Simulated Robot Arm Research Articles

Supporting Human-Automation Collaboration Through Dynamic Function Allocation

Context-sensitive function allocation can take two forms: (a) ‘adaptable automation’, where changes in the allocation of functions are initiated by the user, or (b) ‘adaptive automation’, where the automation triggers changes. However, operational experience suggests that neither approach by itself is sufficient and appropriate. This paper describes a hybrid dynamic function allocation scheme, in which the system and the operator collaborate on selecting and activating appropriate automation levels. The default mode of the system is adaptive automation, but operators can override system selections when they feel the need and have the time to do so. The effectiveness of the hybrid system was compared to fixed function allocations, to an adaptive scheme and to adaptable function allocation in the context of simulated robotic arm control tasks. The hybrid system improved performance and reduced workload in routine scenarios. The system was also preferred over the fixed and adaptive approach by the operators. However, these benefits can be explained mainly by the excessive use of high levels of automation in this condition. The findings have implications on future designs of dynamic function allocation schemes in complex systems.

Confidence-based progress-driven self-generated goals for skill acquisition in developmental robots

A reinforcement learning agent that autonomously explores its environment can utilize a curiosity drive to enable continual learning of skills, in the absence of any external rewards. We formulate curiosity-driven exploration, and eventual skill acquisition, as a selective sampling problem. Each environment setting provides the agent with a stream of instances. An instance is a sensory observation that, when queried, causes an outcome that the agent is trying to predict. After an instance is observed, a query condition, derived herein, tells whether its outcome is statistically known or unknown to the agent, based on the confidence interval of an online linear classifier. Upon encountering the first unknown instance, the agent “queries” the environment to observe the outcome, which is expected to improve its confidence in the corresponding predictor. If the environment is in a setting where all instances are known, the agent generates a plan of actions to reach a new setting, where an unknown instance is likely to be encountered. The desired setting is a self-generated goal, and the plan of action, essentially a program to solve a problem, is a skill. The success of the plan depends on the quality of the agent's predictors, which are improved as mentioned above. For validation, this method is applied to both a simulated and real Katana robot arm in its “blocks-world” environment. Results show that the proposed method generates sample-efficient curious exploration behavior, which exhibits developmental stages, continual learning, and skill acquisition, in an intrinsically-motivated playful agent.

Modeling and Simulation of Flexible Hydraulic Robotic Arm

The flexible robotic arm drived by hydraulic are widely applied in most kinds of large engineering equipments, such as concrete pump truck, bridge monitor truck,etc. Nevertheless, the flexible distortion always break the precision of end-position and cause liberation of the whole arm system. In this paper, the movement of flexible hydraulic robotic arm and hydraulic cylinders are separately analyzed with flexible multi-body dynamics. And the dynamic differential equation is built with the driving force of the hydraulic cylinder as the main force. The equation is based on the theory of flexible multi-body dynamics, building the coupled model of robotic arm system and hydraulic-driving system to study the relation between the end-position, angle and the hydraulic system. What’s more, the simulation model of the mechanical arms is built by the dynamic simulation software. The project will theorectically support the intelligent control or auxiliary control of large engineering equipments.

The Development of a Myoelectric Training Tool for Above-Elbow Amputees

The objective of above-elbow myoelectric prostheses is to reestablish the functionality of missing limbs and increase the quality of life of amputees. By using electromyography (EMG) electrodes attached to the surface of the skin, amputees are able to control motors in myoelectric prostheses by voluntarily contracting the muscles of their residual limb. This work describes the development of an inexpensive myoelectric training tool (MTT) designed to help upper limb amputees learn how to use myoelectric technology in advance of receiving their actual myoelectric prosthesis. The training tool consists of a physical and simulated robotic arm, signal acquisition hardware, controller software, and a graphical user interface. The MTT improves over earlier training systems by allowing a targeted muscle reinnervation (TMR) patient to control up to two degrees of freedom simultaneously. The training tool has also been designed to function as a research prototype for novel myoelectric controllers. A preliminary experiment was performed in order to evaluate the effectiveness of the MTT as a learning tool and to identify any issues with the system. Five able-bodied participants performed a motor-learning task using the EMG controlled robotic arm with the goal of moving five balls from one box to another as quickly as possible. The results indicate that the subjects improved their skill in myoelectric control over the course of the trials. A usability survey was administered to the subjects after their trials. Results from the survey showed that the shoulder degree of freedom was the most difficult to control.

