Concurrent optimal design of modular robotic configuration

This paper presents a new optimization design methodology that is applicable to modular systems. This new methodology is called concurrent optimization design method (CODM). A modular robot is taken as a case study. The CODM is superior to the existing methods for modular robot configuration design in the sense that traditional type synthesis and dimensional synthesis now can be treated once. This mathematically implies that (i) variables are defined for both types and dimensions, and (ii) all the variables are defined in one optimization problem formulation. This paper illustrates that, in fact, optimization design for modular architectures necessitates a multiobjective optimization problem. A genetic algorithm is used to solve for this complex optimization model which contains both discrete and continuous variables. © 2001 John Wiley & Sons, Inc.     

The design of a planar robotic manipulator for optimum performance of prescribed tasks

The application of a general optimization methodology, previously proposed by the authors, is extended here to the design of a three link revolute-joint planar manipulator performing more practical and complicated prescribed tasks. In particular a tool moving task and a spray painting task are considered. Both the minimization of average torque and energy usage required for execution of the tasks are addressed and the optimization is carried out with the link lengths and base coordinates taken as the five design variables. In addition to simple physical bounds placed on the variables, the maximum deliverable torques of the driving motors represent further constraints on the system. Joint angle constraints, not previously considered but of great practical importance, are also imposed in this study. This results in significantly more challenging optimization problems than those previously tackled. The complications arising from lock-up and nonassembly are handled by specially devised procedures. The optimization is carried out via penalty function formulations of the constrained problems to which the Snyman unconstrained trajectory optimization algorithm is applied in a special way. For both tasks and for both objective functions, with the full complement of constraints imposed, feasible designs with low objective function values are obtained by using, in each case, four different infeasible designs as starting points for the algorithm.     

A revisit of fast greedy heuristics for mapping a class of independent tasks onto heterogeneous computing systems

Mixed-machine heterogeneous computing (HC) environments utilize a distributed suite of different high-performance machines, interconnected with high-speed links, to perform groups of computing-intensive applications that have diverse computational requirements and constraints. The problem of optimally mapping a class of independent tasks onto the machines of an HC environment has been proved, in general, to be NP-complete, thus requiring the development of heuristic techniques for practical usage. If the mapping has real-time requirements such that the mapping process is performed during task execution, fast greedy heuristics must be adopted. This paper investigates fast greedy heuristics for this problem and identifies the importance of the concept of task consistency in designing this mapping heuristic. We further propose task priority graph based fast greedy heuristics, which consider the factors of both task consistency and machine consistency (the same concept of consistency as in previous studies). A collection of 20 greedy heuristics, including 17 newly proposed ones, are implemented, analyzed, and systematically compared within a uniform model of task execution time. This model is implemented by the coefficient-of-variation based method. The experimental results illuminate the circumstances when a specific greedy heuristic would outperform the other 19 greedy heuristics.     

Multiple tasks manipulation for a robotic manipulator

Robotic manipulators can execute multiple tasks precisely at the same time and, thus, the task-priority scheme plays an important role in implementing multiple tasks. Until now, several algorithms for task-priority have been used in solving the inverse kinematics for redundant manipulators. In this paper, through the comparative study of existing algorithms, we will propose a new method for task-priority manipulation in terms of two important criteria—algorithmic singularity and task error. This manipulation scheme will be applied to a planar three-link manipulator to demonstrate its effectiveness.     

Toward a scalable modular robotic system

In this article, we propose a simple docking method using an onboard camera module. It has two key ideas: one is image processing using a camera module and LEDs equipped on the modules, and the other is a special modular configuration designed for docking, which absorbs positional errors. We also designed a self-reconfiguration sequence to integrate a docked robot into a periodic structure. The effectiveness of the proposed method is examined by docking/integration experiments using 18 modules.     

A fast solution to identify placement parameters for modular platform manipulators

Ji and Li presented a method to identify placement parameters for a six‐leg platform manipulator [Z. Ji and Z. Li, J Robot Syst 16 (1999), 227–236]. They used Sylvester's dialytic elimination to reduce the identification equations to a univariable polynomial with 16 degrees. This article presents a fast and simple solution to the same problem. The complex function is used to simplify the identification equations, and a univariable polynomial equation is obtained with 8 degrees only. © 2000 John Wiley & Sons, Inc.     

Proposal of a shape adaptive gripper for robotic assembly tasks

This paper proposes a novel robotic gripper used for assembly tasks that can adaptively grasp objects with different shapes. The proposed hand has a combined structure between two kinds of shape adaptive mechanisms where one is the granular jamming and the other is a multi-finger mechanism driven by a single wire. Due to the effect of the two shape adaptive mechanisms, the pose of a grasped object does not change during an assembly operation. The proposed hand has four fingers where two are the active ones and the other two are the passive ones. The pose of the grasped object can be uniquely determined since the passive fingers are used to orient an object placed on a table before the active fingers are closed to grasp it. Assembly experiments of some kinds of parts are shown to validate the effectiveness of our proposed gripper.     

