Browsing Computer Science by Subjects
Now showing items 1-2 of 2
Evolutionary Robot Swarm Cooperative RetrievalIn nature bees and leaf-cutter ants communicate to improve cooperation during food retrieval. This research aims to model communication in a swarm of auton-omous robots. When food is identified robot communication is emitted within a limited range. Other robots within the range receive the communication and learn of the location and size of the food source. The simulation revealed that commu-nication improved the rate of cooperative food retrieval tasks. However a counter-productive chain reaction can occur when robots repeat communications from other robots causing cooperation errors. This can lead to a large number of robots travelling towards the same food source at the same time. The food becomes de-pleted, before some robots have arrived. Several robots continue to communicate food presence, before arriving at the food source to find it gone. Nature-inspired communication can enhance swarm behaviour without requiring a central control-ler and may be useful in autonomous drones or vehicles.
Multi-Agent Reinforcement Learning for Swarm Retrieval with Evolving Neural NetworkThis research investigates methods for evolving swarm communica-tion in a sim-ulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn phero-mone communication autonomously. Building on previous literature on phero-mone communication, this research applies evolution to adjust the topology and weights of an artificial neural network (ANN) which controls the ant behaviour. Compar-ison of performance is made between a hard-coded benchmark algorithm (BM1), a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was suc-cessfully evolved to achieve the task objective, to collect food and return it to a location.