Adept Robot Research Articles

Shared intentionality and the representation of groups; or, how to build a socially adept robot.

Pietraszewski provides a compelling case that representations of certain interaction-types are the "cognitive primitives" that allow all tokens of group-in-conflict to be represented within the mind. Here, I argue that the folk concept GROUP encodes shared intentions and goals as more central than these interaction-types, and that providing a computational theory of social groups will be more difficult than Pietraszewski envisages.

Event-driven industrial robot control architecture for the Adept V+ platform.

Modern industrial robotic systems are highly interconnected. They operate in a distributed environment and communicate with sensors, computer vision systems, mechatronic devices, and computational components. On the fundamental level, communication and coordination between all parties in such distributed system are characterized by discrete event behavior. The latter is largely attributed to the specifics of communication over the network, which, in terms, facilitates asynchronous programming and explicit event handling. In addition, on the conceptual level, events are an important building block for realizing reactivity and coordination. Event-driven architecture has manifested its effectiveness for building loosely-coupled systems based on publish-subscribe middleware, either general-purpose or robotic-oriented. Despite all the advances in middleware, industrial robots remain difficult to program in context of distributed systems, to a large extent due to the limitation of the native robot platforms. This paper proposes an architecture for flexible event-based control of industrial robots based on the Adept V+ platform. The architecture is based on the robot controller providing a TCP/IP server and a collection of robot skills, and a high-level control module deployed to a dedicated computing device. The control module possesses bidirectional communication with the robot controller and publish/subscribe messaging with external systems. It is programmed in asynchronous style using pyadept, a Python library based on Python coroutines, AsyncIO event loop and ZeroMQ middleware. The proposed solution facilitates integration of Adept robots into distributed environments and building more flexible robotic solutions with event-based logic.

VMES: Virtualization aware manufacturing execution system

The large scale emergence in the last decade of various cloud solutions, ranging from software-as-a-service (SaaS) based solutions for business process management and implementation to very sophisticated private cloud solutions capable of high performance computing (HPC) and efficient virtualization, constitute the building blocks for engineering the next generation of flexible enterprise systems that can respond with great agility to changes in their environment. These new technologies are adopted at a certain level by manufacturing enterprises in order to advance in a new era of mass customization where flexibility, scalability and agility are the differentiating factors. In this context, this paper introduces the virtualized manufacturing execution system (vMES), an intermediate layer in the manufacturing stack, and discusses the advantages and limitations offered by this approach for manufacturing enterprises. A classification of MES workloads based on the ISA-95 function model is presented, focusing on the virtualization techniques suitable for each workload, considering the algorithms and technologies used and the virtualization overhead. A pilot vMES implementation using a parallel process for smart resource provisioning and automatic scaling is also presented. The pilot implementation using six Adept robots and one IBM CloudBurst 2.1 private cloud and an ISA-95 based MES is described; the virtualization sequence is analyzed in several scenarios of resource workload collocation on physical cloud blades with and without perturbations.

Stereo Vision System for A Bin Picking Adept Robot

In bin picking applications, robots are required to pick up an object from a pile of stacked or scattered objects placed in a bin. To perform such tasks, identification of the objects to be picked using a vision system is indispensable. In this paper, a stereo vision based automated bin picking system is proposed which identifies the topmost object from a pile of occluded objects and computes its location. The proposed bin picking process consists of two modules namely object segmentation module and object localization module. In the segmentation module, an ‘Acclimatized Top Object Threshold’ [ATOT] algorithm is proposed for segmentation of topmost object and in the localization module, the location of the object is estimated by computing the ‘x’, ‘y’, ‘z’ co-ordinates of the object midpoint using a unified stereo imaging algorithm. The validity of the algorithms is experimentally verified for object pick and place operations using the object location co-ordinates. The developed stereo vision system was implemented and validated for bin pick and place operations on an Adept Cobra 600 Robot.

Segmentation and Location Computation of Bin Objects

In this paper we present a stereo vision based system for segmentation and location computation of partially occluded objects in bin picking environments. Algorithms to segment partially occluded objects and to find the object location [midpoint,x, y and z co-ordinates] with respect to the bin area are proposed. The z co-ordinate is computed using stereo images and neural networks. The proposed algorithms is tested using two neural network architectures namely the Radial Basis Function nets and Simple Feedforward nets. The training results fo feedforward nets are found to be more suitable for the current application. The proposed stereo vision system is interfaced with an Adept SCARA Robot to perform bin picking operations. The vision system is found to be effective for partially occluded objects, in the absence of albedo effects. The results are validated through real time bin picking experiments on the Adept Robot.

