Managing robot Development using Agent based Technologies

Managing robot
Development using Agent
based Technologies
Dr. Reuven Granot
Former Scientific Deputy
Research & Technology Unit
Directorate of Defense, Research & Development,
Israel MoD
[email protected]
September 25 2008
Two non related problems
More than a decade ago, we were already facing:
1. RT software maintenance
The way is done will soon require more work hours
than we can support.
2. International terror and Low Intensity Combat
 Armor less helpful
 Better use remote operation
3. During a sabbatical stay at UBC I realized how both
problems may have the same solution: The Agent
based Technology
September 25 2008
Software Development and
• The need to reuse software.
• Need to change functionality.
• The need to interconnect systems purchased from
– Different sources
– Developed and manufactured at different times
• Using in many cases old/ obsolete hardware (like computers
purchased years ago)
– Legacy Systems, we could not afford to replace
– Non compatible and intentionally developed with the idea
to lock customers to some manufacturers market.
September 25 2008
The need to reuse software
• Control and integration software must be less
expensive as compared with the other parts of the
integrated System.
• Improve Software Quality
– Small software units can be better managed
– As much as possible follow consumer products
• are manufactured by assembling standard available parts.
• Some intelligence is required to anticipate the avarege
(less professional) human operator needs and
– Human intervention very different than control of SW
September 25 2008
The need to interconnect
• System of Systems
• Appearance of less expensive and feature rich sensors,
actuators and controllers, and possible use of
commercial off the shelf products
– Intelligent interconnection
• There is an increasing requirement /trend to network
system together, and combine their controls and key
• Interconnected systems save time and reduce errors
• Enable understanding a larger picture.
– To be used by operators of all types
• Experts
• Reserve and less trained units
September 25 2008
Remote Operation in combat
It is still preferred by designers because of its
simplicity, but not suitable for combat
environment since the human operator:
 needs long readjustment time to switch
between the controlled and the local
is very much dependent upon the controlled
process: traditional teleoperation model: “human as
September 25 2008
Remote Vehicle Operation Problems
• loss of spatial awareness:
– disorientation, loss of context
• cognitive errors:
– “mental model” vs. what’s really
out there
• perceptual errors:
– distance judgment, display
• poor performance:
– imprecise control, obstacle
• other:
– simulator sickness, fatigue
Reduced efficiency &
latency, bandwidth,
- inflexibility: static data &
control flow, task specific
- lack of robustness: operator
variation, human resources,
These problems are due to the
traditional teleoperation
model: “human as
September 25 2008
The Technology Challenge
in Unstructured Environments.
• The state of the art of the current
technology has not yet solved the
problem of controlling complex tasks
autonomously in unexpected contingent
 Consequence: A human operator
should be able to interfere in the
supervisory loop.
The needed control metaphor:
Human Supervised Autonomous
September 25 2008
The Agent
• An agent is a computer system capable of autonomous
action in some environments.
• A general way in which the term agent is used is to denote
a hardware or software-based computer system that enjoys
the following properties:
– autonomy: agents operate without the direct intervention of
humans or others, and have some kind of control over their actions
and internal state;
– social ability: agents interact with other agents (and possibly
humans) via some kind of agent-communication language;
– reactivity: agents perceive their environment, (which may be
the physical world, a user via a graphical user interface, or a
collection of other agents), and respond in a timely fashion to
changes that occur in it.
September 25 2008
Why Software Control Agents?
• Networked subsystems are naturally distributed.
• The Controller, being responsible for achieving the
system goals, should be a subassembly of the
integrated product.
– Itself assembled from smaller, primitive parts.
• Situated in its environment
– Using sensory information and actuators
• Reactive to changes in the environment
• To maintain independence between the assembled
sub-systems, information (not data) should be
September 25
The Distributed Control
• The agent is a control subassembly.
• It may be built upon a primitive task or
composed of an assembly of subordinate
– The agent hierarchy for a specific task is preplanned or defined by the human operator as
part of the preparation for execution of the task.
– The final sequence of operation is deducted
from the hierarchy or negotiated between
agents in the hierarchy.
September 25 2008
Interface Agent
• A software entity, which is capable to represent
the human in the computer SW environment.
• It acts on behalf of the human
• Follows rules and has a well defined expected
attitude/ action.
• May be instructed on the fly and may receive
during mission updated commands from the
human operator.
We need to build agents in order to carry out the tasks,
without the need to tell the agents how to perform these tasks.
September 25 2008

similar documents