A review on reinforcement learning for contact-rich robotic manipulation tasks

Research and application of reinforcement learning in robotics for contact-rich manipulation tasks have exploded in recent years. Its ability to cope with unstructured environments and accomplish hard-to-engineer behaviors has led reinforcement learning agents to be increasingly applied in real-life scenarios. However, there is still a long way ahead for reinforcement learning to become a core element in industrial applications. This paper examines the landscape of reinforcement learning and reviews advances in its application in contact-rich tasks from 2017 to the present. The analysis investigates the main research for the most commonly selected tasks for testing reinforcement learning algorithms in both rigid and deformable object manipulation. Additionally, the trends around reinforcement learning associated with serial manipulators are explored as well as the various technological challenges that this machine learning control technique currently presents. Lastly, based on the state-of-the-art and the commonalities among the studies, a framework relating the main concepts of reinforcement learning in contact-rich manipulation tasks is proposed. The final goal of this review is to support the robotics community in future development of systems commanded by reinforcement learning, discuss the main challenges of this technology and suggest future research directions in the domain.     

MFHS: A modular scheduling framework for heterogeneous system

Current innovative distributed architectures, proposing on-line services, involve more and more computing resources. From a provider point of view, the platform management leads to challenging problematic relating to resource allocation, which involve different kind of quality of service parameters, the provider has to focus on to keep his platform reliable and efficient. MFHS is a modular generic framework, which can be adapted to any distributed computing environment. Structured in modules, MFHS allows to discover the existing computing resources in terms of computing performance, network throughput and disk I/O speeds (Resources Discovery module) and to predict how the experiment should behave (P_i value). As the setting up of real experiments is often complex, MFHS allows: to make theoretical experimentation (based on models), to use any kind of distributed emulators, or to deploy experiments on real-experimental platforms. In this article, these three environments are used to highlight the reliability of MFHS (measured P_i=90% against 94% for the predicted P_i). Deployment and scheduling studies have also been achieved using an experimental Cloud based on OpenStack while Emulab test-bed has been used as emulator. During experiments, four QoS parameters are taken into account (Resources Monitoring module): energy consumption, cost, resource utilization, and makespan. These studies also includes a new heuristic called MMin, based on Max-Min and Min-Min algorithms. Experimentation section, proposes a detailed comparative analysis of these algorithms in terms of QoS results, while the abilities of the proposed heuristic MMin regarding the makespan metric is shown.     

Design of a cat-inspired robotic leg for fast running

This paper introduces a novel design for a robotic leg to achieve a fast running mechanism that is inspired by domestic cats. The skeletomuscular system and parallel leg movement of a cat are analyzed and applied to determine the link parameters and the linkage structure of the proposed mechanism. The linkage design of the leg mechanism is explained, and a kinematic analysis based on vector loop equations is performed. The effectiveness of the proposed mechanism is verified experimentally. A single leg clamped to a vertically moving slider exhibits a step frequency of 4.45 Hz while supporting a 0.5 kg body weight. The biped robot runs at an average speed of 0.75 m/s at a step frequency of 2.8 Hz for a trot gait on flat ground. This leg mechanism can facilitate the development of fast running robot systems.     

Incremental reinforcement learning for multi-objective robotic tasks

Recently reinforcement learning has been widely applied to robotic tasks. However, most of these tasks hide more than one objective. In these cases, the construction of a reward function is a key and difficult issue. A typical solution is combining the multiple objectives into one single-objective reward function. However, quite often this formulation is far from being intuitive, and the learning process might converge to a behaviour far from what we need. Another alternative to face these multi-objective tasks is to use what is called transfer learning. In this case, the idea is to reuse the experience gained after the learning of an objective to learn a new one. Nevertheless, the transfer affects only to the learned policy, leaving out other gained information that might be relevant. In this paper, we propose a different approach to learn problems with more than one objective. In particular, we describe a two-stage approach. During the first stage, our algorithm will learn a policy compatible with a main goal at the same time that it gathers relevant information for a subsequent search process. Once this is done, a second stage will start, which consists of a cyclical process of small perturbations and stabilizations, and which tries to avoid degrading the performance of the system while it searches for a new valid policy but that also optimizes a sub-objective. We have applied our proposal for the learning of the biped walking. We have tested it on a humanoid robot, both on simulation and on a real robot.     

Biomimetic control architecture for robotic cooperative tasks

This article proposes some control algorithms to be applied to the MIROSOT robot league architecture. The MIROSOT league soccer game concept is fairly simple: two teams of robots, with 3–5 robots per side, play football autonomously. The ball that the teams play with is an orange golf ball. Above the pitch is a machine vision camera running at 60 frames per second. This camera is linked to a server, which calculates the positions and velocities of each of the robots and the ball, and then determines what each robot should be doing. These instructions are then communicated to the robots over wireless links. In order to develop an efficient control strategy and architecture, the robots have to use strategies from the real human soccer game. Using the software Simi Scout, a suitable analysis of tactics can be extracted from the games. After analyzing the soccer game, a number of attributes are specified and then embedded at different levels. The specified attributes are interconnected, and the analysis of the game is processed for optimization. Using this information, the robot program is adapted and experimental tests/games are played. We comment on the results, and propose an improved control architecture based on practical results.     

A fast two-stage ACO algorithm for robotic path planning

Ant colony optimization (ACO) algorithms are often used in robotic path planning; however, the algorithms have two inherent problems. On one hand, the distance elicitation function and transfer function are usually used to improve the ACO algorithms, whereas, the two indexes often fail to balance between algorithm efficiency and optimization effect; On the other hand, the algorithms are heavily affected by environmental complexity. Based on the scent pervasion principle, a fast two-stage ACO algorithm is proposed in this paper, which overcomes the inherent problems of traditional ACO algorithms. The basic idea is to split the heuristic search into two stages: preprocess stage and path planning stage. In the preprocess stage, the scent information is broadcasted to the whole map and then ants do path planning under the direction of scent information. The algorithm is tested in maps of various complexities and compared with different algorithms. The results show the good performance and convergence speed of the proposed algorithm, even the high grid resolution does not affect the quality of the path found.     

Automated modeling of modular robotic configurations

This research presents an automated method to build kinematic and dynamic models for assembling modular components of modular robotic systems. By comparison with other approaches, the proposed method is applicable to any robotic configuration with serial, parallel, or hybrid structures. In addition, it is object oriented so that each modular component is an element with a submodel and the overall model can be assembled from submodels subject to the connection constraints.     

Concept of self-reconfigurable modular robotic system

We present a concept of novel self-reconfigurable robotic system made of homogeneous autonomous robotic modules. Each robotic module has only two DOF, however a group of this module is able to change its connective configuration by changing their local connections. A cluster of the modules, thus can metamorphose into arbitrary configuration according to the surrounding environment or desired specification. Not only this ability of structural metamorphosis, the combined modules have functionality of robotic system which is capable of generating complicated motion.     

A database design for the runtime environment of a robotic workcell

Intelligent robotic workcell activities have come to require a database framework for arranging, storing and accessing information in real-time about the workcell environment in a standard way. After a brief introduction to the theory of databases (DB), we examine the general topic of robotic workcells, identify characteristics typical of robotic applications, and then present a survey of DB-related work in the robotics domain. We then construct a set of design constraints based on our analysis of robotic applications, and describe a suitable software architecture. The paper concludes with a discussion of experience gained with two generations of DB implementations.     

A software engineering approach for the development of heterogeneous robotic applications

One of the most evident characteristics of robotic applications is heterogeneity: large robotic projects involve many different researchers with very different programming needs and areas of research, using a variety of hardware and software that must be integrated efficiently (i.e.: with a low development cost) to construct applications that satisfy not only classic robotic requirements (fault-tolerance, real-time specifications, intensive access to hardware, etc.) but also software engineering aspects (reusability, maintainability, etc.). Most existing solutions to this problem either do not deal with such heterogeneity or do not cover specific robotic needs. In this paper we propose a framework for the integration of heterogeneous robotic software through a software engineering approach: the BABEL development system, which is aimed to cover the main phases of the application lifecycle (design, implementation, testing, and maintainance) when unavoidable heterogeneity conditions are present. The capabilities of our system are shown by its support for designing and implementing diverse real robotic applications that use several programming languages (C, C++, JAVA), execution platforms (RT-operating systems, MS-Windows, no operating system at all), communication middleware (CORBA, TCP/IP, USB), and also a variety of hardware components (Personal Computers, microcontrollers, and a wide diversity of sensor and actuator devices in mobile robots and manipulator arms).     

A two-phase analytic approach to robotic system design

A two-phase analytic approach to robotic system design is presented. The first phase evaluates the robotic technological classes according to their functional adequacy; the next phase specifies the desired robotic configuration. The methodology developed here is demonstrated for the case of installing a robot in an automated investment casting shelling production line.     

分布式训练异构任务调度算法研究

分布式机器学习中的工作结点在训练过程中经常需要处理异构任务,但任务发布者可能无法根据有效的先验知识确定边缘服务器集群中哪些是处于训练状态的工作结点.针对边缘服务器集群无法同时满足训练性能与服务质量最大化的问题,对异构任务调度算法进行了研究.首先在集群资源约束下分析了分布式训练收敛性能的影响因素;其次建立了最大化训练性能...