Transcript יכולות נבונות Telerobotic Features
Control Agents making Robotics a reality
Dr. Reuven Granot
Faculty of Science and Scientific Education University of Haifa, Israel Visiting scholar at UBC/Mining Eng. Dept.
September 7, 2005 1
Outline
The need for unmanned systems.
Why tele-robotics?
A new layer of software should be developed in order to support application users in fields of robotics and other semi or autonomous systems to develop more effectively their specific applications. follow upcoming standards like JAUS and CORBA. follow the Distributed and Object Oriented paradigm, but be more than an object or an expert system by being reactive, autonomous and proactive.
transparently take care of inter agent communication and other basic tasks a control agent needs. - a control agent is performing some control task while communicating with other agents or humans as needed. We, at University of Haifa, Israel, are suggesting to collaboratively developing the needed infrastructure for Human Supervised Autonomous Control Agents. A relevant application of semi-autonomous bulldozer.
2
The Need of Unmanned Systems
Is well recognized to perform tasks that are:
• •
DDD
– Dull – Dirty – Dangerous
Illustration from NASA and ORNL publication
Distant
– at different scale
Robot colony on a site preparation task for a PV tent on Mars .
– Macro: space, – Micro: telesurgery, micro and nano devices September 7, 2005 3
Remote Controlled vehicles in combat environment
RC is still preferred by designers o Simple, but not practical for combat or other very demanding environment because the human operator: is very much dependent upon the controlled process needs long readjustment time to switch between the controlled and the local environment.
The state of the art of the current technology has not yet solved the problem of controlling
complex tasks
autonomously in unexpected contingent environments .
o dealing with unexpected contingent events remains to be a major problem of robotics. Consequence: A human operator should be able to interfere: remains at least in the supervisory loop.
September 7, 2005 4
The needed control metaphor:
Human Supervised Autonomous
All these applications require an effective interface between the machine and a human in charge of operating/ commanding the machine.
We are suggesting to perform Human Supervised Autonomous Control, which is known as tele-robotics.
That be done using the software agent technology
September 7, 2005 5
The Tele-robotics paradigm Telerobotics
is a form of
Supervised Autonomous Control.
A machine can be distantly operated by: •
continuous control
: the HO is responsible to continuously supply the robot all the needed control commands.
• a
coherent cooperation
between man and machine, which is known to be
a hard task
.
Supervision and intervention by a human would provide the advantages of on-line fault correction and debugging , and would relax the amount of structure needed in the environment, since a human supervisor could anticipate and account for many unexpected situations .
September 7, 2005 6
The spectrum of control modes.
A telerobot can use: • • •
traded control:
control is or operator or at at the autonomous sub system.
shared control
: the instructions given by HO and by the robot are combined .
strict supervisory control
: the HO instructs the robot, then observes its autonomous actions.
Solid line= major loops are closed through computer, minor loops through human.
September 7, 2005 7
Human Robot Interaction
•
In supervised autonomously controlled equipment, a human operator generates tasks , and a computer autonomously closes some of the controlled loops
.
• Control bandwidth – Robot SW: high – Human response: slow •
Human Operator is expected to
Control several machines/ equipment/ systems be capable to deal with other duties (like a combat environment requests) in somehow relaxed mode of operation.
Make the machine an agent in human operator’s service .
September 7, 2005 8
Software Infrastructure
• Architecture
– Distributed – Objects or some more sophisticated entities?
– Communication
• Development Environment
– Language – Tools – Reusable units September 7, 2005 9
What is a Robot Architecture?
• There are many different ways in which a robot control program can be put together. In order to program a robot in a structured and principled fashion , we use an appropriate robot control architecture. 10 September 7, 2005
Robot Architecture
• A
control architecture
provides
a set of principles
for
organizing a control system
. – It provides structure and constraints which aid the designer in producing a well-behaved controller. • To be successful a system designer has to decide how (in what order? with what priority?) does he put together multiple feedback controllers in a principled fashion and how to
scale up
control to more complex robots, which generally have to deal with many behaviors at once. –
How would you put multiple feedback controllers together?
–
How would you decide which one to use when and for how long and in what priority relative to the others?
September 7, 2005 11
Misconceptions.
1. Programming languages are implementation tools and not architectures .
2. The issue of fundamental power or expressiveness of a robot control architecture : claims have been made about one control architecture being able to
compute
fundamentally more than another. This
cannot be true
if we understand that all are grounded in Turing-complete programming languages. However, the above
is not to say that all architectures are the same
. On the contrary,
architectures impose strong constraints on how robot programs are structured , and the resulting control software ends up looking very different.
