On Probabilistic Strategies for Robot Tasks

Abstract

Robots must act purposefully and successfully in an uncertain world. Sensory information is inaccurate or noisy, actions may have a range of effects, and the robot's environment is only partially and imprecisely modelled. This thesis introduces active randomization by a robot, both in selecting actions to execute and in focusing on sensory information to interpret, as a basic tool for overcoming uncertainty. An example of randomization is given by the strategy of shaking a bin containing a part in order to orient the part in a desired stable state with some high probability. Another example consists of first using reliable sensory information to bring two parts close together, then relying on short random motions to actually mate the two parts, one the part motions lie below the available sensing resolution. Further examples include tapping parts that are tightly wedged, twirling gears before trying to mesh them, and vibrating parts to facilitate a mating operation. Randomization is seen as a primitive strategy that arises naturally in a solution of manipulation tasks. Randomization is as essential to the solution of tasks as are sensing mechanics. An understanding of the way that randomization can facilitate task solutions is integral to the development of the theory of manipulation. Such a theory should try to explain the relationship between solvable tasks and repertoires of actions, with the aim of creating autonomous systems capable of existing in an uncertain world. (Author) (KR)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1990
Accession Number
ADA225714

Entities

People

  • Michael A. Erdmann

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Autonomous Systems
  • Computational Science
  • Computer Science
  • Control Systems
  • Differential Equations
  • Electrical Engineering
  • Geometry
  • Jet Propulsion
  • Mathematical Filters
  • Mechanical Engineering
  • Motion Planning
  • Probabilistic Models
  • Random Variables
  • Robot Navigation
  • Stochastic Processes
  • Two Dimensional

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Distributed Systems and Data Platform Development
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • Autonomy