Artificial neural network dexterous robotics hand optimal control methodology: grasping and manipulation forces optimization

Optimal fingertip forces can always be computed through the well-known optimization algorithms. However, computation time has always remained a real-time constraint. This article presents an efficient scheme to compute optimal grasping and manipulation forces for dexterous robotics hands. This is expressed as a quadratic optimization problem, and an artificial neural network (ANN) is used to learn such quadratic optimization formulations. Computation has been based on a nonlinear model of fingertip contacts and slips. In achieving object grasping while in motion, the hand Jacobian is considered an important matrix to be computed, but it is also highly intensive for real-time computed applications. Consequently, we investigated an efficient approach using artificial neural networks to learn optimal grasping forces. An ANN is used here to learn the optimal contact forces relating hand joint-space torques to the resulting object force. The results have indicated that the ANN has reduced computation times to reasonable values owing to its ability to map nonlinear force relations. Furthermore, the results have revealed that ANNs are capable of learning highly nonlinear relations relating to distributed fingertip forces and joint torques. The technique developed has also proved to be suitable for off-line learning of computed fingertip forces, even with large training samples.     

Neural networks in robotics: A survey

The purpose of this paper is to provide an overview of the research being done in neural network approaches to robotics, outline the strengths and weaknesses of current approaches, and predict future trends in this area.This work was supported, in part, by Sandia National Laboratories under contract No. 06-1977, Albuquerque, New Mexico.     

A new design methodology of electrostrictive actuators for bio-inspired robotics

At present advanced robotics concepts require new and more suitable components to be exploited, especially in the fields of the biomimetic and soft robotics. In this sense, the actuation system represents one of the most limiting factors for the realization of robots with bio-inspired features and performances.This paper presents a new soft actuators based on electroactive polymers (EAPs) technology. The actuator is composed of a pre-stretched silicone film sputtered with a very thin gold film on both sides, working as electrodes. A particular folded geometry, implemented through an innovative fabrication process, allows to exploit the electrostrictive effect and to develop soft actuators suitable in many applications where softness and flexibility are necessary. The manufactured prototypes were developed on the basis of a parametric model that takes into account all geometric parameters and material characteristics. The proposed model is useful to estimate the performances of the actuator and to improve them.     

A survey on bio-inspired networking

The developments in the communication and networking technologies have yielded many existing and envisioned information network architectures such as cognitive radio networks, sensor and actor networks, quantum communication networks, terrestrial next generation Internet, and InterPlaNetary Internet. However, there exist many common significant challenges to be addressed for the practical realization of these current and envisioned networking paradigms such as the increased complexity with large scale networks, their dynamic nature, resource constraints, heterogeneous architectures, absence or impracticality of centralized control and infrastructure, need for survivability, and unattended resolution of potential failures. These challenges have been successfully dealt with by Nature, which, as a result of millions of years of evolution, have yielded many biological systems and processes with intrinsic appealing characteristics such as adaptivity to varying environmental conditions, inherent resiliency to failures and damages, successful and collaborative operation on the basis of a limited set of rules and with global intelligence which is larger than superposition of individuals, self-organization, survivability, and evolvability. Inspired by these characteristics, many researchers are currently engaged in developing innovative design paradigms to address the networking challenges of existing and envisioned information systems. In this paper, the current state-of-the-art in bio-inspired networking is captured. The existing bio-inspired networking and communication protocols and algorithms devised by looking at biology as a source of inspiration, and by mimicking the laws and dynamics governing these systems are presented along with open research issues for the bio-inspired networking. Furthermore, the domain of bio-inspired networking is linked to the emerging research domain of nanonetworks, which bring a set of unique challenges. The objective of this survey is to provide better understanding of the potentials for bio-inspired networking which is currently far from being fully recognized, and to motivate the research community to further explore this timely and exciting topic.     

Testbeds for ubiquitous robotics: A survey

The growing interest in ubiquitous robotics has originated in the last years the development of a high variety of testbeds. This paper presents a survey on existing ubiquitous robotics testbeds comprising networked mobile robots and networks of distributed sensors, cameras and smartphones, among others. The survey provides an insight into the testbed design, internal behavior and use, identifying trends and existing gaps and proposing guidelines for testbed developers. The level of interoperability among different ubiquitous robotics technologies is used as the main conducting criterion of the survey. Other features analyzed include testbed architectures, target experiments and usability tools.     