The Development of a Myoelectric Training Tool for Above-Elbow Amputees

The objective of above-elbow myoelectric prostheses is to reestablish the functionality of missing limbs and increase the quality of life of amputees. By using electromyography (EMG) electrodes attached to the surface of the skin, amputees are able to control motors in myoelectric prostheses by voluntarily contracting the muscles of their residual limb. This work describes the development of an inexpensive myoelectric training tool (MTT) designed to help upper limb amputees learn how to use myoelectric technology in advance of receiving their actual myoelectric prosthesis. The training tool consists of a physical and simulated robotic arm, signal acquisition hardware, controller software, and a graphical user interface. The MTT improves over earlier training systems by allowing a targeted muscle reinnervation (TMR) patient to control up to two degrees of freedom simultaneously. The training tool has also been designed to function as a research prototype for novel myoelectric controllers. A preliminary experiment was performed in order to evaluate the effectiveness of the MTT as a learning tool and to identify any issues with the system. Five able-bodied participants performed a motor-learning task using the EMG controlled robotic arm with the goal of moving five balls from one box to another as quickly as possible. The results indicate that the subjects improved their skill in myoelectric control over the course of the trials. A usability survey was administered to the subjects after their trials. Results from the survey showed that the shoulder degree of freedom was the most difficult to control.

Study on Kinematics and Simulation of Robotic Arm

In order to improve efficiency and automation of spraying, a automatic spray lance, which was regard as an robotic arm, was studied. It could reach the desired position automatically. A study was carried out using Denavit and Hartenberg (D-H) approach to automate the four Degrees of Freedom (DOF) robotic arm. The kinematics of robotic arm was constructed us D-H coordinate frame model. And the inverse kinematics has been solved with inverse transform technique. Some motion parameters could be acquired. Simulation of the robotic arm was studied using the Robotics Toolbox which is MATLAB software. Simulations’ content included homogeneous, construction of robot object, kinematics and trajectory. The results of simulation indicated that the movement of robotic arm could satisfy the demands of four DOF. The robotic was founded able to move to the desired position by simulating. The links’ motion parameters were reasonable and it provided a new spray lance for automatic sprayer.

A Cognitive Model for Generalization during Sequential Learning

Traditional artificial neural network models of learning suffer fromcatastrophic interference. They are commonly trained to perform only one specific task, and, when trained on a new task, they forget the original task completely. It has been shown that the foundational neurocomputational principles embodied by the Leabra cognitive modeling framework, specifically fast lateral inhibition and a local synaptic plasticity model that incorporates both correlational and error-based components, are sufficient to largely overcome this limitation during the sequential learning of multiple motor skills. Evidence has also provided that Leabra is able to generalize the subsequences of motor skills, when doing so is appropriate. In this paper, we provide a detailed analysis of the extent of generalization possible with Leabra during sequential learning of multiple tasks. For comparison, we measure the generalization exhibited by the backpropagation of error learning algorithm. Furthermore, we demonstrate the applicability of sequential learning to a pair of movement tasks using a simulated robotic arm.

Impact of Body Parameters on Dynamic Movement Primitives for Robot Control

The problem of movement coordination in large DoF (Degree of Freedom) robots is complex due to redundancies. In this regard, Dynamic Movement Primitive (DMP) is a useful planning technique, inspired by biology, that can be used to store and reproduce trajectories about every DoF. This work is a preliminary study that aims to understand and quantify the influence of the robot dynamics upon the performance of DMP in a simulated 2DoF robot arm. The investigation demonstrates that the effect of the robot body dynamics needs to be taken into account during the learning process of the DMP.

Active Categorical Perception of Object Shapes in a Simulated Anthropomorphic Robotic Arm

Active perception refers to a theoretical approach to the study of perception grounded on the idea that perceiving is a way of acting, rather than a process whereby the brain constructs an internal representation of the world. The operational principles of active perception can be effectively tested by building robot-based models in which the relationship between perceptual categories and the body-environment interactions can be experimentally manipulated. In this paper, we study the mechanisms of tactile perception in a task in which a neuro-controlled anthropomorphic robotic arm, equipped with coarse-grained tactile sensors, is required to perceptually categorize spherical and ellipsoid objects. We show that best individuals, synthesized by artificial evolution techniques, develop a close to optimal ability to discriminate the shape of the objects as well as an ability to generalize their skill in new circumstances. The results show that the agents solve the categorization task in an effective and robust way by self-selecting the required information through action and by integrating experienced sensory-motor states over time.

Learning Algorithms for Human–Machine Interfaces

The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore-Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction.

