Open AccessProceedings Article
Using Gaussian process regression for efficient motion planning in environments with deformable objects
Barbara Frank,Cyrill Stachniss,Nichola Abdo,Wolfram Burgard +3 more
- 01 Jan 2011
- pp 2-7
TL;DR: The experiments show that the robot is able to accurately predict and thus consider the deformation cost its manipulator introduces to the environment during motion planning, and the computation time is substantially reduced compared to a system that performs physical simulations online.
read more
Abstract: The ability to plan their own motions and to reliably execute them is an important precondition for autonomous robots. In this paper, we consider the problem of planning the motion of a mobile manipulation robot in the presence of deformable objects in the environment. Our approach combines probabilistic roadmap planning with a deformation simulation system. Since the physical deformation simulation is computationally demanding, we use an efficient variant of Gaussian process regression to estimate the deformation cost for individual objects based on training examples. We generate the training data by employing a simulation system in a preprocessing step. Consequently, no simulations are needed during runtime. We implemented and tested our approach on a mobile manipulation robot. Our experiments show that the robot is able to accurately predict and thus consider the deformation cost its manipulator introduces to the environment during motion planning. Simultaneously, the computation time is substantially reduced compared to a system that performs physical simulations online.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Reaching in clutter with whole-arm tactile sensing
TL;DR: It is demonstrated that robots can use whole-arm tactile sensing to perceive clutter and maneuver within it, while keeping contact forces low, and a novel controller is presented that only requires haptic sensing, handles multiple contacts, and does not need an explicit model of the environment prior to contact.
Utility-Guided Palpation for Locating Tissue Abnormalities
Elif Ayvali,Alex Ansari,Long Wang,Nabil Simaan,Howie Choset +4 more
- 19 Jan 2017
TL;DR: The search approach, presented in this letter, incorporates prior information from preoperative images, which can provide an estimate for the location of suspicious sites, thereby reducing unnecessary manipulation and exploration of the organ.
24
Intelligent Hybridization of Regression Technique with Genetic Algorithm for Navigation of Humanoids in Complex Environments
TL;DR: To avoid inter-collision among multiple humanoids during their navigation in a common platform, a Petri-Net model has been proposed and an improvement in performance has been observed.
23
•Proceedings Article
Integrating vehicle routing and motion planning
Scott Kiesel,Ethan Burns,Christopher Makoto Wilt,Wheeler Ruml +3 more
- 25 Jun 2012
TL;DR: This paper presents an approach to the problem that arises in multi-vehicle mission planning based on a combination of tabu search, linear programming, and heuristic search, and demonstrates how integrating multiple diverse techniques can successfully solve challenging real-world planning problems that are beyond the reach of any single method.
Optimisation of hybrid tandem metal active gas welding using Gaussian process regression
TL;DR: In this paper, an additional filler wire with opposite polarity was inserted in tandem flux cored arc welding process to increase the welding speed and deposition rate, which was used for hybrid welding.
15
References
Probabilistic roadmaps for path planning in high-dimensional configuration spaces
Lydia E. Kavraki,P. Svestka,Jean-Claude Latombe,Mark H. Overmars +3 more
- 01 Aug 1996
TL;DR: Experimental results show that path planning can be done in a fraction of a second on a contemporary workstation (/spl ap/150 MIPS), after learning for relatively short periods of time (a few dozen seconds).
Cloth grasp point detection based on multiple-view geometric cues with application to robotic towel folding
Jeremy Maitin-Shepard,Marco F. Cusumano-Towner,Jinna Lei,Pieter Abbeel +3 more
- 03 May 2010
TL;DR: The reliability and robustness of this novel vision-based grasp point detection algorithm enables for the first time a robot with general purpose manipulators to reliably and fully-autonomously fold previously unseen towels.
GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models
Jonathan Ko,Dieter Fox +1 more
TL;DR: This paper shows how non-parametric Gaussian process (GP) regression can be used for learning such models from training data and how these models can be integrated into different versions of Bayes filters, namely particle filters and extended and unscented Kalman filters.
Leaving Flatland: Efficient real-time three-dimensional perception and motion planning
Radu Bogdan Rusu,Aravind Sundaresan,Benoit Morisset,Kris Hauser,Motilal Agrawal,Jean-Claude Latombe,Michael Beetz +6 more
TL;DR: The proposed system includes comprehensive localization, mapping, path planning, and visualization techniques for a mobile robot to operate autonomously in complex three-dimensional indoor and outdoor environments and is shown to be favorable for high-speed autonomous navigation.
251
Gaussian process modeling of large-scale terrain
TL;DR: The proposed model naturally provides a multiresolution representation of space, incorporates and handles uncertainties aptly, and copes with incompleteness of sensory information, and will perform very competitively with grid-based approaches using standard interpolation techniques and triangulated irregular networks using triangle-based interpolations.
213