1,008 Hits in 8.4 sec

Extending the Knowledge of Volumes approach to robot task planning with efficient geometric predicates

Andre Gaschler, Ingmar Kessler, Ronald P. A. Petrick, Alois Knoll
2015 2015 IEEE International Conference on Robotics and Automation (ICRA)  
We use an existing Knowledge of Volumes approach to robot task planning (KVP), which facilitates hybrid planning with symbolic actions and continuous-valued robot and object motion, and make two important  ...  For robots to solve hard tasks in real-world manufacturing and service contexts, they need to reason about both symbolic and geometric preconditions, and the effects of complex actions.  ...  CONCLUSION AND FUTURE WORK In this paper, we extend the existing "knowledge of volumes" (KVP) approach to robot task planning, adding additional geometric predicates, and improving the efficiency of all  ... 
doi:10.1109/icra.2015.7139619 dblp:conf/icra/GaschlerKPK15 fatcat:o5yauks5gzc3zpufyudbk2frlu

KABouM: Knowledge-Level Action and Bounding Geometry Motion Planner

Andre Gaschler, Ronald P. A. Petrick, Oussama Khatib, Alois Knoll
2018 The Journal of Artificial Intelligence Research  
volumes of motions--by sets of convex polyhedra, we can efficiently plan manipulation actions and raise reasoning about geometric predicates, such as collisions, to the symbolic level.  ...  For robots to solve real world tasks, they often require the ability to reason about both symbolic and geometric knowledge.  ...  Acknowledgements The authors would like to thank Torsten Kröger, Svetlana Nogina, Quirin Fischer, and Sören Jentzsch for their help with the implementation and evaluation, and Markus Rickert for his comments  ... 
doi:10.1613/jair.5560 fatcat:c7sga7fdffg4rl3k5vypntq5he

Planning perception and action for cognitive mobile manipulators

Andre Gaschler, Svetlana Nogina, Ronald P. A. Petrick, Alois Knoll, Juha Röning, David Casasent
2014 Intelligent Robots and Computer Vision XXXI: Algorithms and Techniques  
Our approach is based on contingent planning and run-time sensing, integrated in our "knowledge of volumes" planning framework, called KVP.  ...  We demonstrate the effectiveness of our approach on two scenarios covering visual and force sensing on a real mobile manipulator.  ...  CONCLUSION In this paper, we present an application of our "knowledge of volumes" approach to robot task planning (KVP) in the field of mobile manipulation.  ... 
doi:10.1117/12.2038967 fatcat:huiyegnejnh2zof4mivvjau56i

Integrating symbolic and geometric planning for mobile manipulation

Christian Dornhege, Marc Gissler, Matthias Teschner, Bernhard Nebel
2009 2009 IEEE International Workshop on Safety, Security & Rescue Robotics (SSRR 2009)  
The symbolic part is implemented as a classical symbolic planner that tightly integrates a geometric planner enabling us to efficiently generate correct plans.  ...  During the computation of the roadmap we utilize proximity queries to determine non-colliding configurations and to verify collisionfree paths between configurations accurately and efficiently.  ...  ACKNOWLEDGMENT This research was supported by DFG as part of the collaborative research center SFB/TR-8 Spatial Cognition Project R7.  ... 
doi:10.1109/ssrr.2009.5424160 fatcat:osymhzfi45fjve4j362emyzxna

Unified Robot Task and Motion Planning with Extended Planner using ROS Simulator

Gayathri Rajendrana, Uma Vijayasundarama, Bettina O'Briena
2021 Journal of King Saud University: Computer and Information Sciences  
Task planning tends to find a sequence of discrete actions in solving the symbolic problems. Motion planning finds the optimal path by avoiding the geometric obstacles in the environment.  ...  This paper presents a hybrid path planning approach, termed RobMAP (Robotic Motion and Action Planning) for achieving efficient navigation by performing desired tasks in a sequence and thereby generate  ...  RRT is a fast probability planning approach that can be extended to multidimensional spaces with multi-robot Zhang et al. (2020) .  ... 
doi:10.1016/j.jksuci.2021.07.002 fatcat:jni7tsj3kzalrcrjp4sedca4du

Design and Implementation of Linked Planning Domain Definition Language [article]

Michiaki Tatsubori, Asim Munawar, Takao Moriyama
2019 arXiv   pre-print
We demonstrate the usefulness of the proposed planning domain description language with our robotics applications.  ...  Given predefined parameterized actions, a planning service should accept a query with the goal and initial state to give a solution with a sequence of actions applied to environmental objects.  ...  Gaschler et al. combine the power of symbolic, knowledge-level AI planning with the efficient computation of volumes, which serve as an intermediate representation for both robot action and perception  ... 
arXiv:1912.07834v1 fatcat:t56kuig6yffg5jgtcje46cj4hm

From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving

Manfred Eppe, Phuong D H Nguyen, Stefan Wermter
2019 Frontiers in Robotics and AI  
As a result, we demonstrate that the integrated method is able to solve robotic tasks that involve non-trivial causal dependencies under noisy conditions, exploiting both data and knowledge.  ...  In this article, we build on these novel methods to facilitate the integration of action planning with model-free reinforcement learning.  ...  ACKNOWLEDGMENTS We thank Erik Strahl for the technical supports with the computing servers and Fares Abawi for the initial version of the Mujoco simulation for the experiments.  ... 
doi:10.3389/frobt.2019.00123 pmid:33501138 pmcid:PMC7805615 fatcat:zfuealfbgfce7jedo5e27yvtsu

Knowledge and Skill Representations for Robotized Production

Anders Björkelund, Jacek Malec, Klas Nilsson, Pierre Nugues
2011 IFAC Proceedings Volumes  
Model-based systems in control are a means to utilize efficiently human knowledge and achieve high performance.  ...  To that end, we extended the formalized knowledge traditionally used in control to include the control purpose, engineering assumption, quality, involved state machines, and so on.  ...  A coherent approach that extends efficiently (with no or little reprogramming when another XML schema or another type of feedback control is added) is the ultimate challenge for this work.  ... 
doi:10.3182/20110828-6-it-1002.01053 fatcat:byrkkjng2jg6hoi4iytylkvg4m

Geometric backtracking for combined task and motion planning in robotic systems

Julien Bidot, Lars Karlsson, Fabien Lagriffoul, Alessandro Saffiotti
2017 Artificial Intelligence  
We present an approach in which state-based forward-chaining task planning is tightly coupled with sampling-based motion planning and other forms of geometric reasoning.  ...  In order to deal with that, we introduce heuristics based on the collisions between the robot and movable objects detected during geometric backtracking and on kinematic relations between actions.  ...  Acknowledgments This work was partially funded by EU FP7 project "Generalizing Robot Manip-  ... 
doi:10.1016/j.artint.2015.03.005 fatcat:rg4ho7gklvdnfamrs66uhkkjtm

Flexible and Efficient Long-Range Planning Through Curious Exploration [article]

Aidan Curtis, Minjian Xin, Dilip Arumugam, Kevin Feigelis, Daniel Yamins
2020 arXiv   pre-print
Identifying algorithms that flexibly and efficiently discover temporally-extended multi-phase plans is an essential step for the advancement of robotics and model-based reinforcement learning.  ...  The core problem of long-range planning is finding an efficient way to search through the tree of possible action sequences.  ...  Related Work A classical approach to planning is that of sample-based geometric motion planners.  ... 
arXiv:2004.10876v2 fatcat:4ioyp3qubnhvtg7txjjkzuixp4

Semantic Attachments for Domain-Independent Planning Systems [chapter]

Christian Dornhege, Patrick Eyerich, Thomas Keller, Sebastian Trüg, Michael Brenner, Bernhard Nebel
2012 Springer Tracts in Advanced Robotics  
For example, manipulation planning may appear as a subproblem in a robotic planning context or a packing problem can be part of a logistics task.  ...  This allows the evaluation of grounded predicates as well as the change of fluents by externally specified functions.  ...  Acknowledgements This research was partially supported by DFG as part of the collaborative research center SFB/TR-8 Spatial Cognition Project R7, the German Federal Ministry of Education and Research (  ... 
doi:10.1007/978-3-642-25116-0_9 fatcat:zyhjevgfnjb33izp4q3evy5f3q

kPAM-SC: Generalizable Manipulation Planning using KeyPoint Affordance and Shape Completion [article]

Wei Gao, Russ Tedrake
2019 arXiv   pre-print
Manipulation planning is the task of computing robot trajectories that move a set of objects to their target configuration while satisfying physically feasibility.  ...  Extensive hardware experiments demonstrate our pipeline can produce robot trajectories that accomplish tasks with never-before-seen objects.  ...  ACKNOWLEDGEMENTS The authors would like to thank Lucas Manuelli and Peter Florence for their help regarding robot setup and insightful suggestion.  ... 
arXiv:1909.06980v1 fatcat:gc5p2ihydjetrjdhrwm2famf44

FFRob: Leveraging symbolic planning for efficient task and motion planning

Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Pack Kaelbling
2017 The international journal of robotics research  
This structure enables the EAS planner to efficiently compute heuristics that incorporate geometric and kinematic planning constraints to give a tight estimate of the distance to the goal.  ...  Symbolic task planners can efficiently construct plans involving many variables but cannot represent the geometric and kinematic constraints required in manipulation.  ...  Toussaint (2015) formulates task and motion planning as a logic-geometric program, a non-linear constrained optimization problem augmented with a logic and knowledge base.  ... 
doi:10.1177/0278364917739114 fatcat:2nccxehwvvbbjiljq73aq2fnhi

Automatic Synthesis of Fine-Motion Strategies for Robots

Tomás Lozano-Pérez, Matthew T. Mason, Russell H. Taylor
1984 The international journal of robotics research  
This paper describes a formal approach to the synthesis of compliant-motion strategies from geometric descriptions of assembly operations and explicit estimates of errors in sensing and control.  ...  Active compliance enables robots to carry out tasks in the presence of significant sensing and control errors. Compliant motions are quite difficult for humans to specify, however.  ...  Acknowledgments We would like to thank Rodney Brooks, Steve Buckley, and Mike Erdmann for their helpful comments on earlier drafts.  ... 
doi:10.1177/027836498400300101 fatcat:xinbhcc3m5enfm34xgjwqwz3h4

Combining task and motion planning: A culprit detection problem

Fabien Lagriffoul, Benjamin Andres
2016 The international journal of robotics research  
Solving problems combining task and motion planning requires to search across a symbolic search space and a geometric search space.  ...  Because of the semantic gap between symbolic and geometric representations, symbolic sequences of actions are not guaranteed to be geometrically feasible.  ...  ACKNOWLEDGMENTS This work was partially supported by EU FP7 project "Generalizing Robot Manipulation Tasks" (GeRT) [contract number 248273].  ... 
doi:10.1177/0278364915619022 fatcat:ytp6qchrzrekdcgnxkqwzgs2kq
« Previous Showing results 1 — 15 out of 1,008 results