasible footsteps within 5 milliseconds, and the controller is able to generate a new corresponding swing leg trajectory as well as the wholebody motion to dynamically balance the robot to the newly updated footsteps. The proposed perception-control pipeline is evaluated and demonstrated with real experiments using a fullscale humanoid to traverse across uneven terrains featured by static stepping stones, dynamically movable stepping stone, or narrow path., Comment: Submitted to Int. Conf. Robotics and Automation (ICRA) 2021

Optoelectronics applications for transition-metal dichalcogenides are still limited by weak light absorption and their complex exciton modes are easily perturbed by varying excitation conditions, because they are inherent in atomically thin layers. Here, we propose a method of selectively amplifying the primary exciton (A0) among the exciton complexes in monolayer MoS2 via cyclic re-excitation of cavity-free exciton-coupled plasmon propagation. This was implemented by partially overlapping a Ag nanowire (NW) on a MoS2 monolayer separated by a thin SiO2 spacer. Exciton-coupled plasmons in the NW enhance the A0 radiation in MoS2. The cumulative amplification of emission enhancement by cyclic plasmon travelling reaches ~20-fold selectively for the A0, while excluding other B exciton and multiexciton by significantly reduced band-filling, without oscillatory spectra implying plasmonic cavity effects., Comment: 4 pages,4 figures