Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Results
Conclusion
References
All Topics
Computer Science
Artificial Intelligence

Toward a vocabulary of primitive task programs for humanoid robots

Profile image of Victor Ng-Thow-HingVictor Ng-Thow-HingProfile image of Evan DrumwrightEvan Drumwright

International Conference on …

Abstract

Researchers and engineers have used primitive actions to facilitate programming of tasks since the days of Shakey [1]. Task-level programming , which requires the user to specify only subgoals of a task to be accomplished, depends on such a set of primitive task programs to perform these subgoals. Past research in this area has used the commands from robot programming languages as the vocabulary of primitive tasks for robotic manipulators. We propose drawing from work measurement systems to construct the vocabulary of primitive task programs. We describe one such work measurement system, present several primitive task programs for humanoid robots inspired from this system, and show how these primitive programs can be used to construct complex behaviors. Index Terms— robot programming, task-level programming, humanoid robots

Figures (7)
Fig. 1. Several examples of MTM-1 elements in action.
Fig. 1. Several examples of MTM-1 elements in action.
Fig. 2. A depiction of the reach task program in action. This figure shows the process of reaching to a broom in a simulated real-world environment in a collision-free manner.
Fig. 2. A depiction of the reach task program in action. This figure shows the process of reaching to a broom in a simulated real-world environment in a collision-free manner.
4) Release: Release is used to release the grasp on an object. It utilizes a “rest” posture for the robot hand and generates joint-space trajectories to drive the fingers from the current grasping configuration to the rest posture. Thus, it is equivalent to the MTM-1 “normal” release (see Section IlI-F). Fig. 4. Using release to relinquish the grip on the vacuum
4) Release: Release is used to release the grasp on an object. It utilizes a “rest” posture for the robot hand and generates joint-space trajectories to drive the fingers from the current grasping configuration to the rest posture. Thus, it is equivalent to the MTM-1 “normal” release (see Section IlI-F). Fig. 4. Using release to relinquish the grip on the vacuum
Fig. 3. Depiction of using the grasp program to clutch a tennis ball Grasp currently implements only one of the five subcate- gories of the MTM-1 grasp element, that of the “pick up” grasp. “Regrasping” and “transfer grasping”, though not cur- rently handled, could be added to the grasp program without much difficulty. However, grasping among a tion of objects and grasps that require comp jumbled collec- ex interactions with the environment (i.e., the “contact”, “slid e”, and “hook” grasps) present significant obstacles to implementation. Thus, the reach program is currently far less expressive than its corresponding MTM-1! element.
Fig. 3. Depiction of using the grasp program to clutch a tennis ball Grasp currently implements only one of the five subcate- gories of the MTM-1 grasp element, that of the “pick up” grasp. “Regrasping” and “transfer grasping”, though not cur- rently handled, could be added to the grasp program without much difficulty. However, grasping among a tion of objects and grasps that require comp jumbled collec- ex interactions with the environment (i.e., the “contact”, “slid e”, and “hook” grasps) present significant obstacles to implementation. Thus, the reach program is currently far less expressive than its corresponding MTM-1! element.
the fixate program and the eye movements element accom- plish the same task, that of looking at a specific location. Fig. 5. Depiction of the action of the fixate program; the simulated robot is commanded to focus on the vacuum. The robot turns on its base while simultaneously orienting its head.
the fixate program and the eye movements element accom- plish the same task, that of looking at a specific location. Fig. 5. Depiction of the action of the fixate program; the simulated robot is commanded to focus on the vacuum. The robot turns on its base while simultaneously orienting its head.
Fig. 6. Using a complex behavior composed of fixate, position, and release to put down an object
Fig. 6. Using a complex behavior composed of fixate, position, and release to put down an object
Fig. 7. _ Using a complex behavior composed of position and fixate tc simulated vacuuming debris
Fig. 7. _ Using a complex behavior composed of position and fixate tc simulated vacuuming debris

Related papers

Dynamic control for the task/posture coordination of humanoids: Toward synthesis of complex activities
joseph salini

2014

The research developed in this PhD thesis deals with the general problem of dynamic control of ''task-oriented'' under-actuated and redundant systems considering more specifically the humanoid robotic systems. This research brings contributions to the problem of motor activities synthesis for constrained systems by their intrinsic capacities and by particular physical interactions with the environment. More specific issues that were addressed relate to: 1) the dynamic control of humanoid systems for carrying out basic activities requiring task/posture coordination perturbed by physical interactions, 2) the building of sequences of continuous dynamic activities based on a repertoire of motor coordination, 3) the planning and the adaptation of activities in the aim of a supervised automatic sequencing for complex non-deterministic tasks. The first chapter of this thesis is devoted to the description of a physical simulation engine and control laws for the development o...

