24-01-2011, 05:19 PM
Introduction:
Our approach is characterized with a strong inclination for biological inspiration in which examples in nature — social insects in particular — are used as a way of designing strategies for controlling mobile robots. This approach has been successfully applied to the study of task, namely, Ant’s algorithms used in computer networks for routing data between Routers.
This phenomenon found in ants to derive the necessary behaviors for accomplishing this task. We study a species of ant known to possess this capability.
“bio-Computing” is a way “to understand how the relation of brain, body and environment produce behavior, to clarify the essential problems posed, and to devise and test hypotheses under realistic conditions” social insects were capable of successfully navigating and acting in the face of uncertain and unpredictable environments. It was reasoned that if a single robot required complex systems and techniques in order to perform in a reliable manner, then perhaps intelligent systems could be designed with many “simpler” robots using a minimalist approach to sensing and actuation; where group behavior is an emergent property and control is decentralized. Could system reliability be achieved by trading complexity for redundancy coupled with ”randomness” used to explore possible solution paths, which are often traits found in social insect colonies? May be, biology can teach us a thing or two about engineering swarms of simple interacting robots, and the theoretical foundations developed to model and explain these behaviors found in insect colonies can be used to underpin a more rigorous approach to collective robot design. Nature has already demonstrated the feasibility of this approach by way of the social insects.
Artificial intelligence is one of the most complicated tasks in robotics.
Without considering the facts of electronics, mechanical, and instrumentation people are trying to make use of the optimal solutions from AI.
But unfortunately the solutions may not be the optimal in implementation in real time due to lack of co-ordination and leaving behind the nature’s make.
Traditional Artificial Intelligence:
The traditional artificial intelligence which is followed by the world today is not producing 100% fruit full results and it is narrowing the thinking methodology of developing the artificial intelligence for a given particular task in real time environment.
The traditional artificial intelligences calculates the position and controls a mobile robot by giving the directions using 2D calculations it will decided by taking feed back from electronic systems like COMPASS MODULE, GPRS, GPS, GIROSCOPE etc. which makes it more complex and costly. By using all such devices it makes the product much costlier.
For example:
“Roomba-Discovery” displayed at IIT Bombay by iRobot's chief technology officer, Professor Rodney rooks IROBOT. His given statement “Intelligent robots might fail some times”. His commercial robot failed in returning back to its starting position due to some environmental problems.
The “Roomba discovery” is intelligent cleaner robot. Which is attached to a charger at its starting position, its task is to start from its charging position and clean the environment and return back to its position. He used HI-FI systems for position identification and control of his mobile robot “Roomba discovery” and best algorithm is implemented which is much costlier for that task and it has failed to identify its starting position. This shows that in real time environment by using the traditional artificial intelligence it is hard to develop 100% efficient mobile robot, with its tighter coupling between sensing and action, behavior may allow robots to deal with the uncertainty presented by real unstructured environments in which the robots perform their tasks. After all, social insects were capable of successfully navigating and acting in the face of uncertain and unpredictable environments.
“bio-robotics” is a way “to understand how the relation of brain, body and environment produce behavior, to clarify the essential problems posed, and to devise and test hypotheses under realistic conditions”.
Reactive behavior, which results in the robot’s immediate response demanded by real-time environments, lacks the goal-directed component thought to be a necessary component of intelligent autonomous systems.
ODOMETRY AND OTHER DEAD-RECKONING METHODS
Odometry is the most widely used navigation method for mobile robot positioning. It is well known that odometry provides good short-term accuracy, is inexpensive, and allows very high sampling rates. However, the fundamental idea of odometry is the integration of incremental motion information over time, which leads inevitably to the accumulation of errors. Particularly, the accumulation of orientation errors will cause large position errors which increase proportionally with the distance traveled by the robot. Despite these limitations, most researchers agree that odometry is an important part of a robot navigation system and that navigation tasks will be simplified if odometric accuracy can be improved. Odometry is used in almost all mobile robots, for various reasons: & Odometry data can be fused with absolute position measurements to provide better and more reliable position estimation [Cox, 1991; Hollingum, 1991; Byrne et al., 1992; Chenavier and Crowley, 1992; Evans, 1994]. & Odometry can be used in between absolute position updates with landmarks. Given a required positioning accuracy, increased accuracy in odometry allows for less frequent absolute position updates. As a result, fewer landmarks are needed for a given travel distance. & Many mapping and landmark matching algorithms (for example: [Gonzalez et al., 1992; Chenavier and Crowley, 1992]) assume that the robot can maintain its position well enough to allow the robot to look for landmarks in a limited area and to match features in that limited area to achieve short processing time and to improve matching correctness [Cox, 1991]. & In some cases, odometry is the only navigation information available; for example: when no external reference is available, when circumstances preclude the placing or selection of landmarks in the environment, or when another sensor subsystem fails to provide usable data.
How useful is biological inspiration
Colonies of social insects share many system-level characteristics we desire from collective robot systems: simple agents, decentralized control, robustness through mass effect, redundancy, flexibility and autonomy. The many rich examples of colony level collective behavior provided by biologists provide a wealth of data with which to inspire and to provide an underpinning for initial robotic designs. Although useful as a starting point in MRS design, biological inspiration has its limits and engineering models can and should be improved from their biomimetic beginnings.
Bio inspiration from a cockroach:
We designed the robot by observing the insect behavior of cockroach; the basic function of cockroach is scavenger duty in kitchen at night. Our designed robot works on the intelligence of cockroach.
The robot performs its cleaning tasks when we go to bed at night and it cleans its environment randomly like a cockroach searches for its food and if we switch ON any light it follows back to its home just by identifying the wall nearest to it and follow the wall till it reaches a hole, similarly intelligence is applied in our robot. The robot does not use any HI-FI systems, complex algorithm and internal navigation system but the bio inspired intelligence of cockroach and the task is completed at minimum cost.
More
