Control and navigation of an outdoor AGV using fuzzy reasoning

We describe the development of a fuzzy navigator to perform the local navigation and obstacle avoidance tasks for an outdoor AGV. The hybrid architecture incorporates a high level 'model-and-plan' layer, and a low-level 'sense-and-execute' layer. The local navigation module is implemented using a behavioural approach. That is, each of the complex local navigational tasks that need to be carried out is analysed in terms of primitive behaviours and expressed as an aggregation of such behaviours. A fuzzy logic approach to behaviour synthesis and integration has been adopted. The fuzzy behaviours are synthesised based on appropriately fused sensory data received from the complementary sensor devices, especially, proximity sensors and laser scanner. A simulator developed using Matlab is introduced and it is capable of monitoring the vehicle performance through travelling profile, heading angles, change in steering commands, as well as the logic patterns of the proximity sensors. Method to associate these logic patterns to linguistic variables is discussed. Lastly, enhancements to the simulator is presented.