View PDFchevron_right
The Task Matrix Framework for Platform-Independent Humanoid Programming
Victor Ng-Thow-Hing

2006 6th IEEE-RAS International Conference on Humanoid Robots, 2006

Programming humanoid robots is such a difficult endeavor that the focus of the effort has recently been on semiautomated methods such as programming-by-demonstration and reinforcement learning. However, these methods are currently constrained by algorithmic or technological limitations. This paper discusses the Task Matrix, a framework for programming humanoid robots in a platform independent manner, that makes manual programming viable by the provision of software reuse. We examine the Task Matrix and show how it can be used to perform both simple and complex tasks on two simulated humanoid robots.

View PDFchevron_right
Manipulation task primitives for composing robot skills
Pradeep Khosla

Proceedings of International Conference on Robotics and Automation, 1997

A manipulation task primitive is classified by the relative motion between two (rigid) parts. Only twenty different relative motions are possible and these can be used to guide the identification and development of manipulation task primitives. The goal is to build a richer library of robot capabilities in the manipulation domain. By identifying manipulation task primitives and instantiating solutions to them with available sensors and robot hardware in the form of sensorimotor primitives, we provide a higher-level abstraction for composing solutions to complex manipulation tasks.

View PDFchevron_right
Humanoid robots: a new kind of tool
Bryan Adams

IEEE Intelligent Systems, 2000

View PDFchevron_right
From Abstract Task Knowledge to Executable Robot Programs
Rudiger Dillmann

Journal of Intelligent and Robotic Systems, 2008

Robots that are capable of learning new tasks from humans need the ability to transform gathered abstract task knowledge into their own representation and dimensionality. New task knowledge that has been collected e.g. with Programming by Demonstration approaches by observing a human does not a-priori contain any robot-specific knowledge and actions, and is defined in the workspace of the human demonstrator. This article presents a new approach for mapping abstract human-centered task knowledge to a robot execution system based on the target system properties. Therefore the required background knowledge about the target system is examined and defined explicitely.

View PDFchevron_right
An Integrated System to approach the Programming of Humanoid Robotics
Emanuele Menegatti

This paper describes a set of laboratory experiences focused on humanoid robots offered at the University of Padua. Instructors developed an integrated system through which students can work with robots. The aim is to improve the educational experience introducing a new learning tool, namely a humanoid robot, and the Robots Operating System (ROS) in a constructivist framework. This approach to robotics teaching lets students exploiting up-to-date robotic technologies and to deal with multidisciplinary problems, applying a scientific approach. By using humanoid robots, students are able to compare human movements to robot motion. The comparison brings out human/robot similarities, pushing students to solve complex motion problems in a more natural way while discovering robot limitations. In this paper, the learning objectives of the project, and the tools used by the students are presented. A set of evaluation results are provided in order to validate the authors' purpose. Finally, a discussion about designed experiences and possible future improvements is reported, hoping to encourage further spread of educational robotics in schools at all levels.

View PDFchevron_right
Programming Robots for Activities of Everyday Life
Dragule Swaib

2021

Text-based programming remains a challenge to novice programmers in\ua0all programming domains including robotics. The use of robots is gainingconsiderable traction in several domains since robots are capable of assisting\ua0humans in repetitive and hazardous tasks. In the near future, robots willbe used in tasks of everyday life in homes, hotels, airports, museums, etc.\ua0However, robotic missions have been either predefined or programmed usinglow-level APIs, making mission specification task-specific and error-prone.\ua0To harness the full potential of robots, it must be possible to define missionsfor specific applications domains as needed. The specification of missions of\ua0robotic applications should be performed via easy-to-use, accessible ways, and\ua0at the same time, be accurate, and unambiguous. Simplicity and flexibility in\ua0programming such robots are important, since end-users come from diverse\ua0domains, not necessarily with suffcient programming knowledge.The mai...

View PDFchevron_right
A Comprehensive Software Framework for Complex Locomotion and Manipulation Tasks Applicable to Different Types of Humanoid Robots
Stefan Kohlbrecher

Frontiers in Robotics and AI, 2016

While recent advances in approaches for control of humanoid robot systems show promising results, consideration of fully integrated humanoid systems for solving complex tasks, such as disaster response, has only recently gained focus. In this paper, a software framework for humanoid disaster response robots is introduced. It provides newcomers as well as experienced researchers in humanoid robotics a comprehensive system comprising open source packages for locomotion, manipulation, perception, world modeling, behavior control, and operator interaction. The system uses the Robot Operating System (ROS) as a middleware, which has emerged as a de facto standard in robotics research in recent years. The described architecture and components allow for flexible interaction between operator(s) and robot from teleoperation to remotely supervised autonomous operation while considering bandwidth constraints. The components are self-contained and can be used either in combination with others or standalone. They have been developed and evaluated during participation in the DARPA Robotics Challenge, and their use for different tasks and parts of this competition are described.

