Semantic Representation of Robot Manipulation with Knowledge Graph.

Autonomous indoor service robots are affected by multiple factors when they are directly involved in manipulation tasks in daily life, such as scenes, objects, and actions. It is of self-evident importance to properly parse these factors and interpret intentions according to human cognition and semantics. In this study, the design of a semantic representation framework based on a knowledge graph is presented, including (1) a multi-layer knowledge-representation model, (2) a multi-module knowledge-representation system, and (3) a method to extract manipulation knowledge from multiple sources of information. Moreover, with the aim of generating semantic representations of entities and relations in the knowledge base, a knowledge-graph-embedding method based on graph convolutional neural networks is proposed in order to provide high-precision predictions of factors in manipulation tasks. Through the prediction of action sequences via this embedding method, robots in real-world environments can be effectively guided by the knowledge framework to complete task planning and object-oriented transfer.

Reinforcement Learning-Based Reactive Obstacle Avoidance Method for Redundant Manipulators.

Redundant manipulators are widely used in fields such as human-robot collaboration due to their good flexibility. To ensure efficiency and safety, the manipulator is required to avoid obstacles while tracking a desired trajectory in many tasks. Conventional methods for obstacle avoidance of redundant manipulators may encounter joint singularity or exceed joint position limits while tracking the desired trajectory. By integrating deep reinforcement learning into the gradient projection method, a reactive obstacle avoidance method for redundant manipulators is proposed. We establish a general DRL framework for obstacle avoidance, and then a reinforcement learning agent is applied to learn motion in the null space of the redundant manipulator Jacobian matrix. The reward function of reinforcement learning is redesigned to handle multiple constraints automatically. Specifically, the manipulability index is introduced into the reward function, and thus the manipulator can maintain high manipulability to avoid joint singularity while executing tasks. To show the effectiveness of the proposed method, the simulation of 4 degrees of planar manipulator freedom is given. Compared with the gradient projection method, the proposed method outperforms in a success rate of obstacles avoidance, average manipulability, and time efficiency.

High-Performance Anodic Vulcanization-Pretreated Gated P+-π-M-N+ InAs/GaSb Superlattice Long-Wavelength Infrared Detector.

The InAs/GaSb superlattice infrared detector has been developed with tremendous effort. However, the performance of it, especially long-wavelength infrared detectors (LWIR), is still limited by the electrical performance and optical quantum efficiency (QE). Forcing the active region to be p-type through proper doping can highly improve QE, and the gating technique can be employed to greatly enhance electrical performance. However, the saturation bias voltage is too high. Reducing the saturation bias voltage has broad prospects for the future application of gate voltage control devices. In this paper, we report that the gated P+-π-M-N+ InAs/GaSb superlattice long-wavelength infrared detectors exhibit different π region doping levels that have a reduced minimum saturation bias at - 10 V with a 200-nm SiO2 layer after a simple and effective anodic vulcanization pretreatment. The saturation gate bias voltage is much lower than - 40 V that reported with the same thickness of a 200-nm SiO2 passivation layer and similar structure. The optical and electrical characterization indicates that the electrical and optical performance of the device would be weakened by excessive doping concentration. At 77 K, the 50% cutoff wavelength of the device is about 8 µm, the 100% cutoff wavelength is 10 µm, the maximum quantum efficiency is 62.4%, the maximum of responsivity is 2.26 A/W at 5 µm, and the maximum RA of the device is 1259.4 Ω cm2. Besides, the specific detectivity of Be 780 °C-doped detector without gate electrode exhibits a peak of 5.6 × 1010 cm Hz1/2/W at 5 µm with a 70-mv reverse bias voltage, which is more than three times that of Be 820 °C-doped detector. Moreover, the peak specific detectivity could be further increased to 1.3 × 1011 cm Hz1/2/W at 5 µm with a 10-mv reserve bias voltage that has the bias of - 10 V at the gate electrode.

Emotion Recognition Based on Weighted Fusion Strategy of Multichannel Physiological Signals.

Emotion recognition is an important pattern recognition problem that has inspired researchers for several areas. Various data from humans for emotion recognition have been developed, including visual, audio, and physiological signals data. This paper proposes a decision-level weight fusion strategy for emotion recognition in multichannel physiological signals. Firstly, we selected four kinds of physiological signals, including Electroencephalography (EEG), Electrocardiogram (ECG), Respiration Amplitude (RA), and Galvanic Skin Response (GSR). And various analysis domains have been used in physiological emotion features extraction. Secondly, we adopt feedback strategy for weight definition, according to recognition rate of each emotion of each physiological signal based on Support Vector Machine (SVM) classifier independently. Finally, we introduce weight in decision level by linear fusing weight matrix with classification result of each SVM classifier. The experiments on the MAHNOB-HCI database show the highest accuracy. The results also provide evidence and suggest a way for further developing a more specialized emotion recognition system based on multichannel data using weight fusion strategy.

Weighted Feature Gaussian Kernel SVM for Emotion Recognition.

Emotion recognition with weighted feature based on facial expression is a challenging research topic and has attracted great attention in the past few years. This paper presents a novel method, utilizing subregion recognition rate to weight kernel function. First, we divide the facial expression image into some uniform subregions and calculate corresponding recognition rate and weight. Then, we get a weighted feature Gaussian kernel function and construct a classifier based on Support Vector Machine (SVM). At last, the experimental results suggest that the approach based on weighted feature Gaussian kernel function has good performance on the correct rate in emotion recognition. The experiments on the extended Cohn-Kanade (CK+) dataset show that our method has achieved encouraging recognition results compared to the state-of-the-art methods.