Control Architecture For Autonomous Robots Research Articles

Improved Resilience Controllers Using Cognitive Patterns

Construction of robotic controllers has been usually done by the instantiation of specific architectural designs. The ASys design strategy described in this work addresses the synthesis of custom robot architectures by means of a requirements-driven application of universal design patterns. In this paper we present three of these patterns —the Epistemic Control Loop, the MetaControl and the Deep Model Reflection patterns— that constitute the core of a pattern language for a new class of adaptive and robust control architectures for autonomous robots. A reference architecture for self-aware autonomous systems is synthesised from these patterns and demonstrated in the control of an autonomous mobile robot. The term “autonomous” gains a deeper significance in this context of reflective, pattern based controllers.

Behavioral task processing for cognitive robots using artificial emotions

This paper presents an artificial emotional-cognitive system-based autonomous robot control architecture for a four-wheel driven and four-wheel steered mobile robot. Discrete stochastic state-space mathematical model is considered for behavioral and emotional transition processes of the autonomous mobile robot in the dynamic realistic environment. The term of cognitive mechanism system which is composed from rule base and reinforcement self-learning algorithm explain all of the deliberative events such as learning, reasoning and memory (rule spaces) of the autonomous mobile robot. The artificial cognitive model of autonomous robot control architecture has a dynamic associative memory including behavioral transition rules which are able to be learned for achieving multi-objective robot tasks. Motivation module of architecture has been considered as behavioral gain effect generator for achieving multi-objective robot tasks. According to emotional and behavioral state transition probabilities, artificial emotions determine sequences of behaviors for long-term action planning. Also reinforcement self-learning and reasoning ability of artificial cognitive model and motivational gain effects of proposed architecture can be observed on the executing behavioral sequences during simulation. The posture and speed of the robot and the configurations, speeds and torques of the wheels and all deliberative and cognitive events can be observed from the simulation plant and virtual reality viewer. This study constitutes basis for the multi-goal robot tasks and artificial emotions and cognitive mechanism-based behavior generation experiments on a real mobile robot.

Modeling robot cognitive activity through active mental entities

This paper aims at laying down the foundations of an approach to the development of autonomous robot control architecture based on the explicit representation of mental attitudes underlying robot behavior, considered as autonomous active entities. The approach is intended to integrate concepts from the area of distributed architectures and of mental attitude representation and aims at realizing an explicit motivational basis for robot behavior. Starting from an analysis of the evolution of autonomous robot control architectures, we discuss and motivate the introduction of active mental entities in the context of a distributed control architecture. Attention is then focused on two classes of mental entities, namely intender and attender: their main features are illustrated and discussed. A prototypical implementation of the proposed paradigm and its application to the control of the Khepera simulator are then described. A comparison with related works and a discussion of the main directions of future research conclude the paper.

Control Architecture for Behavior Acquisition of Autonomous Robots. Reinforcement Learning Using Globally Coupled Chaotic System.

An autonomous robot that acts in a complex environment needs to learn which action should be performed in each external state. Therefore, we propose a new control architecture for autonomous robots. The control architecture includes a learning system, which consists of globally coupled chaotic elements. A chaotic element has dynamics which are designed so that the elements can collectively execute reinforcement learning. Although each element continuously updates its internal state according to its intrinsic dynamics, this local processing collectively determines an action of the robot and allows it to interact with its environment. The result of this interaction returns to the elements as a payoff, which changes the dynamics. We carried out computational experiments for a navigation task. The results show that the chaotic elements self-organize so that an autonomous mobile robot exhibits such behaviors as goal-reaching, wall-following and collision avoidance.