top of page
Search

TARGET DETECTION BY MOBILE AUTONOMOUS ROBOTS EQUIPPED WITH VARIETY OF SENSORS

Talk by BG (ret.) Barouch Matzliach on the annual Industrial Engineering & Management conference on global innovation, Tel-Aviv, April 1st.



Abstract

In recent years, the modern battlefield is characterized by guerrilla warfare based on enemy with low signature, hidden within civilian population. At the same time, the modern combat weapons (air and land systems) are equipped with a variety of sensors such as radars, optic sensors, “sigint” sensors, thermal sensors etc. The sensors are installed on search agents such as mobile autonomous robots, vehicles or drones. These sensors obtain information about unusual events (firing, movements etc.). However, the noisy environment creates a large number of false alarm events. The information which is collected over the time by the variety of sensors is significant. It allows filtering the false alarm events and detects the real targets, automatically in a short time.

These capabilities are achieved by advanced models, using various ‘Bayesian’ approaches. These models include real-time updating of the location probabilities of the targets within the search area; integrating the various sensors’ outputs to generate a central ‘location-probability map’, and integrating various agents’ information, under different information-sharing policies. This research deals with the construction of autonomous targets’ detection system within large search areas. The system is based on search algorithms and on decision- making methods using artificial intelligence and machine learning tools.

Several algorithms are developed and analyzed, including the following control policies:

• ‘Global View’ – Updated central global probability map, achieved by real time updating of the sensors’ inputs, including probabilities integration between the sensors and integration between the agents’ local information set.

• ‘Agent View’ – Local probability map for each agent, obtained by real-time updating scheme of the sensors probabilities, and probabilities integration among the various sensors, but without data-sharing between the agents.

• ‘Selected Data Sharing’ – Includes enhanced local agent probabilities map obtained by sharing a selected set of high-quality data among the sensors.

• ‘Dynamic Sensors Power’ – A scheme that takes into account the total energy consumption reduction, achieved by real time updating of the sensors’ power. Currently, a software simulation is being developed to analyze the different policies and initial results, which compare the different algorithms, are studied.


Bio. Brigadier General (ret.) Barouch Matzliach is a PhD student at the industrial engineering department in Tel-Aviv University, in the Laboratory of Machine learning, AI and Business Data Analytics (LAMBDA). He holds a B.Sc. in mechanical engineering and M.Sc. in industrial engineering, both in Tel-Aviv University. He has served in the IDF for 30 years. During his service he specialized in developing and manufacturing land combat systems. Matzliach, the chief engineer of Merkava tank project, received the Israel Defense Award for developing ‘Meil Ruach’ – an active protection system of combat vehicles. In 2013, he was promoted to Brigadier General Rank and served for five years, as the head of the Merkava & Armored Vehicles program in the Ministry of Defense.


3 views0 comments

Comentarios


bottom of page