View PDFchevron_right
Using Humanoid Robot to Instruct and Evaluate Performance of a Physical Task
Ali Sharifara

2018

In this paper, we present a tool to assess users ability to change tasks. To do this, we use a variation of the Box and Blocks Test. In this version, a humanoid robot instructs a user to perform a task involving the movement of certain colored blocks. The robot changes randomly change the color of blocks that the user is supposed to move. Canny Edge Detection and Hough Transformation are used to assess user perform the robot's built-in camera. This will allow the robot to inform the user and keep a log of their progress. We present this method for monitoring user progress by describing how the moved blocks are detected. We also present the results of a pilot study where users used this system to perform the task. Preliminary results show that users do not perform differently when the task is changed in this scenario.

View PDFchevron_right
Operating Humanoid Robots in Human Environments
Ee Sian Neo

Depending on the autonomous capability of the robot and the familiarity of the robot system with the task and environment, the level of human intervention differs. This paper introduces a methodology which allows a human operator to seamlessly switch between the continuous control of motion using an analog input device and the discrete behavior control cooperating with the robot using symbolic commands. Using the proposed methods, a human operator is able to operate humanoid robots with high flexibility by only using a simple operation interface. Successful experiments operating humanoid robot HRP-2 in executing everyday tasks proved the high reliability of the proposed operation system.

View PDFchevron_right

References (16)

  1. N. J. Nilsson, "A mobile automaton: An application of artificial intelligence techniques," in Proc. of Intl. Joint Conf. on Artificial Intelligence, Washington, D.C., May 1969.
  2. S. Schaal, "Is imitation learning the route to humanoid robotics?" Trends in Cognitive Sciences, vol. 3, no. 6, pp. 233-242, 1999.
  3. E. Drumwright and M. Matarić, "Generating and recognizing free- space movements in humanoid robots," in 2003 IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), Las Vegas, NV, October 2003, pp. 1672-1678.
  4. T. Lozano-Pérez, "Task planning," in Robot motion: planning and control, M. Brady, J. M. Hollerbach, T. L. Johnson, T. Lozano-Perez, and M. T. Mason, Eds. MIT Press, 1982, pp. 474-498.
  5. R. Taylor, P. Summers, and J. Meyer, "Aml: A manufacturing lan- guage," Intl. Journal of Robotics Research, vol. 1, no. 3, 1982.
  6. S. Narasimhan, "Task level strategies for robots," Ph.D. dissertation, Massachusetts Institute of Technology, 1994.
  7. A. M. Segre, Machine learning of robot assembly plans. Kluwer Academic Publishers, 1988.
  8. J. R. Chen, "Constructing task-level assembly strategies in robot programming by demonstration," Intl. Journal of Robotics Research, vol. 24, no. 12, pp. 1073-1085, Dec 2005.
  9. D. C. Bentivegna, "Learning from observation using primitives," Ph.D. dissertation, Georgia Institute of Technology, 2004.
  10. A. Fod, M. Matarić, and O. Jenkins, "Automated derivation of primi- tives for movement classification," Autonomous Robots, vol. 12, no. 1, pp. 39-54, January 2002.
  11. A. Ijspeert, J. Nakanishi, and S. Schaal, "Learning attractor landscapes for learning motor primitives," in Advances in Neural Information Processing Systems 15, S. Becker, S. Thrun, and K. Obermayer, Eds., 2002, pp. 1547-1554.
  12. D. W. Karger and W. M. Hancock, Advanced Work Measurement. New York, NY: Industrial Press, Inc., 1982.
  13. W. Antis, J. John M. Honeycutt, and E. N. Koch, The Basic Motions of MTM. The Maynard Foundation, 1973.
  14. B. W. Niebel, Motion and time study, 8th ed. Richard D. Irwin, Inc., 1988.
  15. E. Drumwright and V. Ng-Thow-Hing, "The task matrix: An extensible framework for creating versatile humanoid robots," in Proc. of the IEEE Intl. Conf. on Robotics and Automation (ICRA), Orlando, FL, USA, 2006.
  16. K. Hirai, M. Hirose, Y. Haikawa, and T. Takenaka, "The development of honda humanoid robot," in Proc. of the IEEE Intl. Conf. on Robotics and Automation (ICRA), Leuven, Belgium, May 1998, pp. 1321-1326.

