3,126 Hits in 7.1 sec

Topology-Guided Path Integral Approach for Stochastic Optimal Control in Cluttered Environment [article]

Jung-Su Ha and Soon-Seo Park and Han-Lim Choi
2018 arXiv   pre-print
This paper addresses planning and control of robot motion under uncertainty that is formulated as a continuous-time, continuous-space stochastic optimal control problem, by developing a topology-guided  ...  path integral control method.  ...  Acknowledgment This work was supported by Agency for Defense Development (under contract #UD150047JD).  ... 
arXiv:1603.05099v2 fatcat:vsjjoyvpk5aqliihd43uqjs6ia

Probabilistic Safety Programs [article]

Ashish Kapoor, Debadeepta Dey, Shital Shah
2016 arXiv   pre-print
Achieving safe control under uncertainty is a key problem that needs to be tackled for enabling real-world autonomous robots and cyber-physical systems.  ...  We propose to perform these evaluations by first compiling the PSP to a graphical model then using a fast variational inference algorithm.  ...  (a) RRT* tree (red) generated from current position. (b) Using PSP to prune unsafe regions of the tree. (c) Shortest path in safe tree found towards goal node.  ... 
arXiv:1610.05376v1 fatcat:fnpisodjkfesfdsqrpwqjex4xu

The Value of Planning for Infinite-Horizon Model Predictive Control [article]

Nathan Hatch
2021 arXiv   pre-print
In these problems, MPC is often formulated to track a path or trajectory returned by a planner.  ...  Model Predictive Control (MPC) is a classic tool for optimal control of complex, real-world systems.  ...  Even though it cannot take shortcuts along the planned path like MPPI can, it seems like the stochasticity of MPPI (or its ability to account for and avoid obstacles when the planned path goes near them  ... 
arXiv:2104.02863v1 fatcat:tmnoz5jpvvfo7ft34ejgmk73cm

Motion planning in high-dimensional spaces [article]

Luka Petrović
2018 arXiv   pre-print
The increased use of high DOF robots that must perform tasks in real time in complex dynamic environments spurs the need for fast motion planning algorithms.  ...  In this overview, we discuss several types of strategies for motion planning in high dimensional spaces and dissect some of them, namely grid search based, sampling based and trajectory optimization based  ...  There are two common paradigms for successful motion planning. The first paradigm separates motion planning into path planning and path execution.  ... 
arXiv:1806.07457v2 fatcat:c5g37frxgbhldauf3qz5letup4

3D planning and trajectory optimization for real-time generation of smooth MAV trajectories

Matthias Nieuwenhuisen, Sven Behnke
2015 2015 European Conference on Mobile Robots (ECMR)  
Complex indoor and outdoor missions for autonomous micro aerial vehicles (MAV) constitute a demand for fast generation of collision-free paths in 3D space.  ...  Our approach utilizes coarse grid-based path planning with an approximate model of flight dynamics to determine collision-free trajectories.  ...  ACKNOWLEDGMENT This work was funded by the German Federal Ministry for Economic Affairs and Energy (BMWi) in the Autonomics for Industry 4.0 project InventAIRy.  ... 
doi:10.1109/ecmr.2015.7324217 dblp:conf/ecmr/NieuwenhuisenB15 fatcat:fkghse26pvf7va35ynohw433ya

An Efficient Stochastic Constrained Path Planner for Redundant Manipulators

Arturo Gil Gil Aparicio, Jaime Valls Valls Miro
2021 Applied Sciences  
The proposed Stochastic Constrained Optimization (SCO) solution remains close to optimal whilst exhibiting computational tractability, being an attractive proposition for implementation on real robots,  ...  along a task-space trajectory in the presence of obstacles.  ...  A significant branch of stochastic planners is based on Rapidly-exploring Random Trees (RRTs) [13] .  ... 
doi:10.3390/app112210636 fatcat:a5qzja3v2bhapprlb3xjul44zy

Addressing cost-space chasms in manipulation planning

Dmitry Berenson, Thierry Simeon, Siddhartha S. Srinivasa
2011 2011 IEEE International Conference on Robotics and Automation  
Such chasms are particularly common in planning for manipulators because many useful cost functions induce narrow or lowerdimensional low-cost areas.  ...  Finding paths in high-dimensional spaces becomes difficult when we wish to optimize the cost of a path in addition to obeying feasibility constraints.  ...  We have also described general cost functions in workspace, task space, and C-space that are useful for manipulation planning and that induce such cost-space chasms.  ... 
doi:10.1109/icra.2011.5979797 dblp:conf/icra/BerensonSS11 fatcat:422swal53fclhbdmxcddcfpgwq

Cross-entropy motion planning

Marin Kobilarov
2012 The international journal of robotics research  
A method for computing high-quality trajectories is proposed building upon recent developments in sampling-based motion planning and stochastic optimization.  ...  The cross-entropy method is combined with recent optimal motion planning methods such as the rapidly exploring random trees (RRT * ) in order to handle complex environments.  ...  Acknowledgements The author thanks the reviewers for the useful directions for improving the paper.  ... 
doi:10.1177/0278364912444543 fatcat:i4uhlrv7inej5eycb422dwjrka

Systematic Literature Review of Sampling Process in Rapidly-exploring Random Trees

