In-hand manipulation is a fundamental ability for multi-fingered robotic hands that interact with their environments. Owing to the high dimensionality of robotic hands and intermittent contact dynamics, effectively programming a robotic hand for in-hand manipulations is still a challenging problem. To address this challenge, this work employs deep reinforcement learning (DRL) algorithm to learn in-hand manipulations for multi-fingered robotic hands. A reward-shaping method is proposed to assist the learning of in-hand manipulation. The synergy of robotic hand postures is analysed to build a low-dimensional hand posture space. Two additional rewards are designed based on both the analysis of hand synergies and its learning history. The two additional rewards cooperating with an extrinsic reward are used to assist the in-hand manipulation learning. Three value functions are trained jointly with respect to their reward functions. Then they cooperate to optimise a control policy for in-hand manipulation. The reward shaping not only improves the exploration efficiency of the DRL algorithm but also provides a way to incorporate domain knowledge. The performance of the proposed learning method is evaluated with object rotation tasks. Experimental results demonstrated that the proposed learning method enables multi-fingered robotic hands to learn in-hand manipulation effectively.

The main purpose of this study is to bring in a new extension of multi-objective optimisation on the basis of ratio analysis plus full multiplicative form (MULTIMOORA) in trapezoidal neutrosophic number (TrNN) environment. MULTIMOORA strategy provides high efficiency and effectiveness in problem-solving. The new MULTIMOORA strategy consists of three components. The components are ratio system approach, reference point approach, and full multiplicative form. To develop the proposed strategy, the authors find out three ranking order of alternatives using the three components. The final ranking order of the alternatives is based on dominance property. The study is original as it first develops the MULTIMOORA strategy in the TrNN environment, which they call TrNN- MULTIMOORA. They solve a realistic banking problem involving multi-attribute group decision making in the TrNN environment to reflect the applicability and proficiency of the developed strategy. They also present a comparison between the proposed strategy and the existing tomada de decisao interativa e multicritévio and VlseKriterijumska Optimizcija I Kaompromisno Resenje strategies.

Group decision making typically requires eliciting and coordinating the preferences of group members. In this study, the authors develop an overall framework of group consensus in context of hesitant fuzzy linguistic preference relations (HFLPRs). A new notion of distance measure between two HFLPRs is defined, based on which a consensual framework consists of two mechanisms, the automatic consensus reaching and the interactive consensus reaching is presented. Accordingly, they, respectively, design two algorithms to implement these mechanisms. Finally, a group decision problem of green supplier selection is provided to exemplify and verify both of the proposed methods, and a comparative analysis with some related approaches is performed.

Compared with conventional image sensors, event cameras have been attracting attention thanks to their potential in environments under fast motion and high dynamic range (HDR). To tackle the lost-track issue due to fast illumination changes under HDR scene such as tunnels, an object tracking framework has been presented based on event count images from an event camera. The framework contains an offline-trained detector and an online-trained tracker which complement each other: The detector benefits from pre-labelled data during training, but may have false or missing detections; the tracker provides persistent results for each initialised object but may suffer from drifting issues or even failures. Besides, process and measurement equations have been modelled, and a Kalman fusion scheme has been proposed to incorporate measurements from the detector and the tracker. Self-initialisation and track maintenance in the fusion scheme ensure autonomous real-time tracking without user intervene. With self-collected event data in urban driving scenarios, experiments have been conducted to show the performance of the proposed framework and the fusion scheme.

In recent years, hyper-complex deep networks (such as complex-valued and quaternion-valued neural networks – QVNNs) have received a renewed interest in the literature. They find applications in multiple fields, ranging from image reconstruction to 3D audio processing. Similar to their real-valued counterparts, quaternion neural networks require custom regularisation strategies to avoid overfitting. In addition, for many real-world applications and embedded implementations, there is the need of designing sufficiently compact networks, with few weights and neurons. However, the problem of regularising and/or sparsifying QVNNs has not been properly addressed in the literature as of now. In this study, the authors show how to address both problems by designing targeted regularisation strategies, which can minimise the number of connections and neurons of the network during training. To this end, they investigate two extensions of and structured regularisations to the quaternion domain. In the authors’ experimental evaluation, they show that these tailored strategies significantly outperform classical (real-valued) regularisation approaches, resulting in small networks especially suitable for low-power and real-time applications.