155 Hits in 2.9 sec

Experiments in Subsymbolic Action Planning with Mobile Robots [chapter]

John Pisokas, Ulrich Nehmzow
2005 Lecture Notes in Computer Science  
In this paper, we present experiments with two autonomous mobile robots, which use autonomously learned subsymbolic representations of perceptual and behavioural space to determine goal-achieving sequences  ...  The ability to determine a sequence of actions in order to reach a particular goal is of utmost importance to mobile robots.  ...  Action Selection versus Action Planning The bulk of research on subsymbolic planning to date has focused on simulated agents, rather than situated, embodied mobile robots.  ... 
doi:10.1007/978-3-540-32274-0_14 fatcat:saoywiut4fepjht4lrcndn335a

Deep Blue Cannot Play Checkers: The Need for Generalized Intelligence for Mobile Robots

Troy D. Kelley, Lyle N. Long
2010 Journal of Robotics  
Generalized intelligence is much more difficult than originally anticipated when Artificial Intelligence (AI) was first introduced in the early 1960s.  ...  Deep Blue, the chess playing supercomputer, was developed to defeat the top rated human chess player and successfully did so by defeating Gary Kasporov in 1997.  ...  Intelligence would allow the robots to perceive their environment, plan their activities, solve problems, and learn from experience [4] .  ... 
doi:10.1155/2010/523757 fatcat:27syv3qao5dthnhl6lkp75c4di

Learning structured reactive navigation plans from executing MDP navigation policies

Michael Beetz, Thorsten Belker
2001 Proceedings of the fifth international conference on Autonomous agents - AGENTS '01  
The resulting plans support action planning and opportunistic task execution. XFRMLEARN is implemented and extensively evaluated on an autonomous mobile robot.  ...  Autonomous robots, such as robot office couriers, need navigation routines that support flexible task execution and effective action planning.  ...  The research reported in this paper is partly funded by the Deutsche Forschungsgemeinschaft (DFG) under contract number BE 2200/3-1.  ... 
doi:10.1145/375735.375795 dblp:conf/agents/BeetzB01 fatcat:ovln7czxjvd7bbcuxfhdxmxrzy

Bridging the Symbolic/Subsymbolic Gap [chapter]

Ben Goertzel, Cassio Pennachin, Nil Geisweiller
2014 Atlantis Thinking Machines  
We discuss the potential use of this integrated system to control mobile robots, as exemplified via a thought-experiment involving eye-hand coordination.  ...  This is a "tight" integration, in which the symbolic and subsymbolic aspects exert detailed real-time influence on each others' operations.  ...  Current robots, in some cases, can carry out specialized actions with great accuracy, but they lack this sort of integration, and thus generally have difficulty effectively carrying out actions in unforeseen  ... 
doi:10.2991/978-94-6239-030-0_11 fatcat:2sdgwxkq5jc6djeznwez5rn3fi

Specializing Underdetermined Action Descriptions Through Plan Projection [article]

Gayane Kazhoyan, Michael Beetz
2018 arXiv   pre-print
Plan execution on real robots in realistic environments is underdetermined and often leads to failures. The choice of action parameterization is crucial for task success.  ...  By thinking ahead of time with the fast plan projection mechanism proposed in this paper, a general plan can be specialized towards the environment and task at hand by choosing action parameterizations  ...  In the domain of mobile manipulation, the choice of action parameterization is crucial for task success. There is a large number of parameters and most of them are subsymbolic.  ... 
arXiv:1812.08224v1 fatcat:qqaldyoirff3bokxbex4kftnqi

A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments [chapter]

José R. Millán, Carme Torras
1992 Reinforcement Learning  
This paper presents a reinforcement connectionist system which finds and learns the suitable situationaction rules so as to generate feasible paths for a point robot in a 2D environment with circular obstacles  ...  capabilities, (iv) copes with dynamic environments, and (v) solves an instance of the path finding problem with strong performance demands.  ...  Carme Torras has been partially supported by the ESPRIT Basic Research Action number 3234.  ... 
doi:10.1007/978-1-4615-3618-5_8 fatcat:ow5dphym7nbqlnsvininp5suky

Unsupervised learning of object affordances for planning in a mobile manipulation platform

Emre Ugur, Erol Sahin, Erhan Oztop
2011 2011 IEEE International Conference on Robotics and Automation  
Nehmzow, “Experiments in subsymbolic action parameters.  ...  In case, for simplicity we defined multiple actions planning with mobile robots,” in International Symposium on Robotics (e.g. move−30◦ , move−30◦ ) for different instantiations of the and  ... 
doi:10.1109/icra.2011.5979677 dblp:conf/icra/UgurSO11 fatcat:czixr6v7lbf3dp6kpqhic5zcmy

Control of Mobile Robots Using the Soar Cognitive Architecture

Scott D. Hanford, Oranuj Janrathitikarn, Lyle N. Long
2009 Journal of Aerospace Computing Information and Communication  
A multithreaded software system written using Java and integrated with the Soar cognitive architecture has been implemented on two types of mobile robots.  ...  The CRS has been designed so that its capabilities can be expanded in the future through the inclusion of additional sensors and motors, additional software systems, and more sophisticated Soar agents.  ...  Soar has been used with a mobile robot equipped with sonar sensors and a robotic gripper to locate and pick up cups [33] .  ... 
doi:10.2514/1.37056 fatcat:j4dw5f65qja7jahzspwranqzlq

A reinforcement connectionist approach to robot path finding in non-maze-like environments

Jos� Del R. Mill�n, Carme Torras
1992 Machine Learning  
This paper presents a reinforcement connectionist system which finds and learns the suitable situationaction rules so as to generate feasible paths for a point robot in a 2D environment with circular obstacles  ...  capabilities, (iv) copes with dynamic environments, and (v) solves an instance of the path finding problem with strong performance demands.  ...  Carme Torras has been partially supported by the ESPRIT Basic Research Action number 3234.  ... 
doi:10.1007/bf00992702 fatcat:gono2whhvrfepl6tx22uulkcim

Robotic Action Control: On the Crossroads of Cognitive Psychology and Cognitive Robotics [chapter]

Roy de Kleijn, George Kachergis, Bernhard Hommel
2015 Cognitive Robotics  
In other words, action planning must be a temporally extended process in which abstract representations to some extent provide abstract goal descriptions, which must be integrated with lower-level subsymbolic  ...  Everyday action planning A major obstacle in the way of robots performing everyday actions is the translation of high-level, symbolic task descriptions into sensorimotor action plans.  ... 
doi:10.1201/b19171-16 fatcat:mzhfxmdlpnbnbjabtzcsxj7hbu

Meeting Newell's other challenge: Cognitive architectures as the basis for cognitive engineering

Wayne D. Gray, Michael J. Schoelles, Christopher W. Myers
2003 Behavioral and Brain Sciences  
These properties suit ART for large-scale technological applications, ranging from control of mobile robots, face recognition, remote sensing, medical diagnosis, and electrocardiogram analysis to tool  ...  "Dealing with dynamic behavior requires a theory of perception and action as well as a theory of cognition" (sect. 2.5).  ... 
doi:10.1017/s0140525x03280134 fatcat:kq7g3sg2vzfqtkwwztqlfu7sua

Review of Consciousness and the Possibility of Conscious Robots

Lyle N. Long, Troy D. Kelley
2010 Journal of Aerospace Computing Information and Communication  
This paper discusses the psychological, philosophical, and neurological definitions of consciousness and the prospects for the development of conscious machines or robots in the foreseeable future.  ...  Given the complexity of cognition and consciousness a hybrid parallel architecture with significant input/output appears to offer the best solution for the implementation of a complex system of systems  ...  In fact, if machines can be imbued with emotions, they may also experience feelings such as depression.  ... 
doi:10.2514/1.46188 fatcat:lildzd7tjjhbtng2pdv3gien6a

PlanSys2: A Planning System Framework for ROS2 [article]

Francisco Martín, Jonatan Ginés, Vicente Matellán, Francisco J. Rodríguez
2021 arXiv   pre-print
Among its main features, it can be highlighted the optimized execution, based on Behavior Trees, of plans through a new actions auction protocol and its multi-robot planning capabilities.  ...  PlanSys2 aims to be the reference task planning framework in ROS2, the latest version of the de facto standard in robotics software development.  ...  As shown in Table II , the experiment lasted two hours, in which the robot carried out 32 plans, with no system Fig. 9 : Long-time experiment in the real robot [33] . failure and 9 re-plans.  ... 
arXiv:2107.00376v1 fatcat:fk4jipjdkvfgverxmxqhu3hpru

Sensorimotor transformations in the worlds of frogs and robots

Michael A. Arbib, Jim-Shih Liaw
1995 Artificial Intelligence  
The paper develops a multilevel approach to the design and analysis of systems with "action-oriented perception", situating various robot and animal "designs" in an evolutionary perspective.  ...  , and path planning in frogs.  ...  Detours and path planning In the present section, we show how a study of frog behavior led to a model of path planning that was then applied to the design of the control of mobile robots, and which anticipated  ... 
doi:10.1016/0004-3702(94)00055-6 fatcat:tnuagftutfg75hdoo3hxwjr7cu

Designing Grounded Agents: From RoboCup to the Real-World [chapter]

Christopher Stanton
2009 Lecture Notes in Computer Science  
This paper discusses the nature and role of "grounding" in designing programs for controlling autonomous mobile robots.  ...  However, little (if any) of the knowledge of "how to ground" is embedded in the artificial agent. Consequently, brittle, purpose-built systems result.  ...  grounding autonomous mobile robots.  ... 
doi:10.1007/978-3-642-02921-9_54 fatcat:mva3hal4pnfphn4lwh46uu42l4
« Previous Showing results 1 — 15 out of 155 results