Luiz Gustavo Veras, Felipe Medeiros, Lamartine Guimaraes
2019 IEEE Access  
One of the most wide algorithms used for this purpose is the rapidly-exploring random tree (RRT), in which each node of a tree data structure is generated from a search space by a random sampling process  ...  INDEX TERMS Non-uniform sampling, informed sampling, path planning, RRT, systematic literature review.  ...  RAPIDLY-EXPLORING RANDOM TREE (RRT) The RRT algorithm for path planning is described in Alg. 1.  ... 
doi:10.1109/access.2019.2908100 fatcat:n4nxxpquurcmlaeayjrnmlcxru

LQG-obstacles: Feedback control with collision avoidance for mobile robots with motion and sensing uncertainty

Jur van den Berg, David Wilkie, Stephen J. Guy, Marc Niethammer, Dinesh Manocha
2012 2012 IEEE International Conference on Robotics and Automation  
We integrate a Kalman filter for state estimation and an LQR feedback controller into a closed-loop dynamics model of which a higher-level control objective is the "control input".  ...  environments with obstacles and narrow passages.  ...  In general, planning for more noise allowed smoother, gentler paths. 3) Timing Results: A benefit of LQG-Obstacles is the ability to run fast enough for feedback control.  ... 
doi:10.1109/icra.2012.6224648 dblp:conf/icra/BergWGNM12 fatcat:bqlbxydlgncwjpg6grplpombza

3D path planning and execution for search and rescue ground robots

Francis Colas, Srivatsa Mahesh, Francois Pomerleau, Ming Liu, Roland Siegwart
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In this article, we present a system that is able to plan and execute a path in a complex environment starting from noisy sensor input.  ...  One milestone for autonomous mobile robotics is to endow robots with the capability to compute the plans and motor commands necessary to reach a defined goal position.  ...  ACKNOWLEDGMENT The authors thank Andreas Breitenmoser, Martin Rufli and Elena Stumm for their most valuable input and discussions. And Stéphane Magnenat for his thorough review of the paper.  ... 
doi:10.1109/iros.2013.6696431 dblp:conf/iros/ColasMPLS13 fatcat:co2nmasfirbslbjjuxtoknbsjq

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs [article]

Rohan Chitnis, Tom Silver, Beomjoon Kim, Leslie Pack Kaelbling, Tomas Lozano-Perez
2020 arXiv   pre-print
Our experiments consider five planners across four domains, including robotic navigation among movable obstacles (NAMO), robotic task and motion planning for sequential manipulation, and classical planning  ...  We observe that (1) imposing a constraint can induce context-specific independences that render some aspects of the domain irrelevant, and (2) an agent can take advantage of this fact by imposing constraints  ...  Acknowledgments We would like to thank Kelsey Allen for valuable comments on an initial draft.  ... 
arXiv:2007.13202v3 fatcat:7l746gpd7reppgr6fyqhkx7u6e

Control Barrier Function Augmentation in Sampling-based Control Algorithm for Sample Efficiency [article]

Chuyuan Tao, Hunmin Kim, Hyungjin Yoon, Naira Hovakimyan, Petros Voulgaris
2021 arXiv   pre-print
For a nonlinear stochastic path planning problem, sampling-based algorithms generate thousands of random sample trajectories to find the optimal path while guaranteeing safety by Lagrangian penalty methods  ...  However, the sampling-based algorithm can perform poorly in obstacle-rich environments because most samples might violate safety constraints, invalidating the corresponding samples.  ...  Notation Description t Time index for path-planning. i Sample index for path-planning. x i t τi Sample trajectory when the index is i. V Real control input sequence.  ... 
arXiv:2111.06974v1 fatcat:acnrkpmuhzdabil2pndpau4oea

Regression-based LP solver for chance-constrained finite horizon optimal control with nonconvex constraints

Ashis Gopal Banerjee, Masahiro Ono, Nicholas Roy, Brian C. Williams
2011 Proceedings of the 2011 American Control Conference  
The aim of this work is to significantly reduce the computation time of the previous algorithm so that it can be applied to practical problems, such as a path planning with multiple obstacles.  ...  Matrix transformations and boosting trees are then applied to generate learning models; fast inference is performed at run-time for new but similar FRR problems that occur when the system dynamics and/  ...  ACKNOWLEDGMENTS We would like to thank Michael Kerstetter, Scott Smith, Ronald Provine, and the Boeing Company for their support.  ... 
doi:10.1109/acc.2011.5990937 fatcat:dga7g5c72zdljkemcpxkdxr5vm

Finding Coordinated Paths for Multiple Holonomic Agents in 2-d Polygonal Environment [article]

Pavel Janovský and Michal Čáp and Jiří Vokřínek
2014 arXiv   pre-print
We focus on the problem of finding continuous coordinated paths for multiple mobile disc agents in a 2-d environment with polygonal obstacles.  ...  We compare the performance of a widely-used reactive method ORCA with three variants of a popular planning algorithm RRT* applied to multi-agent path planning and find that an algorithm combining reactive  ...  RRT* FOR MULTI-AGENT PATH FIND-ING The RRT* algorithm was originally designed for singleagent motion planning, however, it can be adapted to solve multi-agent path planning problems.  ... 
arXiv:1402.3613v1 fatcat:t5qcantgofarjgbe2zvdktwchy
« Previous Showing results 1 — 15 out of 3,126 results