Monte Carlo Uncertainty Characterization & Chance Constraint Design in Motion Planning for Fielded sUAS

2022 ◽  
Author(s):  
Katherine Glasheen ◽  
John J. Bird ◽  
Eric W. Frew
Keyword(s):  
Monte Carlo ◽  
Motion Planning ◽  
Chance Constraint ◽  
Uncertainty Characterization

On Receding Horizon Chance Constraint Motion Planning for Uncertain Multi-Agent Systems

2019 ◽  
Author(s):  
Yash Bagla ◽  
Vaibhav Srivastava
Keyword(s):  
Motion Planning ◽  
Autonomous Systems ◽  
Random Trees ◽  
Chance Constraint ◽  
Multi Agent Systems ◽  
Receding Horizon ◽  
Uncertain Environments ◽  
Uncertainty Model ◽  
Planning Algorithm ◽  
Multi Agent

Abstract We propose and study a motion planning algorithm for multi-agent autonomous systems to navigate through uncertain and dynamic environments. We use a receding horizon chance constraint framework that allows for tuning the trade-off between the risk of collision and the infeasibility of paths. We consider sampling-based incremental planning algorithms and extend them to the case of multiple agents and dynamic and uncertain environments. The receding horizon control framework is used to incorporate sensor measurements at a fixed interval of time to reduce uncertainty about agents’ state and environment. Our presentation focuses on rapidly-exploring random trees (RRTs) and the assumption of Gaussian noise in the uncertainty model. Our algorithm is illustrated using several examples.

Goal-directed robot manipulation through axiomatic scene estimation

2017 ◽  
Vol 36 (1) ◽  
pp. 86-104 ◽  
Author(s):  
Zhiqiang Sui ◽  
Lingzhu Xiang ◽  
Odest C Jenkins ◽  
Karthik Desingh
Keyword(s):  
Monte Carlo ◽  
Markov Chain ◽  
Markov Chain Monte Carlo ◽  
Motion Planning ◽  
Autonomous Robots ◽  
Autonomous Control ◽  
Ideal Case ◽  
Robot Manipulation ◽  
Goal State ◽  
Scene Graph

Performing robust goal-directed manipulation tasks remains a crucial challenge for autonomous robots. In an ideal case, shared autonomous control of manipulators would allow human users to specify their intent as a goal state and have the robot reason over the actions and motions to achieve this goal. However, realizing this goal remains elusive due to the problem of perceiving the robot’s environment. We address and describe the problem of axiomatic scene estimation for robot manipulation in cluttered scenes which is the estimation of a tree-structured scene graph describing the configuration of objects observed from robot sensing. We propose generative approaches to scene inference (as the axiomatic particle filter, and the axiomatic scene estimation by Markov chain Monte Carlo based sampler) of the robot’s environment as a scene graph. The result from AxScEs estimation are axioms amenable to goal-directed manipulation through symbolic inference for task planning and collision-free motion planning and execution. We demonstrate the results for goal-directed manipulation of multi-object scenes by a PR2 robot.

scholarly journals Review of mobile robots obstacle avoidance, localization, motion planning, and wheels

2020 ◽  
Vol 20 (2) ◽  
pp. 768
Author(s):  
Mustafa A. Mhawesh ◽  
Zaid H. Al-Tameemi ◽  
Omar Muhammed Neda
Keyword(s):  
Monte Carlo ◽  
Motion Planning ◽  
Mobile Robots ◽  
Obstacle Avoidance ◽  
Dynamic Networks ◽  
Ultrasonic Sensors ◽  
Obstacle Avoiding ◽  
Planning Framework ◽  
Monte Carlo Localization ◽  
Recorded Data

<span>The main objective of this research is to study the obstacle avoidance, Monte Carlo Localization (MCL) method, motion planning in dynamic networks for mobile robots, and mobile robots wheels depending on the previous published researches. The researchers had done their experiments on different mobile robots and had validated them. This research helps the readers to learn how the robot changes its directions to prevent itself from collisions depending on three ultrasonic sensors. Also, they will learn the localization of the mobile robots depending on the recorded data from RHINO and MINERVA robots. In addition to learning the obstacle avoiding and the localization of mobile robots, the readers will learn new planning framework. Furthermore, they will get knowledge in types of mobile robots wheels.</span>

Sign in / Sign up

Export Citation Format

Share Document