🚀 go-pugleaf

              Special University PhD Oral Examination


        *********************************************************
          Experimental Integration of Planning in a Distributed
                           Robotic System


                  Gerardo Pardo-Castellote
            Department of Electrical Engineering

                  Tuesday, August 9, 1994. 
		   3:45 pm in Durand 450
 
         ********************************************************



                          ABSTRACT
                          --------

This talk examines several new concepts developed and lessons learned
while attacking the challenging problem of developing an intelligent,
dual-arm robotic workcell.  The system combines a high-level graphical
user interface, an on-line motion planner, real-time vision, and an
on-line simulator to control a dual-arm robotic system.

The graphical user interface provides high-level user direction.  The
motion planner generates complete on-line plans to carry out these
directives, specifying both single and dual-armed motion and
manipulation.  Combined with the robot control and real-time vision,
the system is capable of performing object acquisition from a moving
conveyor belt as well as reacting to environmental changes on-line.

The talk will feature four main research contributions: 


1. System design and interfaces.  The system is based on a novel
  "interface-first" design technique.  This technique structures the
  complex command and data flow as combinations of three fundamental
  robotic interface components: world-model, robot-command, and
  task-level direction.

2. Network architecture.  Complex distributed robotic systems
  require very complex data flow.  A powerful new subscription-based,
  network-data-sharing system, was developed (and is being
  commercialized) that enables transparent connectivity.

3. Path time-parameterization.  A fast (linear-time,
  proximate-optimal) solution to the fundamental problem of
  time-parameterization of robot paths will be presented.

4. Implementation. The architecture and design of the hierarchical
  control system for the experimental dual-arm assembly workcell will
  be presented.


The talk concludes with a videotape of the robotic workcell in action.
The videotape shows the system performing complex, multi-step tasks
autonomously, including dual-arm object acquisitions from a moving
conveyor, object motion among obstacles, re-grasps, and hand-overs.
All these tasks occur under task-level human supervision.