Internal States Sensory Data Learn/Act Action Development Action Selection Action[1] Action[2] Action[N] Action[i] (being developed) Action[i] Environment Action Combining
Internal States Sensory Data Learn/Act Action Development Action Selection Seek Follow Acquired (always runs) Action being developed. (Seek, Follow, Acquire) 0/1 Acquire Heading adjustment Speed adjustment Environment
Front of Robot (Oriented at 90 degrees) Right Sensor (Oriented at 45 degrees) Left Sensor (Oriented at 135 degrees) Sound Source D0 D1 Signal Strength at Right Sensor = Sound Source Intensity/D1^2 Signal Strength at Left Sensor = Sound Source Intensity/D0^2
Input from left acoustic sensorInput from right acoustic sensor Input layer to hidden layer weights Transfer function Hidden layer to output layer weights Heading adjustment Speed adjustment
Lead robot in a line of n = 12 robots. It is manually controlled. Follower robots. Id = 1 to n-1. Each is controlled by a feed-forward neural network. Each robot follows the robot whose id is one less than its own. Id = 0 Id = 1 Id = 2 Id = 3 Id = 11 Line Formation.
Lead robot. Id = 0 Modified tree Formation. Id = 3 Id = 4Id = 5 Id = 6Id = 7 Id = 2 Follower robots. Id = 1 to n-1. Each is controlled by a feed-forward neural network. Each robot follows the robot whose id is its own divided by 2. Id = 1