12 September 7, 2005
Robot Architecture Major Classes/Categories
• • • • Intuitively, this means that there are infinitely many ways to structure a robot program, but they all fall into one of
major classes/categories of control:
Deliberative Control
: Think hard, act later. ─ SPA, serial, complete each step first – then proceed
Reactive Control
: Don’t think, (re)act. ─ Direct connection between perception to action, no memory, no planning.
Hybrid Control
: Think and act independently, in parallel. ─ Deliberative and Reactive modules run independently at different time scales
Behavior-Based Control
: Think the way you act. – Distributed by behavioral task decomposition – Each behavior has its restricted planning and execution capabilities September 7, 2005 13
The Choice of the Control Architecture
•
When it comes to more complex robots
, i.e., robots that have to deal with complex environments and complex tasks , the control architecture becomes very important.
• The different
properties of an environment
that will impact the robot's controller (and therefore the choice of control
architecture
): – noisy, – speed/response time of sensors and effectors – total/partial hidden state/ observable – discrete v. continuous state ; static v. dynamic ... • Similarly, the properties of the robot's task impact the choice of the control architecture.
The task requirements can constrain the architecture choice
. September 7, 2005 14
Parallel Processing Paradigm.
•
• As robot control is engaged to deal
with more complex problems
,
centralized
supervisory
architectures encounter barriers to real time performance
caused by computational complexity coupled with
insufficient computing power and sensor resources.
– Despite startling advances in hardware and software technology and similarly surprising cost reductions, these fundamental
barriers remain unchanged
.
The parallel-processing paradigm
only technology to challenge this fact.
may be the September 7, 2005 15
Asynchronous and Synchronous processes
• The other leading architectural trend is typified by a mixture of asynchronous and synchronous control and data flow. –
Asynchronous
processes are characterized as loosely coupled and event-driven without strict execution deadlines. –
Synchronous
processes, in contrast, are tightly coupled , utilize a common clock and demand hard real time execution .
September 7, 2005 16
Time Scale.
Time-scale
is an important way of distinguishing control architectures.
•
Reactive systems
respond to the real-time requirements of the environment, • while
deliberative system
look ahead (plan) and thus work on a longer time-scale . •
Hybrid systems
must combine the two time-scales in an effective way , usually requiring a middle layer; consequently they are often called
three-layer
architectures
. • Finally,
behavior-based systems
attempt to bring the different time-scales closer together by distributing slower computation over concurrent behavior modules. September 7, 2005 19
Representation
• Another key distinguishing feature between architectures is
representation
of the world/environment, also called
world modeling.
• Some tasks and architectures involve storing information about the environment
internally
, in the form of an
internal representation
of the environment. • For example , while exploring a maze, a robot may want to remember a sequence of moves it has made (e.g., "left, left, right, straight, right, left"), so it can back-track and find its way. Thus, the robot is constructing a representation of its path through the maze. The robot can also build a
map
of the maze, by drawing it using exact lengths of corridors and distances between walls , etc. .
This is also a representation of its environment, a model of the world . • If two robots are working together, and one is much slower than the other, if the fast robot remembers/learns that the other is always slower, that is also a type of a model of the world, in this case, a model of the other robot.
20
Different World Models.
• There are numerous aspects of the world that a robot can represent/model, and numerous ways in which it can do it, including:
* spatial
metric or topological: maps, navigable spaces, structures
* objects
instances of detectable things in the world
* actions * self/ego * intentional * symbolic
September 7, 2005 outcomes of specific actions on the self and environment stored proprioception: sensing internal state, self- limitations, etc.
goals, intended actions, plans abstract encoding of state/information 21
• Regarding the architecture of robotic systems, we discussed so far two key issues distinguishing architectures, as had to do with –
time-scale
(reactive) and
–
looking ahead (deliberative)
.
• A third key issue we need to consider is
modularity
, i.e., the way in which the architecture decomposes into components.
24 September 7, 2005
What is a behavior?
• An individual behavior is
a stimulus/ response pair
for a
given environmental setting
that is modulated by attention and determined by intention .
Attention:
prioritizes tasks and focuses sensory resources and is determined by the current environmental context
.
Intention:
determines which set of behaviors should be active based on the robotic agent’s internal goals and objectives.
Apparent or emergent behavior:
the global behavior of the robot as a consequence of the interaction of the active individual behaviors.
•
Behaviors serve as the basic building blocks for robotic actions.
25
What are Behaviors?
• typically has the following properties: – – – –
are feedback controllers achieve specific tasks /goals are typically executed in can store state (closed-loop, extended in time parallel/concurrently ) and be used to construct world models/ representation
– – –
can directly connect sensors and effectors are typically higher-level than actions can also take inputs from other behaviors and send outputs to other behaviors
• when assembled into distributed representations , behaviors can be used to look ahead but at a time-scale comparable with the rest of the behavior-based system .
