A framework for goal generation and management (original) (raw)
Related papers
Agent in a Box: A Framework for Autonomous Mobile Robots with Beliefs, Desires, and Intentions
Electronics, 2021
This paper provides the Agent in a Box for developing autonomous mobile robots using Belief-Desire-Intention (BDI) agents. This framework provides the means of connecting the agent reasoning system to the environment, using the Robot Operating System (ROS), in a way that is flexible to a variety of application domains which use different sensors and actuators. It also provides the needed customisation to the agent’s reasoner for ensuring that the agent’s behaviours are properly prioritised. Behaviours which are common to all mobile robots, such as for navigation and resource management, are provided. This allows developers for specific application domains to focus on domain-specific code. Agents implemented using this approach are rational, mission capable, safety conscious, fuel autonomous, and understandable. This method was used for demonstrating the capability of BDI agents to control robots for a variety of application domains. These included simple grid environments, a simulat...
An Integrated Approach to Goal Selection in Mobile Robot Exploration
Sensors
This paper deals with the problem of autonomous navigation of a mobile robot in an unknown2D environment to fully explore the environment as efficiently as possible. We assume a terrestrial mobilerobot equipped with a ranging sensor with a limited range and 360º field of view. The key part of theexploration process is formulated as the d-Watchman Route Problem which consists of two coupledtasks—candidate goals generation and finding an optimal path through a subset of goals—which aresolved in each exploration step. The latter has been defined as a constrained variant of the GeneralizedTraveling Salesman Problem and solved using an evolutionary algorithm. An evolutionary algorithmthat uses an indirect representation and the nearest neighbor based constructive procedure was proposedto solve this problem. Individuals evolved in this evolutionary algorithm do not directly code thesolutions to the problem. Instead, they represent sequences of instructions to construct a feasible solution...
Domain-Independent Heuristics for Goal Formulation
Goal-driven autonomy is a framework for intelligent agents that automatically formulate and manage goals in dynamic environments, where goal formulation is the task of identifying goals that the agent should attempt to achieve. We argue that goal formulation is central to high-level autonomy, and explain why identifying domain-independent heuristics for this task is an important research topic in high-level control. We describe two novel domain-independent heuristics for goal formulation (motivators) that evaluate the utility of goals based on the projected consequences of achieving them. We then describe their integration in M-ARTUE, an agent that balances the satisfaction of internal needs with the achievement of goals introduced externally. We assess its performance in a series of experiments in the Rovers With Compass domain. Our results show that using domain-independent heuristics yields performance comparable to using domain-specific knowledge for goal formulation. Finally, i...
A cognitive agent for searching indoor environments using a mobile robot
2011
Recently there has been increased interest in the use of cognitive architectures for mobile robots. In this research, a cognitive agent (developed using Soar) has been developed to perform an indoor search and rescue mission using a mobile robot. For this application, sensor processing systems such as image processing, fuzzy logic, and image matching are used to generate information about the environment. The cognitive agent described in this paper is capable of using this information about the environment to explore a building while detecting and recording the locations of common types of intersections, making decisions about where to go based on these intersections, and detecting objects of interest and recording their locations. Results are given for a test in a simple environment.