Active tracking of unknown surface using force sensing and control technique for robot

This paper is an introduction to a methodology of active tracking of unknown surface using force sensing and control technique for robot. The hierarchical system of force sensing and control for robot is built from the perspective of large-scale system. And a novel strategy of force sensing and control is presented on the basis of information fusion of force and position, fuzzy hierarchical coordination and neural control. The essential equations have been derived precisely for robot to understand the unknown surface under the consideration of friction and constraint conditions of motion and force. New algorithms of fuzzy hierarchical coordination-based neural control have been developed. The experimental researches of tracking bulb surface for robot are implemented in Adept robot. Good result is obtained.

Robotic Grasping by Showing: An Experimental Comparison of Two Algorithms

Abstract This paper describes and evaluates the results of two algorithms for robotic grasp formulation on previously unseen 2-D thick laminae. Each algorithm determines the grasp specification from a binary image of the object to be grasped; one is an approach based on Powers’ Perceptual Control Theory and the other is based on hierarchical occupancy arrays. The experimental comparison of the two algorithms involves locating suitable grasps on objects that are difficult to grasp because of their geometry and because of variations in surface roughness and in product size and shape; they are trapezoidal portions of frozen fish coated in breadcrumbs, although for the purposes of this study artificial replica products were used. Grasp sites were located using the two different algorithms, and the quality of the grasps achieved was tested empirically using a ‘pick-up and shake’ routine on an Adept robot to simulate high speed manipulation in a production environment.

A Symmetry Theory of Planar Grasp

A theory for identification and classification of two-fingered grasps is described and demonstrated. It is shown that optimal finger positions are obtained from the pairwise intersections of three subsets in the configuration space for the gripper: the symmetry and antisymmetry sets, and the critical set of the grasp map. Furthermore the three sets themselves form boundaries in a natural partition of configuration space. The partition corresponds to a classification of possible grasps according to their stability properties. An implementation of the theory has been developed for an ADEPT robot with visual sensing.

Development of a soldering/inspection workcell for surface mount devices

The small focused spot size and localized heating possible with laser soldering makes it an attractive alternative technique for bonding surface mount devices with small lead pitch onto a printed wiring board. Using a Nd:YAG laser, we have applied this technique to reflow soldering of a test device-a 224-pin quad ceramic chip (lead spacing 25 mil)-onto pretinned substrates. The soldering step was incorporated into a larger workcell, in which an Adept robot was used to place the component in position and also to scan the laser beam, delivered via a fiber, over the leads to be soldered. The mobile laser head was modified to accept a miniature CCD camera coupled to a Cognex vision system, which allowed coincident viewing of the soldering process and postsoldering inspection of the joints.

Control of switched reluctance motor torque for force control applications

The paper presents a method for controlling switched reluctance motor (SRM) torque for force control applications. SRMs are used in AdeptOne robots, and the authors perform experiments with two robots, controlled in coordination, in grasping and manipulation of various objects. The object and robot parameters are not exactly known, and adaptive methods are used to control the overall system. These methods are model-based control techniques which require high bandwidth torque control. This requirement is typical for high precision mechanisms. SRM characteristics are very nonlinear. In particular the torque ripple, friction, and the torque versus position and current relationships were analyzed in the context mentioned above, and specifically, for force control applications. The proposed method is based on a new commutation algorithm and a measured torque versus position and current relationship, used to smooth the SRM's torque ripple, hence generating a torque output nearly independent of position. Furthermore, the internal friction is estimated on-line, and compensated for. This renders a high accuracy torque tracking. The torque control method is based on feedback from the motor angular velocity, motor angle, armature current, and feedforward for friction compensation and cancellation of nonlinear effects. The method has been tested experimentally on Adept motors and the results were very encouraging. The method has been also used for adaptive control of two coordinated Adept robots.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

MIELE STANDARDIZES ON ADEPT ROBOTS FOR ASSEMBLY APPLICATIONS

German domestic appliance manufacturer Miele has decided to standardize on Adept robots for assembly applications at its plant in Bielefeld. Four of the Californian robot company's machines are already employed in the plant, assembling different elements of vacuum cleaners and dishwashers.

ADEPT HELPS PHILIPS

PHILIPS APPLIES ADEPT ROBOTS TO AUTOMATE CAPACITOR ASSEMBLY ‐ Adept robots are helping Philips Components to revitalise completely its capacitor production facility in Zwolle, the Netherlands. In an attempt to combat international competition, particularly from the Japanese, Philips has entirely redesigned both product and process to enable the whole range of capacitors to be produced in a single highly automated flexible facility. In this way, Philips hopes to overcome the competitive pressure that four or five years ago threatened the very existence of the plant. Says Hans de Vries, Manager of Mechanisation, “We were too expensive, the machinery was too old and the labour content was too high”. The modern plant he is currently installing could not be more automated. Based around 12 SCARA robots supplied by Californian robotics manufacturer Adept Technology, the plant can be operated round the clock with just three operators in attendance at all times.