26
Behaviors and Modularity
Behavior-based systems are not limited in the ways that reactive systems are . As a result, behavior-based systems have the following key properties:
1) the ability to react in real-time . 2) the ability to use representations to generate efficient (not only reactive) behavior. 3) the ability to use a uniform structure and representation throughout the system (so no intermediate layer ).
27 September 7, 2005
Assembling Behaviors.
• • Systems are constructed from multiple behaviors .
Emergent behavior
“whole”) capability where the sum is considerably greater than its parts.
implies a holistic (attention to the • • Emergence is “the appearance of novel properties in whole systems”.
• Intelligence emerges from the interaction of the components of the system.
Coordination functions
are algorithms used to assemble behaviors.
– Conflict can result when two or more behaviors are active, each with its own independent response.
September 7, 2005 28
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; –
pro-activeness
: agents do not simply act in response to their environment; they are able to exhibit goal-directed behavior by
taking the initiative
. 29 September 7, 2005
Agents and Behaviors
• Behavior is defined as the way how we/people observe the system/robot acts/behaves.
• The robot system is NOT aware of what we know about it.
– What makes the system act as we observe is its software.
• Behaviors are implemented by agents .
30 September 7, 2005
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 7, 2005 31
Agents are not Objects
•
Agents may act inside the robot software to implement behaviors:
Feedback controllers
Control subassemblies
Perform Local Goals/ tasks
• Differ from
Objects
– – – –
autonomous, reactive and pro-active encapsulate some state, are more than expert systems are situated in their environment and take action instead of just advising to do so.
32 September 7, 2005
Agent control loop
• agent starts in some initial
internal state
i 0
.
• observes its environment
state
e
, and generates a
percept
see(e)
.
• internal state of the agent is then updated via
next
function, becoming
next_(i 0
,
see(e))
.
• the action selected by agent is action (
next(i0
,
see(e))
)) This action is then performed .
• Goto (2).
September 7, 2005 33
Human Operator
• •
Monitors the activities agents
.
and the performance of the assembly of Responsible for the completion of the major task (global goal)
–
may interfere by sending
• • •
change orders .
emergent (executed immediately, without considering any possibility to return to achieve the goal/in the shortest possible way) “as is ordered” or normal
– –
checked by the interface agent which negotiates execution with other agents in order to optimize execution performance
–
Conflict resolution algorithm
•
defined as default , or
•
defined by the human operator
•
suggested to algorithm.
in its change order or the operator by a simplified decision support
36 September 7, 2005
D9 Bulldozer
• A good starting project :
–
earthmoving tasks are loosely coupled with locomotion tasks.
–
earthmoving tasks are not really simple and
–
locomotion tasks are not really complicated.
•
The operator has very limited information about his surroundings or machine performance.
September 7, 2005 38
JAUS
Platoon Commander Squad Commander Squad Commander Squad Commander Squad Commander Vehicle Commander Vehicle Commander
From M. W. Torrie
Vehicle Commander Vehicle Commander
A hierarchy of Commanders different resolution in space and time
RCS
Embeds a hierarchy of agents within a hierarchy of organizational units: Intelligent Nodes or
RCS_Nodes
.
September 7, 2005 39
RCS_Node
Perceived Objects & Events Value Judgment Commanded Task (Goal) Update Sensory Processing Predicted Input Observed Input World Modeling Knowledge Database Plan Behavior Generation State Commanded Actions (Subgoals) September 7, 2005 41
Agents in Behavior Generation hierarchy
• Tasks are decomposed and assigned in a command chain.
• Actions are coordinated • Resources are allocated as plan approved.
• Tasks achievements are monitored (VJ) • Execution in parallel September 7, 2005 43
Small Size Scaled Model
• The implementation differs by mechanical, perceptual and control elements from the full scale application. • It still may help to identify
unusual situations which
the software agent must be capable to deal with. • Full scale machines may be tested only at field ranges, which are
expensive
.
time consuming
and very • A small scale model
may be tested in office
environment, enabling the software developers to
shorten test cycles
by orders of magnitude.
45 September 7, 2005
Expected situations
• •
The bulldozer moves forward placing the blade too low
–
The human decides: the blade should be placed higher
Command issued: “lift the blade”.
experiencing too much power to enable earth moving forward
–
the human operator would prefer to withdraw attack the soil from a new position behind and
– –
the human operator is distant the bulldozer is “close” to the ditch ;
>
a better practice would be to first complete the maneuver .
Bulldozer using Fuzzy Control decides to perform the better practice and withdraws only after the maneuver is completed .
September 7, 2005 46
The Model
September 7, 2005 47
autonomous-bulldozer\robot.WMV
4 min autonomous-bulldozer\robot.mpg
3 min September 7, 2005 48
September 7, 2005 49
September 7, 2005 50