102,922 Hits in 9.4 sec

Planning strategy representation in DoLittle [chapter]

Jacky Baltes
1998 Lecture Notes in Computer Science  
The search control method applies different general operators based on a strongest first principle; planning biases that are expected to lead to small search spaces are tried first.  ...  This paper introduces multi-strategy planning and describes its implementation in the DoLittle system, which can combine many different planning strategies, including means-ends analysis, macro-based planning  ...  DoLittle's search control The representation of different planning strategies is alone not sufficient for a multi-strategy planning system.  ... 
doi:10.1007/3-540-64575-6_38 fatcat:tg7lsngevfaiznmjvie6ft5k3m

RTS AI Problems and Techniques [chapter]

Santiago Ontañón, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David Churchill, Mike Preuss
2015 Encyclopedia of Computer Graphics and Games  
Definition Real-Time Strategy (RTS) games is a sub-genre of strategy games where players need to build an economy (gathering resources and building a base) and military power (training units and researching  ...  technologies) in order to defeat their opponents (destroying their army and base).  ...  Reactive planning [67] , a decompositional planning similar to hierarchical task networks [23] , allows for plans to be changed at different granularity levels and so for multi-scale (hierarchical) goals  ... 
doi:10.1007/978-3-319-08234-9_17-1 fatcat:6w2ysoduwfa5pa4qs4cjzpa3si

Using genetic programming to learn and improve control knowledge

Ricardo Aler, Daniel Borrajo, Pedro Isasi
2002 Artificial Intelligence  
The purpose of this article is to present a multi-strategy approach to learn heuristics for planning.  ...  This multi-strategy system, called HAMLET-EVOCK, combines a learning algorithm specialized in planning (HAMLET) and a genetic programming (GP) based system (EVOCK: Evolution of Control Knowledge).  ...  Acknowledgements We thank the reviewers for their very useful comments. The suggested additional experiments helped considerably to clarify HAMLET handicaps and HAMLET-EVOCK behavior.  ... 
doi:10.1016/s0004-3702(02)00246-1 fatcat:pdua4db5dbhddeh7nm63mqng7e


Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, Julian Togelius, Michael Wagner
2013 Dagstuhl Publications  
The chapter first summarises the state of the art in search algorithms for games.  ...  This chapter arises from the discussions of an experienced international group of researchers interested in the potential for creative application of algorithms for searching finite discrete graphs, which  ...  as foreseen by a range of leading researchers in AI for search and abstraction in games.  ... 
doi:10.4230/dfu.vol6.12191.i dblp:conf/dagstuhl/X13b fatcat:i4isdb5w4fastcbnczbtsdulkm

Combining Policy Search with Planning in Multi-agent Cooperation [chapter]

Jie Ma, Stephen Cameron
2009 Lecture Notes in Computer Science  
We propose a novel method called Policy Search Planning (PSP), in which Policy Search is used to find an optimal policy for selecting plans from a plan pool.  ...  It is cooperation that essentially differentiates multi-agent systems (MASs) from single-agent intelligence.  ...  Under RoboCup we are planning to define more plans and more features for PSP in our OxBlue 2D and 3D teams to further verify the robustness of our method.  ... 
doi:10.1007/978-3-642-02921-9_46 fatcat:i7xjulygnbdw5b43gslnie4nua

Testing harbour patrol and interception policies using particle-swarm-based learning of cooperative behavior

Tom Flanagan, Chris Thornton, Jorg Denzinger
2009 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications  
We also can evaluate the quality of an attack using several measures that can be prioritised and used in a multi-objective manner in the search.  ...  We present a general scheme for testing multiagent systems, respectively policies used by them, for unwanted emergent behavior using learning of cooperative behavior via particle swarm systems.  ...  Since is a partial ordering (and has domination ordering components) we have to use a PSS for multi-objective optimisation (with being the ordering used to determine domination between positions) and we  ... 
doi:10.1109/cisda.2009.5356561 dblp:conf/cisda/FlanaganTD09 fatcat:v2llrgoinzcvrfhmp5pztzvmfy

Genetic Re-planning Strategy of Wormhole Model using Neural Learned Vibration Behavior in Robotic Assembly

Lejla Banjanovic-Mehmedovic, Fahrudin Mehmedovic, Ivan Bosankic, Senad Karic
2013 Automatika  
Original scientific paper This paper investigates the genetic based re-planning search strategy, using neural learned vibration behavior for achieving tolerance compensation of uncertainties in robotic  ...  Neural network based learning was used to generate wider scope of parameters in order to improve the robot behavior during each state of the assembly process.  ...  learning algorithm and re-planning search strategy.  ... 
doi:10.7305/automatika.54-4.309 fatcat:736sjgopuvavdfulo4scuxmfom

Multi-Robot Coordination and Planning in Uncertain and Adversarial Environments [article]

