One of the many challenges in building robust and reliable autonomous systems is the large number of parameters and settings such systems often entail. The traditional approach to this task is simply to have system experts hand tune various parameter settings, and then validate them through simulation, offline playback, and field testing. However, this approach is tedious and time consuming for...

Meta-cognition refers to learners' autonomous awareness of their own mental process and the ability to reflect, control, evaluate and regulate their own cognitive process. Influenced by traditional teaching mode, college students are always lack of the ability of autonomic learning and of learning methods. We should foster their consciousness of meta-cognition using meta-cognition strategy, hel...

Reinforcement learning is one of effect,ive controller for autonomous robots. Became it does not need priori knowledge and hehaviom to complete given tasks are obtained automatically by repeating trial and error. However a large number of trials are required to realize complex tasks. So the task that can be obt.ained using t.he real robot is restricted to simple ones. Comidering these points, v...

A novel integrative learning architecture based on a reinforcement learning schemata model (RLSM) with a spike timing-dependent plasticity (STDP) network is described. This architecture models operant conditioning with discriminative stimuli in an autonomous agent engaged in multiple reinforcement learning tasks. The architecture consists of two constitutional learning architectures: RLSM and S...

Autonomous Intelligent Systems (AIS) integrate planning, learning, and execution in a closed loop, showing an autonomous intelligent behavior. A Learning Life Cycle (LLC) Operators, Trained Base Operators and World Interaction Operators. The extension of the original architecture to support the new type of operators is presented.

This paper presents a Q-learning approach to state-based planning of behaviour-based walking robots. The learning process consists of a teaching stage and an autonomous learning stage. During the teaching stage, the robot is instructed to operate in some interesting areas of the solution space to accumulate some prior knowledge. Then, the learning is switched to the autonomous learning stage to...

Abstract As one of the three pillars in computational intelligence, fuzzy systems are a powerful mathematical tool widely used for modelling nonlinear problems with uncertainties. Fuzzy take form linguistic IF-THEN rules that easy to understand human. In this sense, inference mechanisms have been developed mimic human reasoning and decision-making. From data analytic perspective, provide an eff...