Towards Reliable Autonomous Agents
نویسنده
چکیده
We are interested in producing reliable autonomous robots that can operate for extended periods of time in uncertain, dynamic environments. We have been developing methodologies and software tools to facilitate this, including the Task Control Architecture and probabilistic methods for representing and reasoning about uncertainty. The aim is to incrementally produce reliable behavior by adding (perhaps automatically) execution monitors and exception handlers that can detect when expectations are being violated and react appropriately. We have been developing and testing these ideas on a number of mobile robot platforms, including a six-legged planetary rover, a wheeled Lunar rover, and an office-navigation robot.
منابع مشابه
Towards Modelling Real Time Constraints
Software agents are highly autonomous, situated and interactive software components. They autonomously sense their environment and respond accordingly. Agents behaviours are often constrained by by real time constraints such as the time in which the agent is expected to respond .i.e. time needed for a task to complete. Failing to meet such a constraint can result in a task being not achieved. T...
متن کاملReliable Intersection Control in Non-cooperative Environments
We propose a reliable intersection control mechanism for strategic autonomous and connected vehicles (agents) in non-cooperative environments. Each agent has access to his/her earliest possible and desired passing times, and reports a passing time to the intersection manager, who allocates the intersection temporally to the agents in a First-ComeFirst-Serve basis. However, the agents might have...
متن کاملTowards Competence in Autonomous Agents
My thesis aims to contribute towards building autonomous agents that are able to develop what White (1959) called competency over their environment—agents that are able to achieve mastery over their domain and are able to solve new problems as they arise using the knowledge and skills they acquired in the past. While the field of machine learning has made much progress in solving individual, is...
متن کاملTowards reliable multi-agent systems: An adaptive replication mechanism
Distributed cooperative applications are now increasingly being designed as a set of autonomous entities, named agents, which interact and coordinate (thus named a multi-agent system). Such applications are often very dynamic: new agents can join or leave, they can change roles, strategies, etc. This high dynamicity creates new challenges to the traditional approaches of fault-tolerance. In thi...
متن کاملAutonomous Drug-Encapsulated Nanoparticles: Towards a Novel Non-Invasive Approach to Prevent Atherosclerosis
Introduction This paper proposes the concept of autonomous drug-encapsulated nanoparticle (ADENP) as a novel non-invasive approach to prevent atherosclerosis. ADENP consists of three simple units of sensor, controller (computing), and actuator. The hardware complexity of ADENP is much lower than most of the nanorobots, while the performance is maintained by the synergism in the swarm architectu...
متن کامل