| Autonomous robots are robots
which can perform desired tasks in unstructured environments without continuous human guidance. Many kinds of robots are
autonomous to some degree. Different robots can be autonomous in different ways. A high degree of autonomy is particularly
desirable in fields such as space exploration, where
communication delays and interruptions are unavoidable.
Some modern factory robots are "autonomous" within the strict confines
of their direct environment. Maybe not every degree of freedom exists in their surrounding environment but the work place of the
factory robot is challenging and can often be unpredictable or even chaotic. The exact orientation and position of the next
object of work and (in the more advanced factories) even the type of object and the required task must be determined. This can
vary unpredicatably (at least from the robot's point of view). From the start, factory robots have not been subject to continuous
human guidance or necessarily any human guidance at all.
One important area of robotics research is to enable the robot to cope with its environment whether this be on land,
underwater, in the air, underground or in space.
A fully autonomous robot in the real world has the ability to:
- Gain information about the environment.
- Work for months or years without human intervention.
- Travel from point A to point B, without human navigation assistance.
- Avoid situations that are harmful to people, property or itself
- Repair itself without outside assistance.
A robot may also be able to learn autonomously. Autonomous learning includes the ability to:
- Learn or gain new capabilities without outside assistance.
- Adjust strategies based on the surroundings.
- Adapt to surroundings without outside assistance.
Autonomous robots still require regular maintenance, as do other machines.
Examples of progress towards commercial autonomous robotics
SELF-MAINTENANCE: The first requirement for physical autonomy is the ability for a robot to take care of itself. The
most basic self-maintenance is to find a docking station and recharge itself or swap its batteries as needed. Once this is
accomplished, social robots can perform and interact without additional autonomous behaviors. Toy robots, for instance, are
increasingly sophisticated socially: the most advanced example is Sony's Aibo range
of robotic toy dogs, which are capable of self-docking. Honda performing robots (http://www.newscientist.com/news/news.jsp?id=ns99994845) are now also available for rent, at
costs "similar to those of hiring a rock star."
Self maintenance is based on "proprioception", or sensing one's own status. Most robots have proprioceptive heat monitoring.
Some robots can now sense whether they are level, wet, stuck or otherwise in jeopardy. Proprioception was the focus of the DARPA
Proceptor project, including participants from CMU, SRI, SAIC, ActivMedia Robotics and many other research groups trying to
identify whether robotic vehicles were encountering a tree or lake they must circumnavigate vs. a bush or puddle they might pass
over. Increased proprioception will be required for robots to work autonomously near people and in harsh environments.
TASK PERFORMANCE: The next step in autonomous behavior is to actually perform a physical task. A new area showing
commercial promise is domestic robots, with a flood of small vacuuming robots beginning with iRobot and Electrolux in 2002. While
the level of intelligence is not high in these systems, they are capable of lightly cleaning floors, primarily using bump sensing
to tell them to change direction. Similarly, the Friendly Robotics lawn mower uses an RF perimeter wire, like a dog fence, as a
virtual version of bump sensing. However, this mower uses sophisticated tiling algorithms, rather than random motion, to
calculate the most effective pattern for cutting the entire lawn.
The next level of autonomous task performance requires a robot to perform conditional tasks. For instance, MobileRobots'
security robot can be programmed to detect intruders and respond in a particular way depending upon where the intruder is.
INDOOR POSITION SENSING AND NAVIGATION: For a robot to associate behaviors with a place requires it to know where it is
and to be able to navigate point-to-point. Such navigation began with wire-guidance in the 1970's and progressed in the early
2000's to beacon-based triangulation. Current commercial robots autonomously navigate based on sensing natural features. The
first commercial robots to achieve this were Pyxus' HelpMate hospital robot and the CyberMotion guard robot, both designed by
robotics pioneers in the 1980's. These robots originally used manually created CAD floor plans, sonar sensing and wall-following
variations to navigate buildings. The next generation, such as MobileRobots' PatrolBot and autonomous wheelchair, both introduced
in 2004, have the ability to create their own laser-based maps of a building and to navigate open areas as well as corridors.
Their control system changes its path on-the-fly if something blocks the way. Add the ability to control elevators and electronic
doors, as SwissLog's and many other indoor bots do, and now robots can now freely navigate entire buildings. Autonomous
stair-climbing, however, has not yet been achieved by any commercial bot.
As these indoor techniques continue to develop, vacuuming robots will not be limited to a single room, but will be able to
traverse at least a single floor on their own. Security robots will be able to cooperatively surround intruders and cut off
exits. These advances also bring concommitant protections: robots' internal maps typically permit "forbidden areas" to be defined
to prevent robots from autonomously entering certain regions.
OUTDOOR AUTONOMOUS POSITION-SENSING AND NAVIGATION: Outdoor autonomy is most easily achieved in the air, since
obstacles are rare. Cruise missiles are rather dangerous highly
autonomous robots. Pilotless drone aircraft are increasingly used for reconnaissance. Some of these unmanned aerial vehicles (UAVs) are capable of flying their entire mission without any human interaction at all except
possibly for the landing where a person intervenes using radio remote control. But some drone aircraft are capable of a safe,
automatic landing also.
Outdoor autonomy is the most difficult for ground vehicles, due to: a) 3-dimensional terrain; b)great disparities in surface
density; c) weather exigencies and d) instability of the sensed environment.
In the US, the MDARS project, which defined and built a prototype outdoor surveillance robot in the 1990's, is now moving into
production and will be implemented in 2006. This robot can navigate semi-autonomously and detect intruders, using the MRHA
software architecture planned for all ummanned military vehicles. MobileRobots.com will be producing its first outdoor
surveillance robot for commercial use during the same year.
The Mars rovers MER-A and MER-B can find the
position of the sun and navigate their own routes to destinations on the fly by:
- mapping the surface with 3-D vision
- computing safe and unsafe areas on the surface within that field of vision
- computing optimal paths across the safe area towards the desired destination
- driving along the calculated route;
- repeating this cycle until either the destination is reached, or there is no known path to the destination
The DARPA Grand Challenge is an attempt to encourage
development of even more autonomous capabilities for ground vehicles.
External links
|