Related papers

The Task Matrix: An Extensible Framework for Creating Versatile Humanoid Robots
Victor Ng-Thow-Hing

The successful acquisition and organization of a large number of skills for humanoid robots can be facilitated with a collection of performable tasks organized in a task matrix. Tasks in the matrix can utilize particular preconditions and inconditions to enable execution, motion trajectories to specify desired movement, and references to other tasks to perform subtasks. Interaction between the matrix and external modules such as goal planners is achieved via a high-level interface that categorizes a task using its semantics and execution parameters, allowing queries on the matrix to be performed using different selection criteria. Performable tasks are stored in an XML-based file format that can be readily edited and processed by other applications. In its current implementation, the matrix is populated with sets of primitive tasks (eg., reaching, grasping, arm-waving) and macro tasks that reference multiple primitive tasks (Pick-and-place and Facing-and-waving).

View PDFchevron_right
Programming by demonstration: Dual-arm manipulation tasks for humanoid robots
Rudiger Dillmann

2004

This paper deals with easy programming methods of dual-arm manipulation tasks for humanoid robots. Hereby a Programming by Demonstration system is used in order to observe, learn and generalize tasks performed by humans. A classification for dual-arm manipulations is introduced, enabling a segmentation of tasks into adequate subtasks. Further it is shown how the generated programs are mapped on and executed by a humanoid robot.

View PDFchevron_right
Expanding task functionality in established humanoid robots
Victor Ng-Thow-Hing

Proceedings of IEEE- …, 2007

Many humanoid robots like ASIMO are built to potentially perform more than one type of task. However, the need to maintain a consistent physical appearance of the robot restricts the installation of additional sensors or appendages that would alter its visual identity. Limited battery power for free- moving locomotive robots places temporal and spacial complexity limits on the algorithms we can deploy on the robot. With these conditions in mind, we have developed a distributed robot architecture that combines onboard functionality with external system modules to perform tasks involving interaction with the environment. An information model called the Cognitive Maporganizes output produced by multiple perceptual modules and presents a common abstraction interface for other modules to access the information. For the planning and generation of motion on the robot, the Task Matrix embodies a task abstraction model that maps a high level task description into its primitive motions realizable on the robot. Our architecture supports different control paradigms and information models that can be tailored for specific tasks. We demonstrate environmental tasks we implemented with our system, such as pointing at moving objects and pushing an object around a table in simulation and on the actual ASIMO robot

View PDFchevron_right
TDM: A software framework for elegant and rapid development of autonomous behaviors for humanoid robots
Vincent Berenz

2011

Through the use of module based software solutions, programming humanoid robots became simple in the sense that detailed knowledge of the underlying software and hardware layers became largely unnecessary. In this paper we argue that the current situation, while being satisfactory for most users, requires improvement for facing situations in which delivery of a complex autonomous behavior is part of the final target. In such case, implementing a dedicated behavior control architecture remains a complex task. In this paper we propose a behavior oriented software framework to be added above the existing modular architecture. This framework is based on centralized integration of sensory data, schematic representation of objects, resource management and intrinsic motivation. It supports code organization, favors code reuse and allows rapid obtention of behaviors that can be easiliy modified or extended. A version of the framework for Aldebaran Nao was developed and tested.

View PDFchevron_right
A Worked-Out Experience in Programming Humanoid Robots via the Kinetography Laban
Paolo Salaris

Springer Tracts in Advanced Robotics, 2015

This chapter discusses the possibility of using Laban notation to program humanoid robots. Laban notation documents human movements by a sequence of symbols that express movements as defined in the physical space. We show, by reasoning around the simple action of "taking a ball", the flexibility of the notation that is able to describe an action with different level of details, depending on the final objective of the notation. These characteristics make Laban notation suitable as a high level language and as a motion segmentation tool for humanoid robot programming and control. The main problem in robotics is to express actions that are defined and operate in the physical space in terms of robot motions that originate in the robot motor control space. This is the fundamental robotics issue of inversion. We will first show how symbols used by Laban to describe human gestures can be translated in terms of actions for the robot by using a framework called Stack of Tasks. We will then report on an experience tending to implement on a simulated humanoid platform the notation score of a "Tutting Dance" executed by a dancer. Once the whole movement has been implemented on the robot, it has been again notated by using Laban notation. The comparison between both scores shows that robot's movements are slightly different from dancer's ones. We then discuss about plausible origins of these differences.

View PDFchevron_right

Related topics

  • Intelligent and Expert Systems
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved