Filters








2,195 Hits in 5.0 sec

Abstractions for computing all robotic sensors that suffice to solve a planning problem [article]

Yulin Zhang, Dylan A. Shell
2020 arXiv   pre-print
These lead to algorithms that we have implemented and which suffice to solve particular problem instances, albeit only of small scale.  ...  Toward taming this complexity, two contributions are made: (1) we show how to represent the search space for this more general problem and describe data structures that enable whole sets of sensors to  ...  CONCLUSION This paper explores the space of all sensors that provide enough information to solve the planning problem for the robots.  ... 
arXiv:2005.10994v1 fatcat:2hsyudgvjzhq3as5vrg7rab4ou

On the Role of Stored Internal State in the Control of Autonomous Mobile Robots

Erann Gat
1993 The AI Magazine  
The vision system on the real robot is actually quite good. Extra noise is introduced artificially into the simulated vision to ensure that the system will work with noisy data.  ...  The first problem can be solved by operating the planner in parallel with a process that deals with contingencies.  ...  Second, these difficulties are not unique to planning but apply to all sequential computations.  ... 
doi:10.1609/aimag.v14i1.1034 dblp:journals/aim/Gat93 fatcat:uayzu6y6h5hlpmujg7tngm6cai

Knowledge Processing for Cognitive Robots

Moritz Tenorth, Dominik Jain, Michael Beetz
2010 Künstliche Intelligenz  
Knowledge processing methods are an important resource for robots that perform challenging tasks in complex, dynamic environments.  ...  When applied to robot control, such methods allow to write more general and flexible control programs and enable reasoning about the robot's observations, the actions involved in a task, action parameters  ...  Acknowledgments This work is supported in part within the DFG excellence initiative research cluster Cognition for Technical Systems (CoTeSys), see also www.cotesys.org.  ... 
doi:10.1007/s13218-010-0044-0 fatcat:pur4jvsmfbbt7kznsqefqdxxiq

Iterator-Based Temporal Logic Task Planning [article]

Sebastián Zudaire and Martín Garrett and Sebastián Uchitel
2020 arXiv   pre-print
We propose a hybrid control framework that uses an iterator to manage the discretised workspace hiding it from a plan enacted by a discrete event controller.  ...  We provide a novel approach, particularly suited for tasks specifications with universally quantified locations, that has constant time with respect to the number of locations, enabling synthesis of plans  ...  When goals and assumptions are restricted to a GR(1) form [4] the control problem can solved in polynomial time.  ... 
arXiv:2001.07678v2 fatcat:glrdyrjoz5fxvizqlpe2cbbwoe

Towards Comprehensive Computational Models for Plan-Based Control of Autonomous Robots [chapter]

Michael Beetz
2005 Lecture Notes in Computer Science  
In the second part of the paper we describe Structured Reactive Controllers (SRCs), our own approach to the development of a comprehensive computational model for the planbased control of robotic agents  ...  We identify computational principles that enable autonomous robots to accomplish complex, diverse, and dynamically changing tasks in challenging environments.  ...  Figure 6 pictures an execution trace for a sample problem-solving scenario.  ... 
doi:10.1007/978-3-540-32254-2_29 fatcat:wdlop6bwdbf7hm5dzmbpzjft6i

Real-time system architecture design practices

Andrey Getmanskiy, Semen Sechenev, Igor Ryadchikov, Alexander Gusev, Nikita Mikhalkov, Dmitry Kazakov, Alexey Simulin, Dmitry Sokolov
2021 Procedia Computer Science  
The goal of the paper is to reveal separate classes of such architectures as well as to define preconditions for choosing a particular architecture.  ...  The goal of the paper is to reveal separate classes of such architectures as well as to define preconditions for choosing a particular architecture.  ...  Here we list all the questions that we found relevant: 1. Are there highly specialized hardware and software solutions for the task you are solving?  ... 
doi:10.1016/j.procs.2021.04.199 fatcat:pbrm37ukuvdrjfdgba3ditdkvy

Learning a Spatial Field in Minimum Time with a Team of Robots [article]

Varun Suryan, Pratap Tokekar
2020 arXiv   pre-print
We study an informative path-planning problem where the goal is to minimize the time required to learn a spatially varying entity.  ...  We also study a multi-robot version where the objective is to minimize the time required by the last robot to return to a common starting location called depot.  ...  We show that a non-adaptive algorithm suffices to solve the problem and yields a polynomial-time constant-factor approximation to the optimal algorithm.  ... 
arXiv:1909.01895v2 fatcat:c27nqqyamzaqxbrvpruojdsjee

Metric View Planning Problem with Traveling Cost and Visibility Range

Pengpeng Wang, Ramesh Krishnamurti, Kamal Gupta
2007 Engineering of Complex Computer Systems (ICECCS), Proceedings of the IEEE International Conference on  
In this paper, we consider the problem where a point robot in a 2D or 3D environment equipped with an omnidirectional range sensor of finite range D is asked to inspect a set of surface patches, while  ...  We then analyze the natural two-level algorithm, presented in [6], of solving first the view planning problem to get an approximate solution, and then solving, again using an approximation algorithm, the  ...  They proposed to solve the problem by a decoupled two-level approach, i.e., to plan the minimum number of viewpoints without considering robot traveling cost first and then to solve approximately the Metric  ... 
doi:10.1109/robot.2007.363163 dblp:conf/icra/WangKG07a fatcat:22szgw6565gi3lzaslc6o5gzl4

Sub-goal based Robot Visual Navigation through Sensorial Space Tesselation

George Palamas, J. Andrew Ware Andrew
2013 International Journal of Advanced Research in Artificial Intelligence (IJARAI)  
Experiments in simulation show that an evolved robot, adapted to both exteroceptive and proprioceptive data, is able to successfully drive through a list of sub-goals minimizing the problem of local minima  ...  During the next step, a genetic algorithm evolves a navigation controller that the robot uses for visual servoing, driving through a set of nodes on the topological map.  ...  ACKNOWLEDGMENT The authors would like to thank all laboratory members for their valuable discussions through this research.  ... 
doi:10.14569/ijarai.2013.021106 fatcat:6eqnvhx3zjdypoypwboxua4w6y

Lifelong robot learning

Sebastian Thrun, Tom M. Mitchell
1995 Robotics and Autonomous Systems  
Computational tractability turned out to be a severe obstacle for designing control structures for complex robots in complex domains, and robots were far from being "reactive." Precision bottleneck.  ...  The robot device must be precise enough to accurately execute plans that were generated using the internal models of the world.  ...  Acknowledgment We thank the CMU Robot Learning Group and the Odysseus team at CMU for invaluable discussion that contributed to this research.  ... 
doi:10.1016/0921-8890(95)00004-y fatcat:dqxlycto4rf3lotx6ykzoqsuqq

Lifelong Robot Learning [chapter]

Sebastian Thrun, Tom M. Mitchell
1995 The Biology and Technology of Intelligent Autonomous Agents  
Computational tractability turned out to be a severe obstacle for designing control structures for complex robots in complex domains, and robots were far from being "reactive." Precision bottleneck.  ...  The robot device must be precise enough to accurately execute plans that were generated using the internal models of the world.  ...  Acknowledgment We thank the CMU Robot Learning Group and the Odysseus team at CMU for invaluable discussion that contributed to this research.  ... 
doi:10.1007/978-3-642-79629-6_7 fatcat:gfyvm2ql25gdxgsqxko5cuou6m

Towards Learning Abstract Representations for Locomotion Planning in High-dimensional State Spaces [article]

Tobias Klamt, Sven Behnke
2019 arXiv   pre-print
Ground robots which are able to navigate a variety of terrains are needed in many domains.  ...  We further apply our method to the problem of search-based planning of hybrid driving-stepping locomotion.  ...  In recent years, learning-based approaches for solving robot motion planning problems have been proposed.  ... 
arXiv:1903.02308v1 fatcat:aioii2bzbretnbme3qwnvknfle

Active vision in robotic systems: A survey of recent developments

Shengyong Chen, Youfu Li, Ngai Ming Kwok
2011 The international journal of robotics research  
Planning for robot vision is a complex problem for an active system due to its sensing uncertainty and environmental uncertainty.  ...  The aim of sensor planning is to determine the pose and settings of vision sensors for undertaking a vision-based task that usually requires obtaining multiple views of the object to be manipulated.  ...  It is difficult to compute robust viewpoints which satisfy all constraints. However, evolutionary computation is especially powerful in solving such problems.  ... 
doi:10.1177/0278364911410755 fatcat:pdpxmt4a5nhdvdojcsassxox6i

Sensor-based, task-constrained motion generation under uncertainty

Arne Sieverling, Nicolas Kuhnen, Oliver Brock
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
cannot be known to the robot, and should do so only using their on-board sensors.  ...  Motion generation methods suitable for these applications must account for endeffector task constraints, must reason about environment uncertainty, i.e. the fact that the exact state of the dynamic environment  ...  To solve it optimally, a planner would need to plan on belief space capturing all possible states of the world. This is computationally infeasible.  ... 
doi:10.1109/icra.2014.6907492 dblp:conf/icra/SieverlingKB14 fatcat:b7bes7yvsnf5znzgsdo3tlmajy

Robot navigation in unknown terrains using learned visibility graphs. Part I: The disjoint convex obstacle case

B. Oommen, S. Iyengar, N. Rao, R. Kashyap
1987 IEEE Journal on Robotics and Automation  
Ultimately, the availability of the complete visibility graph enables the robot to plan globally optimal paths and also obviates the further usage of sensors.  ...  An algorithm is presented to navigate a robot in an unexplored terrain that is arbitrarily populated with disjoint convex polygonal obstacles in the plane.  ...  ACKNOWLEDGMENT We would like to thank Prof. T. Lazano-Perez of the Massachusetts Institute of Technology for carefully reading the manuscript and for his helpful and critical comments.  ... 
doi:10.1109/jra.1987.1087133 fatcat:e3vwpvz45jcmbflw2qv42rgrsm
« Previous Showing results 1 — 15 out of 2,195 results