A new approach to skill acquisition in assembly is proposed. An assembly skill is represented by a hybrid dynamic system where a discrete event controller models the skill at the task level. The output of the discrete event controller provides the reference commands for the underlying robot controller. This structure is naturally encoded by a hidden Markov model (HMM). The HMM parameters are obtained by training on sensory data from human demonstrations of the skill. Currently, assembly tasks have to be performed by human operators or by robots using expensive fixtures. Our approach transfers the assembly skill from an expert human operator to the robot, thus making it possible for a robot to perform assembly tasks without the use of expensive fixtures. 1 Introduction Manipulation tasks such as assembly are easily performed by human operators. However, these tasks are still difficult for robots and require the use of precise and expensive fixtures. Furthermore, human operators are ab...

In this paper, we present and compare two methods of identifying single-ended contact formations from force sensor patterns. Instead of using geometric models of the workpieces, both methods use force sensor signals only. In the first method, fuzzy logic is used to model the patterns in the force signals. Membership functions are generated automatically from training data and then used by the fuzzy classifier. In the second method, a neural network architecture is used to learn the mapping from force signals to contact formation class. Experimental results are presented for both the fuzzy and neural network classifiers, and the results are compared. In some cases, the fuzzy classifier has better performance, and in other cases, the neural net classifier is better. The results are discussed, and, finally, a training modification is presented which dramatically improves the performance of the inadequate neural net classifiers. 1. Introduction The motivation behind this work is to transf...

A new task-level adaptive controller is presented for the hybrid dynamic control of constrained motion systems. Using a hybrid dynamic model of the process, velocity constraints are derived from which satisfactory velocity commands are obtained. Due to modelling errors and parametric uncertainties, the velocity commands may be erroneous and may result in sub-optimal performance. A task-level adaptive control scheme, based on the occurrence of discrete events, is used to change the model parameters from which the velocity commands are determined. Automated control of an assembly task is given as an example and simulations and experiments for this task are presented. These results demonstrate the applicability of the method and also indicate properties for rapid convergence.

A method for combining dynamic force and static position measurements for the monitoring of assembly is presented. A multilayer perceptron (MLP) network is used as a classifier where the individual network outputs correspond to contact state transitions occuring during the assembly process. When a contact state transition occurs, the MLP output with the largest value is chosen. The recognised contact state is sent to a discrete event controller which guides the workpiece through a series of contact states to the final desired configuration. The MLP has been successfully implemented on a Motorola 68040 based VxWorks board with successful recognition rates of 94.4% and 92.0% on a training set and an independent test set, respectively. 1 Introduction Reliable monitoring of robotic assembly allows for error detection and recovery from unwanted and unexpected situations. In this paper we present a method for combining data from two common information sources; dynamic force and static pos...

Abstract not found

The motivation behind this work is to transfer force-based assembly skills to robots by using human demonstration. For this purpose, we model the skills as a sequence of contact formations (which describe how a workpiece touches its environment) and desired transitions between contact formations. In this paper, we present a method of identifying single-ended contact formations from force sensor patterns. Instead of using geometric models of the workpieces, fuzzy logic is used to learn and model the patterns in the force signals. Membership functions are generated automatically from training data and then used by the fuzzy classifier. This classification scheme is used to learn desired sequences of contact formations which comprise a force-based skill. Experimental results are presented which use the technique to extract skill information from human demonstration data. 1 Introduction Robot programming by using human demonstration provides a natural approach to human-robot interaction a...

Force guided robot control is a control scheme based on the interpretation of measured force acting on the robot end effector. A functional map relating the correction of motion to force measurements is generated based on the geometry of the workpiece and its kinematic behavior in interacting with the environment. In the traditional force-guided control schemes, the contact force measured by a force sensor is directly fed back to a feedback controller to generate a motion correction signal. In this paper, instead of simply measuring contact forces, we take positive actions by giving perturbation to the end effector and observing the reaction forces to the perturbation in order to obtain much richer and more reliable information. By the correlation between the input perturbation and the resultant reaction forces, we can determine the gradient of the force profile and guide the part correctly. By applying a type of direct adaptive control, the contact force is maintained at the lowest le...

Current manufacturing methods for robotic-controlled assembly rely on accurate positioning to ensure task completion, often through the use of special fixtures and precise calibration of the workspace. The reliance on precision positioning to achieve proper alignment creates problems in both programming and control of contact-based tasks. As a means of addressing these problems, we have been investigating the use of qualitative contact states (QCS) for modeling and learning low-level, force-based skills. Sensorimotor skills are modeled using force-based discrete states, which describe qualitatively how contact is being made with the environment. The qualitative states can be identified from force signals by viewing them as projected clusters in the force sensor space. In this paper, we investigate the automatic clustering of force data by applying a competitive agglomeration algorithm to extract clusters which can be used for QCS classifier training. Experimental results are included u...

control Whether they are asked to polish or assemble parts, clean the house or open doors, the future generation of robots will have to cope with contact tasks under uncertainty in a stable and safe manner. Obtaining a controlled contact motion under uncertainty is still a major challenge for the robotics community. At present most research groups focus on one of the subcomponents (i.e., modeling, planning, estimation or control) of the system, and no overall system is developed yet. This paper presents a literature survey of the state-of-the-art of the subcomponents and points to the need for effective integration of those components. 1