137documents trouvés
Models for safe and legible manipulator trajectories. D2.1
T.SIMEON, J.CORTES, E.A.SISBOT, M.GHARBI, R.ALAMI
RIS
Rapport de Contrat : Projet Européen PHRIENDS. FP6-045359, Octobre 2007, 14p. , N° 07840
Diffusion restreinte
118806Stochastic motion roadmaps for planning with motion uncertainty
T.SIMEON, K.GOLDBERG, R.ALTEROVITZ
RIS, Berkeley
Conférence invitée : Invited Paper. IROS 2007, Workshop on Algorithmic Motion Planning, San Diego (USA), 29 Octobre - 2 Novembre 2007, 4p. , N° 07483
Diffusable
Plus d'informations
Abstract
In many motion planning applications ranging from maneuvering vehicles over unfamiliar terrain to steering flexible medical needles through human tissue, the response of a robot to commanded actions cannot be precisely predicted. We present a new motion planning framework, the Stochastic Motion Roadmap (SMR), that explicitly considers uncertainty in robot motion to maximize the probability of avoiding collisions and successfully reaching a goal. In the framework, we first build a roadmap by sampling collision-free states in the configuration space and then locally sample motions at each state to estimate state transition probabilities for each possible action. Given a query, we use the roadmap to formulate a Markov Decision Process (MDP), which we solve using dynamic programming to compute stochastically optimal plans. The SMR thus combines a sampling-based roadmap representation of the configuration space, as in PRM's, with the well-established theory of MDP's. We present initial results for a non-homolonomic mobile robot with bang-bang steering and demonstrate that SMR's generate motion plans with significantly higher probabilities of success compared to traditional shortest-path plans.
Provably safe motions strategies for mobile robots in dynamic domains
R.ALAMI, K.MADHAVA KRISHNA, T.SIMEON
RIS
Ouvrage (contribution) : Autonomous navigation in dynamic environments , Springer tracts in advanced robotics 35, Springer, N°ISBN 978-3-540-73421-5, 2007, pp.85-106 , N° 07422
Diffusable
111126The stochastic motion roadmap: a sampling framework for planning with Markov motion uncertainty
R.ALTEROVITZ, T.SIMEON, K.GOLDBERG
RIS, Berkeley
Manifestation avec acte : Robotics: Science and Systems, Atlanta (USA), 27-30 Juin 2007, 8p. , N° 07020
Diffusable
Plus d'informations
Abstract
We present a new motion planning framework that explicitly considers uncertainty in robot motion to maximize the probability of avoiding collisions and successfully reaching a goal. In many motion planning applications ranging from maneuvering vehicles over unfamiliar terrain to steering flexible medical needles through human tissue, the response of a robot to commanded actions cannot be precisely predicted. We propose to build a roadmap by sampling collision-free states in the configuration space and then locally sampling motions at each state to estimate state transition probabilities for each possible action. Given a query specifying initial and goal configurations, we use the roadmap to formulate a Markov Decision Process (MDP), which we solve using Infinite Horizon Dynamic Programming in polynomial time to compute stochastically optimal plans. The Stochastic Motion Roadmap (SMR) thus combines a sampling-based roadmap representation of the configuration space, as in PRM's, with the well-established theory of MDP's. Generating both states and transition probabilities by sampling is far more flexible than previous Markov motion planning approaches based on problem-specific or grid-based discretizations. We demonstrate the SMR framework by applying it to non-holonomic steerable needles, a new class of medical needles that follow curved paths through soft tissue, and confirm that SMR's generate motion plans with significantly higher probabilities of success compared to traditional shortest-path plans.
Disassembly path planning for objects with articulated parts
J.CORTES, T.SIMEON
RIS
Manifestation avec acte : IFAC International Workshop on Intelligent Assembly and Disassembly (IAD'07), Alicante (Espagne), 23-25 Mai 2007, pp.34-39 , N° 07022
Diffusable
Plus d'informations
Abstract
Sampling-based path planning algorithms are powerful tools for computing disassembly motions. This paper presents a variant of the RRT algorithm particularly devised for the disassembly of objects with articulated parts. Configuration parameters generally play two different roles in this type of problems: some of them are essential for the disassembly task, while others only need to move if they hinder the progress of the disassembly process. The proposed method is based on such a partition of the configuration parameters. Results show a remarkable performance improvement compared to standard path planning techniques.
Molecular disassembly with RRT-like algorithms
J.CORTES, L.JAILLET, T.SIMEON
RIS
Manifestation avec acte : 2007 IEEE International Conference on Robotics and Automation (ICRA'07) , Rome (Italie), 10-14 Avril 2007, pp.3301-3306 , N° 06600
Diffusable
Plus d'informations
Abstract
This paper addresses the problem of computing pathways for a ligand to exit from the active site of a protein. Such problem can be formulated as a mechanical disassembly problem for two articulated objects. Its solution requires searching paths in a constrained high-dimensional configurationspace. Indeed, the ligand passageway inside the protein is often extremely cluttered so that current path planning techniques are unable to solve the disassembly problem in reasonable computing time. The techniques presented in this paper are based on the RRT algorithm. First we discuss some simple and general modifications of the basic algorithm that significantly improve its performance. Then we describe a new variant of the planner that treats ligand and protein degrees of freedom separately. This new algorithm outperforms the basic RRT, particularly for very constrained problems, and is able to handle models with hundreds of degrees of freedom.We analyze the effects of each RRT variant via several examples of different complexity. Although discussions and results of this paper focus on molecular models, the ideas behind the algorithms are general and can be applied to path planners for disassembling articulated mechanical parts.
A robotic-based path planning approach for computing large-amplitude motions of flexible molecules
J.CORTES, T.SIMEON
RIS, RIA
Manifestations avec acte à diffusion limitée : 3ème Journées Annuelle "GénoToul" (GénoToul'2006), Toulouse (France), 23 Novembre 2006, pp.58-61 , N° 06787
Diffusable
108542A mobile robot that performs human acceptable motions
E.A.SISBOT, L. F.MARIN URIAS, R.ALAMI, T.SIMEON
RIA
Manifestation avec acte : 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'2006), Beijing (Chine), 9-12 Octobre 2006, pp.1811-1816 , N° 06163
Diffusable
107967Path deformation roadmaps
L.JAILLET, T.SIMEON
RIA
Manifestation avec acte : 7th International Workshop on the Algorithmic Foundations of Robotics (WAFR'2006), New York City (USA), 16-18 Juillet 2006, 17p. , N° 06126
Diffusable
108345How may I serve you ? A robot companion approaching a seated person in a helping context
K.DAUTENHAHN, M.WALTERS, S.WOODS, K.L.KOAY, C.NEHANIV, E.A.SISBOT, R.ALAMI, T.SIMEON
Hertfordshire, RIA
Manifestation avec acte : 2006 Conference on Human-Robot Interaction (HRI'06), Salt Lake City (USA), 2-3 Mars 2006, 8p. , N° 06025
Diffusable
106445