A saliency-driven robotic head with bio-inspired saccadic behaviors for social robotics

This paper presents a robotic head for social robots to attend to scene saliency with bio-inspired saccadic behaviors. Scene saliency is determined by measuring low-level static scene information, motion, and object prior knowledge. Towards the extracted saliency spots, the designed robotic head is able to turn gazes in a saccadic manner while obeying eye–head coordination laws with the proposed control scheme. The results of the simulation study and actual applications show the effectiveness of the proposed method in discovering of scene saliency and human-like head motion. The proposed techniques could possibly be applied to social robots to improve social sense and user experience in human–robot interaction.     

发育机器人研究综述

发育机器人是国际上近年兴起的一个研究热点，但在国内相关研究工作尚未全面起步．较为全面地介绍了发育机器人的基本概念、核心思想和发展历程，重点剖析了几种典型的发育模型和学习方法，针对该领域目前存在的学术争论，如组成结构，研究目的和性能评价等，做了详细的探讨．本文最后从理论研究和应用两方面展望了发育机器人的发展趋势，并指出了需要进一步研究解决的问题。     

Recent advances in evolutionary and bio-inspired adaptive robotics: Exploiting embodied dynamics

Applied Intelligence - This paper explores current developments in evolutionary and bio-inspired approaches to autonomous robotics, concentrating on research from our group at the University of...     

Development of multi-fingered dexterous hand for grasping manipulation

In this paper, a developed multi-fingered dexterous hand with flexible tactile skin is described. The dexterous hand has 5-fingers with 6-DOFs and each finger is equipped with a small harmonic drive gear and a fine high-power mini actuator. To achieve the goal of grasping with high accuracy, each fingertip is covered with the tactile array sensors for determination of the force between the finger and the grasped object. Some preliminary experiments are conducted to illustrate the performance of the grasping of the developed dexterous hand.     

DexHand: dexterous hand manipulation motion synthesis for virtual reality

Virtual Reality - Natural object manipulation is one of the important human skills. However, generating natural hand manipulation motions that are adaptive to object shapes and the tasks at hand in...     

Fitness functions in evolutionary robotics: A survey and analysis

This paper surveys fitness functions used in the field of evolutionary robotics (ER). Evolutionary robotics is a field of research that applies artificial evolution to generate control systems for autonomous robots. During evolution, robots attempt to perform a given task in a given environment. The controllers in the better performing robots are selected, altered and propagated to perform the task again in an iterative process that mimics some aspects of natural evolution. A key component of this process–one might argue, the key component–is the measurement of fitness in the evolving controllers. ER is one of a host of machine learning methods that rely on interaction with, and feedback from, a complex dynamic environment to drive synthesis of controllers for autonomous agents. These methods have the potential to lead to the development of robots that can adapt to uncharacterized environments and which may be able to perform tasks that human designers do not completely understand. In order to achieve this, issues regarding fitness evaluation must be addressed. In this paper we survey current ER research and focus on work that involved real robots. The surveyed research is organized according to the degree of a priori knowledge used to formulate the various fitness functions employed during evolution. The underlying motivation for this is to identify methods that allow the development of the greatest degree of novel control, while requiring the minimum amount of a priori task knowledge from the designer.     

Symbol emergence in robotics: a survey

Humans can learn a language through physical interaction with their environment and semiotic communication with other people. It is very important to obtain a computational understanding of how humans can form symbol systems and obtain semiotic skills through their autonomous mental development. Recently, many studies have been conducted regarding the construction of robotic systems and machine learning methods that can learn a language through embodied multimodal interaction with their environment and other systems. Understanding human?-social interactions and developing a robot that can smoothly communicate with human users in the long term require an understanding of the dynamics of symbol systems. The embodied cognition and social interaction of participants gradually alter a symbol system in a constructive manner. In this paper, we introduce a field of research called symbol emergence in robotics (SER). SER represents a constructive approach towards a symbol emergence system. The symbol emergence system is socially self-organized through both semiotic communications and physical interactions with autonomous cognitive developmental agents, i.e. humans and developmental robots. In this paper, specifically, we describe some state-of-art research topics concerning SER, such as multimodal categorization, word discovery, and double articulation analysis. They enable robots to discover words and their embodied meanings from raw sensory-motor information, including visual information, haptic information, auditory information, and acoustic speech signals, in a totally unsupervised manner. Finally, we suggest future directions for research in SER.     

