Saturday, February 27, 2010

Robot to detect and decontaminate landmines

Mrigank Tiwari, TNN, Feb 26, 2010, 11.02pm IST

ALLAHABAD: For war ravaged third world countries like Afghanistan and Iraq battling with casualties and serious injuries to civilians on account of undetected landmines and for security personnel taking on the naxals in Chhattisgarh, Andhra Pradesh and Jharkhand, the news would certainly be a welcome one.

The scientists from Indian Institute of Information Technology, Allahabad (IIIT-A) are on course to developing a robot which can detect landmines and decontaminate them easily. Moreover, what is heartening to note is that the prototype of the robot is already on the verge of completion which means that once tested successfully it would make way for the production of the said robot on a large-scale.

The project entitled `Designing an Intelligent Robot for Explosive Detection and Decontamination' funded by MHRD, government of India, taken up by a student, Ashish Kumar Agarwal under the guidance of Prof G C Nandi, explores the design and development of classifier based on statistical methods and soft-computing based approaches, which is capable of identifying the mines and non-mines using various clustering, classification and rules establishment algorithms as to compare the algorithm on the basis of complexity and accuracy.

Talking to TOI, Ashish said, "If we already know about the upcoming hazards, it is very easy to find the way to abolish it. My objective is to predict whether at a particular point of working area is occupied by mines or not, with some confidence parameter. The robot is being designed to move toward these predicted areas to decontaminate the mines. These mines occupied area can be known before initiation of robot movements or can be predicted dynamically, so to design an obstacle-free path for robot is another aspect beyond the domain of this module."

He added, "Designing such a classifier is a big challenge because data is not linearly separable and since it has overlapping features, it is not possible to design a classifier with 100 per cent accuracy. This project deals with PVC tubes, wood piece and copper cylinders as non-mine data in addition to data of various mines. The basic idea of the classification is based on a fact that it is safe if the non-mines data is predicted as mine, but it is not the case when we predict mines data as non-mines. So the unsupervised learning based ART algorithm divides the data into several clusters which are merged on the basis of above fact. The data may be given in image form or some tabular form having all numeric or categorised attributes.

Exuding confidence that the robot would go a long way in reducing incidents of deaths due to hidden and undetected landmines, the research coordinator, Prof G C Nandi said, "Anti-personnel landmines are a significant barrier to economic and social development in a number of countries, so we need a classification system that can differentiate a mine from metallic debris on the basis of given data. This data is generated by some highly accurate sensors."

He added, "All the eight different algorithms have been implemented to compare the results. This classifier is giving result with 80 per cent accuracy. The best result is being given by ART and genetic algorithm. Fuzzy C-mean and Gustavson Kessel is also good because of membership values for each class. This module can differentiate between the PVC tube, wood piece, brass tube, copper cylinder (non-mine data) and the mine data obtained from various sources. On the basis of this prediction, path designers develop an obstacle-free path to decontaminate these mines.

No comments: