Corpus ID: 8132328

Integration of 3D Object Recognition and Planning for Robotic Manipulation: A Preliminary Report

  title={Integration of 3D Object Recognition and Planning for Robotic Manipulation: A Preliminary Report},
  author={Damien Jade Duff and Esra Erdem and Volkan Patoglu},
We investigate different approaches to integrating object recognition and planning in a tabletop manipulation domain with the set of objects used in the 2012 RoboCup@Work competition. Results of our preliminary experiments show that, with some approaches, close integration of perception and planning improves the quality of plans, as well as the computation times of feasible plans. 
Optimal global planning for cognitive factories with multiple teams of heterogeneous robots
A formal framework is introduced that provides methods to diagnose failures due to broken robots, and to handle changes in manufacturing orders and in workspaces, and proves the optimality of the global plan. Expand
Finding optimal feasible global plans for multiple teams of heterogeneous robots using hybrid reasoning: an application to cognitive factories
It is proved that the optimal coordination problem is NP-complete, and a solution is described using automated reasoners, to find an optimal global plan for multiple teams. Expand
Hybrid Reasoning for Teams of Heterogeneous Robots: Finding an Optimal Feasible Global Plan
We address two key challenges of domains including teams of heterogeneous robots, hybrid reasoning for each team and finding an optimal global plan for multiple teams, by utilizing state-of-the-artExpand
Cognitive factories with multiple teams of heterogeneous robots: Hybrid reasoning for optimal feasible global plans
This work forms the problem of finding an optimal coordination of teams that can help each other, proves its intractability, and describes how to solve this problem using existing automated reasoners. Expand


Planning to see: A hierarchical approach to planning visual actions on a robot using POMDPs
This work defines a novel hierarchical POMDP-based approach for visual processing management and shows empirically that HiPPo and CP outperform the naive application of all visual operators on all ROIs and produces more robust plans than CP or the naive visual processing. Expand
Levels of Integration between Low-Level Reasoning and Task Planning
A systematic analysis of levels of integration between discrete high-level reasoning and continuous low- level reasoning to address hybrid planning problems in robotics and performs experiments on hybrid planning Problems in robotic manipulation and legged locomotion domains. Expand
Composition of Image Analysis Processes Through Object-Centered Hierarchical Planning
This paper presents a new approach to the knowledge-based composition of processes for image interpretation and analysis that provides a relatively general design or planning framework, within which problem specific image analysis and recognition processes can be generated more efficiently and effectively. Expand
3D is here: Point Cloud Library (PCL)
  • R. Rusu, S. Cousins
  • Engineering, Computer Science
  • 2011 IEEE International Conference on Robotics and Automation
  • 2011
PCL (Point Cloud Library) is presented, an advanced and extensive approach to the subject of 3D perception that contains state-of-the art algorithms for: filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation. Expand
Combining perception and knowledge processing for everyday manipulation
Key features of K-COPMAN are that it can make a robot environment-aware and that it supports goal-directed as well as passive perceptual processing. Expand
Combining high-level causal reasoning with low-level geometric reasoning and motion planning for robotic manipulation
A formal framework that combines high-level representation and causality-based reasoning with low-level geometric reasoning and motion planning with an application to robotic manipulation, and embeds geometric reasoning in causal reasoning. Expand
Borg: A Knowledge-Based System for Automatic Generation of Image Processing Programs
To develop a system that automates the generation of image processing applications, it is suggested to use a knowledge-rich resolution model and to integrate seven design rules. Expand
Automated software module reconfiguration through the use of artificial intelligence planning techniques
An approach is described to enable novices to use complex software libraries and the interactions between, and requirements of, the software modules are represented in a declarative language based on artificial intelligence (AI) planning techniques. Expand
Fast Point Feature Histograms (FPFH) for 3D registration
This paper modifications their mathematical expressions and performs a rigorous analysis on their robustness and complexity for the problem of 3D registration for overlapping point cloud views, and proposes an algorithm for the online computation of FPFH features for realtime applications. Expand
Causal Theories of Action and Change
A mathematically simple language for expressing knowledge of this kind of causal knowledge is defined and a general approach to formalizing action domains in it is described. Expand