Computational complexity of manipulation: A survey

In situations when a group of people has to make a decision based on the set of individual preferences, they use a certain aggregation method, in particular, voting. One of the main problems for any non-dictatorial social choice rule is the possibility for the voters to achieve a more preferable outcome of the voting by misrepresenting their preferences. Such actions on behalf of the voters are called manipulation, or strategic voting. One approach used to compare social choice rules in terms of how hard they are to manipulate is to find the complexity classes of manipulation problems for a given aggregation method. In this work, we present a survey of the studies of complexity classes of manipulation problems under various model assumptions and constraints.     

A survey on coverage path planning for robotics

Coverage Path Planning (CPP) is the task of determining a path that passes over all points of an area or volume of interest while avoiding obstacles. This task is integral to many robotic applications, such as vacuum cleaning robots, painter robots, autonomous underwater vehicles creating image mosaics, demining robots, lawn mowers, automated harvesters, window cleaners and inspection of complex structures, just to name a few. A considerable body of research has addressed the CPP problem. However, no updated surveys on CPP reflecting recent advances in the field have been presented in the past ten years. In this paper, we present a review of the most successful CPP methods, focusing on the achievements made in the past decade. Furthermore, we discuss reported field applications of the described CPP methods. This work aims to become a starting point for researchers who are initiating their endeavors in CPP. Likewise, this work aims to present a comprehensive review of the recent breakthroughs in the field, providing links to the most interesting and successful works.     

Cognitive neuroscience and robotics: Advancements and future research directions

In recent years, brain-based technologies that capitalise on human abilities to facilitate human–system/robot interactions have been actively explored, especially in brain robotics. Brain–computer interfaces, as applications of this conception, have set a path to convert neural activities recorded by sensors from the human scalp via electroencephalography into valid commands for robot control and task execution. Thanks to the advancement of sensor technologies, non-invasive and invasive sensor headsets have been designed and developed to achieve stable recording of brainwave signals. However, robust and accurate extraction and interpretation of brain signals in brain robotics are critical to reliable task-oriented and opportunistic applications such as brainwave-controlled robotic interactions. In response to this need, pervasive technologies and advanced analytical approaches to translating and merging critical brain functions, behaviours, tasks, and environmental information have been a focus in brain-controlled robotic applications. These methods are composed of signal processing, feature extraction, representation of neural activities, command conversion and robot control. Artificial intelligence algorithms, especially deep learning, are used for the classification, recognition, and identification of patterns and intent underlying brainwaves as a form of electroencephalography. Within the context, this paper provides a comprehensive review of the past and the current status at the intersection of robotics, neuroscience, and artificial intelligence and highlights future research directions.     

A real-time strategy for dexterous manipulation: Fingertips motion planning,force sensing and grasp stability

This paper presents a global strategy for object manipulation with the fingertips with an anthropomorphic dexterous hand: the LMS Hand of the ROBIOSS team from PPRIME Institute in Poitiers (France). Fine manipulation with the fingertips requires to compute on one hand, finger motions able to produce the desired object motion and on the other hand, it is necessary to ensure object stability with a real time scheme for the fingertip force computation. In the literature, lot of works propose to solve the stability problem, but most of these works are grasp oriented; it means that the use of the proposed methods are not easy to implement for online computation while the grasped object is moving inside the hand. Also simple real time schemes and experimental results with full-actuated mechanical hands using three fingers were not proposed or are extremely rare. Thus we wish to propose in a same strategy, a robust and simple way to solve the fingertip path planning and the fingertip force computation. First, finger path planning is based on a geometric approach, and on a contact modelling between the grasped object and the finger. And as force sensing is required for force control, a new original approach based on neural networks and on the use of tendon-driven joints is also used to evaluate the normal force acting on the finger distal phalanx. And an efficient algorithm that computes fingertip forces involved is presented in the case of three dimensional object grasps. Based on previous works, those forces are computed by using a robust optimization scheme.In order to validate this strategy, different grasps and different manipulation tasks are presented and detailed with a simulation software, SMAR, developed by the PPRIME Institute. And finally experimental results with the real hand illustrate the efficiency of the whole approach.