Humans create Robots as an extension in the development in technology. This creates a ladder to reach higher in the industrial engineering that handles materials, tools or specialised devices to move one place to other through various methodology. Now a days Robot replaces human operators and its structure and control architectures varies according to the applications.
Robot may be a
1.Fixed sequence Robot – performs the fixed sequence of successive stages of a task
2.Variable-Sequence Robot – task sequences are easily modifiable.
3.Playback Robot – A human performs the task manually by leading the Robot
4.Numerical Control Robot – works based on movement program given by operator
5.Intelligent Robot – A robot with the means to understand its environment, has got the ability to successfully complete a task despite the changes in the environment.
General Robot structure is composed of
- Manipulator or rover : Main body of Robot (Links, joints, other structural elements of the system)
- End effector: the part that is connected to the last joint hand
- Actuators : Muscles of the manipulators (Servo motors, stepper motors, pneumatic and hydraulic cylinder ..etc)
- Sensors: To collect the information about the internal state of robot or to communicate to the outside environment.
- For example: vision system, touch and tactile sensors etc which help to communicate with the environment.
- Controller : The controller receives data from the computer, controls the motions of the actuator and coordinates these motions with the sensory feedback information.
DIFFERENT TYPES OF CONTROL ARCHITECTURES
1.Deliberative control architecture
In a deliberative control architecture the robot first plans a solution for the task by reasoning about the outcome of its actions and then executes it. Control process goes through a sequence of sensing, model update, and planning.
Reasons about contingencies and computes solutions to the given task and provides goal-directed strategies
Solutions tend to be fragile in the presence of uncertainty and requires frequent re-planning. Reacts slowly to changes and unexpected occurrences.
2.Behavior based control architecture
In a behavior-based control architecture the robot’s actions are determined by a set of parallel, reactive behaviors which map sensory input and state to actions.
Reactive, behavior-based control combines relatively simple behaviors, each of which achieves a particular subtask, to achieve the overall task. Robot can react fast to changes. But the system does not depend on complete knowledge of the environment and the Emergent behavior (resulting from combining initial behaviors) can make it difficult to predict exact behavior which makes it difficult to assure that the overall task is achieved.
Subsumption architecture is one of the earliest behavior-based architectures, in which behaviors are arranged in a strict priority order where higher priority behaviors subsume lower priority ones as long as they are not inhibited.
Reacts fast to changes and does not rely on accurate models, no need for replanning.
Difficult to anticipate what effect combinations of behaviors will have and to construct the strategies that will achieve complex, novel tasks. Also requires redesign of control system for new tasks
3.Hybrid control architecture
- Hybrid architectures combine reactive control with abstract task planning
- Abstract task planning layer makes deliberative decisions and plans goal directed policies
- Reactive behavior layer provides reactive actions and handles sensors and actuators.
Permits goal-based strategies and ensures fast reactions to unexpected changes. So reduces complexity of planning.
Choice of behaviors limits range of possible tasks and the behavior interactions have to be well modeled to be able to form plans.