Distributed Multi-Agent Area Exploration
- Start Date: 01/01/15
- End Date: -
- Guide: Kamalakar Karlapalem
- Students Involved: Ayush Datta, Rahul Tallamraju
- Goal:To explore a distributed, cooperative path planning technique for multiple drones (∼200) to explore an unknown region (∼10,000 connected units) in the presence of obstacles.
We propose a distributed, cooperative path planning technique for multiple drones (∼200) to explore an unknown region (∼10,000 connected units) in the presence of obstacles. The map of an unknown region is dynami- cally created based on the information obtained from sen- sors and other drones. The unknown region is considered as connected region split up into hexagonal unit regions. We use two types of communication, one long range and another more frequently used short range communication. The short range communication within drones in smaller proximity helps avoiding obstacles and re-exploration of cells already explored by companion drones located in same sub- area. The long range communication helps in deciding opti- mal next sub area to be targeted by individual drones based weighted RNN (Reverse nearest neighbour). Simulation results show that two types of communication in a weighted hexagonal representation of subareas makes exploration more efficient, scalable and more resilient to communication failure and drone failure/malfunctioning.IROS paper