Geodesic Gaussian kernels for value function approximation

The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in simulated robot arm control and Khepera robot navigation.

Recurrent Cerebellar Loops Simplify Adaptive Control of Redundant and Nonlinear Motor Systems

We have described elsewhere an adaptive filter model of cerebellar learning in which the cerebellar microcircuit acts to decorrelate motor commands from their sensory consequences (Dean, Porrill, & Stone, 2002). Learning stability required the cerebellar microcircuit to be embedded in a recurrent loop, and this has been shown to lead to a simple and modular adaptive control architecture when applied to the linearized 3D vestibular ocular reflex (Porrill, Dean, & Stone, 2004). Here we investigate the properties of recurrent loop connectivity in the case of redundant and nonlinear motor systems and illustrate them using the example of kinematic control of a simulated two-joint robot arm. We demonstrate that (1) the learning rule does not require unavailable motor error signals or complex neural reference structures to estimate such signals (i.e., it solves the motor error problem) and (2) control of redundant systems is not subject to the nonconvexity problem in which incorrect average motor commands are learned for end-effector positions that can be accessed in more than one arm configuration. These properties suggest a central functional role for the closed cerebellar loops, which have been shown to be ubiquitous in motor systems (e.g., Kelly & Strick, 2003).

Evolution of prehension ability in an anthropomorphic neurorobotic arm

In this paper, we show how a simulated anthropomorphic robotic arm controlled by an artificial neural network can develop effective reaching and grasping behaviour through a trial and error process in which the free parameters encode the control rules which regulate the fine-grained interaction between the robot and the environment and variations of the free parameters are retained or discarded on the basis of their effects at the level of the global behaviour exhibited by the robot situated in the environment. The obtained results demonstrate how the proposed methodology allows the robot to produce effective behaviours thanks to its ability to exploit the morphological properties of the robot's body (i.e. its anthropomorphic shape, the elastic properties of its muscle-like actuators and the compliance of its actuated joints) and the properties which arise from the physical interaction between the robot and the environment mediated by appropriate control rules.

Towards robot cultures?

The study of imitation and other mechanisms of social learning is an exciting area of research for all those interested in understanding the origin and the nature of animal learning in a social context. Moreover, imitation is an increasingly important research topic in Artificial Intelligence and social robotics which opens up the possibility of individualized social intelligence in robots that are part of a community, and allows us to harness not only individual learning by the single robot, but also the acquisition of new skills by observing other members of the community (robots, humans, or virtual agents). After an introduction to the main research issues in research on imitation in various fields (including psychology, biology and robotics), we motivate the particular focus of this work, namely the correspondence problem. We describe Action Learning for Imitation via Correspondences between Embodiments (Alice), an implemented generic framework for solving the correspondence problem between differently embodied robots. Alice enables a robotic agent to learn a behavioral repertoire suitable to performing a task by observing a model agent. Importantly, the model agent could possibly possess a different type of body, e.g. a different number of limbs or joints (implying different degrees of freedom), a different height, different sensors, a different basic action repertoire, etc. Previously, in a test-bed where the agents differed according to their possible movement patterns, we demonstrated that the character of imitation achieved will depend on the granularity of subgoal matching, and on the metrics used to evaluate success. In our current work, we implemented Alice in a new test-bed called Rabit where simple simulated robotic arm agents use various metrics for evaluating success according to actions, states, effects, or weighted combinations. We examine the roles of synchronization, looseness of perceptual matching, and of proprioceptive matching by a series of experiments. Also, we study how Alice copes with changes in the embodiment of the imitator during learning. Our simulation results suggest that synchronization and loose perceptual matching allow for faster acquisition of behavioral compentencies at low error rates. Social learning (broadly construed) plays a role as a replication mechanism for behaviors and results in variability when the transmitted behavior differs from the model’s behavior, thus providing the evolutionary substrate for culture and its pre-cursors. Social learning in robotics could therefore serve as the basis for culture in societies whose members include artificial agents. We address the use of imitative social learning mechanisms like Alice for transmission of skills between robots, and give first examples of transmission of a skill despite differences in embodiment of agents involved. In the particular setup, transmission occurs through a chain, as well as emerging in cyclic arrangements of robots. These simple examples demonstrate that by using social learning and imitation, (proto-)cultural transmission is possible among robots, even in heterogeneous groups of robots.

Evolving the Neural Controller for a Robotic Arm Able to Grasp Objects on the Basis of Tactile Sensors

We describe the results of a set of evolutionary experiments in which a simulated robotic arm provided with a two-fingered hand has to reach and grasp objects with different shapes and orientations on the basis of simple tactile information. The results that we obtained are encouraging and demonstrate that the problem of grasping objects with characteristics that vary within a certain range can be solved by producing rather simple forms of behavior. These forms of behavior exploit emergent characteristics of the interaction between the body of the robot, its control system, and the environment. In particular we show that evolved individuals do not try to keep the environment stable, but rather push and pull the objects; thus, they produce a dynamic in the environment and exploit the interaction between the body of the robot and the dynamic environment to master different environmental conditions with similar control strategies.

Evolving in Real Time a Neural Net Controller of Robot‐Arm: Track and Evolve

Evolutionary Engineering (EE) is defined to be “the art of using evolutionary algorithms approach such as genetic algorithms to build complex systems”. This paper deals with a neural net based system. It analyses ability of genetically trained neural nets to control Simulated robot arm, witch tries to track a moving object. In difference from classical Approaches neural network learning is performed on line, i.e., in real time. Usually systems are built/evolved, i.e., genetically trained separately of their utilization. That is how it is commonly done. It's a fact that evolution process is heavy on time; that's why Real-Time approach is rarely taken into consideration. The results presented in this paper show that such approach (Real-Time EE) is possible. These successful results are essentially due to the “continuity” of the target's trajectory. In EE terms, we express this by the Neighbourhood Hypothesis (NH) concept.

An Efficient Constraint Force Computation in Multibody Systems

An efficient method for constraint force analysis of specified joints has been developed in a serially connected open chain multibody system. In the method, the system equations of motion are derived using the recursive formulation, but constraint forces are computed non-recursively for specified joints. The efficiency of the proposed formulation has been compared with the recursive Newton-Euler formulation by the operational counting and the CPU time measure. To validate solution accuracy of the proposed method, the 7 d. o.f RRC robot arm simulation has been carried out. Essentially the same simulation results are obtained from the proposed method and from the commercial dynamics analysis program DADS.

Benchmarking cerebellar control

Cerebellar models have long been advocated as viable models for robot dynamics control. Building on an increasing insight in and knowledge of the biological cerebellum, many models have been greatly refined, of which some computational models have emerged with useful properties with respect to robot dynamics control. Looking at the application side, however, there is a totally different picture. Not only is there a robot on the market which uses anything remotely connected with cerebellar control, but also in research labs most testbeds for cerebellar models are restricted to toy problems. Such applications hardly ever exceed the complexity of a 2 DoF simulated robot arm; a task which is hardly representative for the field of robotics, or relates to realistic applications. In order to bring the amalgamation of the two fields forward, we advocate the use of a set of robotics benchmarks, on which existing and new computational cerebellar models can be comparatively tested. It is clear that the traditional approach to solve robotics dynamics loses ground with the advancing complexity of robotic structures; there is a desire for adaptive methods which can compete as traditional control methods do for traditional robots. In this paper we try to lay down the successes and problems in the fields of cerebellar modelling as well as robot dynamics control. By analysing the common ground, a set of benchmarks are suggested which may serve as typical robot applications for cerebellar models.

An adaptive fuzzy sliding-mode controller for a robot arm

This paper deals with a new adaptive sliding mode controller and its practical application to a robot manipulator arm. The theory for this new fuzzy sliding mode controller approach and for the heuristics-bayed linguistic adaptation is presented and a mathematical description is derived. Furthermore the application of this adaptive controller is shown for a simulated two-link robot arm and for the real time operation of a mobile three-link robot arm, respectively. The obtained results show the high efficiency of the new controller type.

Monitoring and diagnosis of multiple incipient faults using fault tree induction

The paper presents DE/IFT, a new fault diagnosis engine which is based on the authors' IFT algorithm for induction of fault trees. It learns from an examples database comprising sensor recordings, all of which have been classified as corresponding to either the normal behaviour of the system or to one or more fault states. The fault trees generated by IFT are translated into functions in the C programming language. The disgnosis engine links these into a shell program to yield a software system for monitoring and fault diagnosis which has a fast reaction time and is capable of dealing with complicated fault situations. The use of DE/IFT is demonstrated by diagnosing incipient faults in a simulated pneumatic servo-controlled robot arm, where the sensor recordings it uses are transient responses of the servo system to an input test signal. A variety of different situations are considered, including singly occurring faults and multiple simultaneous faults, developing steadily over time or occurring intermittently.