Lifeng Zhou, Pratap Tokekar
2021 arXiv   pre-print
These algorithms have been applied to tasks such as formation control, task assignment and scheduling, search and planning, and informative data collection.  ...  In order for multi-robot systems to become practical, we need coordination algorithms that can scale to large teams of robots dealing with dynamically changing, failure-prone, contested, and uncertain  ...  Acknowledgements The authors would like to thank the National Science Foundation (NSF IIS-1637915) and the Office of Naval Research (ONR N00014-18-1-2829) for their supports.  ... 
arXiv:2105.00389v1 fatcat:bwnyxvpvzjfrbjxyiysnmq5e74

A distributed architecture for an instructable problem solver

Baltes, MacDonald
1994 Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences HICSS-94  
The problem solving module is able to combine diverse problem solving strategies on a single problem, by using a common representation for operators, and learning operators by analyzing solution traces  ...  It is controlled from the next level by a tightly constrained planner.  ...  Acknowledgements This work is support by the Natural Sciences and Engineering Research Council of Canada, the Alberta Microelectronic Centre, and the University of Calgary.  ... 
doi:10.1109/hicss.1994.323365 fatcat:zbxqtyzr4fesrholhgnntoun3q

Storing and Indexing Plan Derivations through Explanation-based Analysis of Retrieval Failures

L. H. Ihrig, S. Kambhampati
1997 The Journal of Artificial Intelligence Research  
It replaces the detailed and lengthy search for a solution with the retrieval and adaptation of previous planning experiences.  ...  An empirical evaluation of this approach demonstrates the advantage of learning from experienced retrieval failure.  ...  Mali, Eric Lambrecht, Eric Parker, and the anonymous reviewers for their helpful comments on earlier versions of this paper. Thanks are due to Terry Zimmerman for providing insight i n to ucpop+ebl.  ... 
doi:10.1613/jair.424 fatcat:v5emgsmr7fhtlkxbzjlvkdeacu

Construction and Simulation of Multi-Objective Rescheduling Model Based on PSO

J. X. Li, X. N. Wen
2020 International Journal of Simulation Modelling  
To make up for the gap, this paper classifies dynamic events by scheduling strategies, and details the hypotheses and constraints of dynamic job-shop scheduling.  ...  The research results provide a reference for the application of swarm intelligence in the field of the JSP.  ...  ACKNOWLEDGEMENT Shaanxi province soft science research program key project (2016KRZ010); sponsored by the Seed Foundation of Innovation Practice for Graduate Students in Xi'dian University.  ... 
doi:10.2507/ijsimm19-2-co8 fatcat:bcvh23zerzc43mogfibapaydv4

Motion planning for mobile Robots–focusing on deep reinforcement learning: A systematic Review

Huihui Sun, Weijie Zhang, Runxiang YU, Yujie Zhang
2021 IEEE Access  
Furthermore, the recently-emerged methods of DRL are also surveyed, especially the ones involving the imitation learning, meta-learning and multi-robot systems.  ...  According to the surveys, the potential research directions of motion-planning algorithms serving for mobile robots are enlightened.  ...  [134] proposed a distributed RL model based on multi-sensor in order to solve the motion planning problem of multiple robots.  ... 
doi:10.1109/access.2021.3076530 fatcat:53kdh5cfgvcang5xymf4vrqx2e

Research status of operational environment partitioning and path planning for multi - robot systems

Xuefeng Dai, Qi Fan, Dahui Li
2017 Journal of Physics, Conference Series  
This paper analyzes and summarizes the current research status of coordinated algorithms for multi-robot systems, from perspectives of partitioning the environment, and path planning.  ...  There is a lot of applications for multi-robot systems instead of single robot systems. Therefore, coordination algorithms have become popular in the field of robotics for two decades.  ...  In addition, in order to solve the uncertainty of environment partitioning and path planning for multi-robot systems, and improve the robustness of multi-robot system, this research is also the focus of  ... 
doi:10.1088/1742-6596/887/1/012080 fatcat:v7dio6mhajfshcrayhw7oyyyza

Multi-Agent Systems for Search and Rescue Applications

Daniel S. Drew
2021 Current Robotics Reports  
Purpose of Review The goal of this review is to evaluate the current status of multi-robot systems in the context of search and rescue.  ...  Summary Multi-agent systems are not currently ready for deployment in search and rescue applications; however, progress is being made in a number of critical domains.  ...  Conflict of Interest The author declares that he has no conflict of interest.  ... 
doi:10.1007/s43154-021-00048-3 fatcat:vluqs6xhzreyhgs4a54jvrhd2q

Game Theory for Unmanned Vehicle Path Planning in the Marine Domain: State of the Art and New Possibilities

Marco Cococcioni, Lorenzo Fiaschi, Pierre F. J. Lermusiaux
2021 Journal of Marine Science and Engineering  
There has thus been a commensurate number of approaches and methods to optimize this kind of path planning.  ...  To achieve autonomy in such highly dynamic uncertain conditions, many types of autonomous path planning problems need to be solved.  ...  In particular, the use of multi-objective optimization for multi-task path planning seems to arise quite naturally.  ... 
doi:10.3390/jmse9111175 fatcat:3v6oyeo4yfgcvatahm5rki456u
« Previous Showing results 1 — 15 out of 102,922 results