Sie sind auf Seite 1von 32

OPTIMIZING PATH FOR

ROBOT MOVEMENT WITH


MOVING OBSTACLES
USING HYBRID
ALGORITHM
Under guidence
Dr. Pankaj Tomar
Sapna Verma
3rd sem(M.tech (R&A))
(0030208105)
OBJECTIVE
The research focuses on planning path for
robot in static and dynamic environment.
To develop and implement a Hybrid algorithm
for path planning for robot.
The approach is expressed to be able to
determine the Optimal feasible path for robot in
static and dynamic environment with static and
dynamic obstacles and compare the result of
previous approach & find out better solution..

INTRODUCTION
Path planning(navigation) : Path planning in robotics is
concerned with developing the logic for navigation of robot.
Path planning of a robot is to determine a collision-free path
from a starting point to a goal point optimizing a performance
criterion such as distance, time or energy.
Navigation(planning and following a route)
Primary function: 1.mission planner
2.path planning
3.map making
4. Localization
there are two categories of path planning algorithms,
namely off-line and on-line.
on-line or local path planning:
When complete information about environment is not
available in advance, mobile robot gets information
through sensors and plans its path as it moves through
the environment
off-line or global path planning:
Path planning of robots in environments where
complete information about static obstacles and
trajectory of moving obstacles are known in
advance.
Literature review
1) An Image Based Path Planning Using A-Star Algorithm
Heramb Nandkishor Joshi, Prof J. P. Shinde Dept. Of
Electronics and telecommunications STESs Sinhgad Academy
of Engg, Pune, India (May 2014).
The aim of this paper is to plan a path for autonomous robot, based on
image processing techniques in the unknown environment. The
proposed system finds and analyses an optimal path for a robots, while
avoiding obstacles along the way. The environment is first captured as
an image using a camera. Obstacles detecting methods are then
performed to identify the existence of obstacles within the unknown
environment. In this paper we focus on the application of space
exploration where Rocks and craters are recognized as obstacles and
then shortest path is obtain by A-Star algorithm.
2) Global Path Planning for Autonomous Mobile
Robot using Genetic Algorithm Masoud Samadi,
Mohd Fauzi Othman Center for Artificial
Intelligence and Robotics Universiti Teknologi
Malaysia Kuala Lumpur , Malaysia(2013),
In this work, a path planning method by utilizing genetic
algorithm (GA) is presented. The optimized path in terms
of length and cost is generated by GA optimization. The
proposed method is a global path planning method ,It
reads the map of the environment and plans the optimized
path by using GA method simulated in MATLAB R2012b
software. The simulation results are presented and
analyzed.
3) PATH PLANNING OF MOBILE ROBOT USING BASED
ARTIFICIAL NEURAL NETWORK(may 2013)
A. D. Dubey, R. B. Mishra and A. K. Jha, Dept. of Computer
Engineering, Indian Institute of Technology Banaras Hindu
University, Varanasi, India 3Dept. of Mechanical Engineering,
Indian Institute of Technology Banaras Hindu University, Varanasi,
India.
In this paper, we have applied a artificial neural network which is
used to determine a collision free shortest path of a mobile robot
from the initial point to the destination in an unknown environment.
In this paper we have created an Artificial Neural Network (ANN)
which is used to a path by its nonlinear functional approximation.
The training samples of this artificial neural network have been
collected by a reinforcement learning method known as Q learning.
This path planning algorithm has been devised using five state action
mapping relationship. The algorithm was applied on our designed
mobile robot manipulator and the results show that the path planning
done by this method was better than the path devised out by using
ANN and Q learning method separately.
4) Neural network and genetic algorithm based global
path planning in a static environment(2005) DU Xin
,CHEN Hua-hua , GU Wei-kang Department of
Information Science and Electronics Engineering,
Zhejiang University, Hangzhou 310027, China) (School
of Communication Engineering, Hangzhou Dianzi
University, Hangzhou 310018, China).
Robot global path planning in a static environment is an
important problem. The paper proposes a method of
global path planning based on neural network and genetic
algorithm. We constructed the neural network model of
environmental information in the workspace for a robot
and used this model to establish the relationship between
a collision avoidance path and the output of the model.
5) Solving Path Planning Problem by an ACO-PSO Hybrid
Algorithm Chunxue Shi, Yingyong Bu, Ziguang Li2 Jun
Tan(2007),School of Mechanical and Electronical Engineering, Center
South University, Changsha 410083, China,School of Mechanical and
Electronical Engineering, Changsha Science & Technology University,
Changsha, China.
An ACO-PSO Hybrid Algorithm Solving Path Planning Problem
based on Swarm Intelligence (SI) is proposed. The problem first is
described and some corresponding definitions are presented. Ant
colony optimization (ACO) is used to establish the corresponding
solution, and some material algorithm steps are set out. Particle swarm
optimization (PSO) is applied to optimize the parameters in ACO, and
parameters can be selected self- adaptively. Through the steps above,
algorithm performance can be greatly enhanced and the reliability of
parameters selecting can be guaranteed. At last simulation experiments
are carried out, and the results prove the veracity of the algorithm.
PATH PLANNING USING VREP
2Department of Mechanical Engineering, M.V.G.R. College of
Engineering, JNTU (KakinadaVizianagaram, Andhra Pradesh,
India,karteek968@gmail.com,praveenkalla@mvgrce.edu.in
The dynamics model is used rarely when the kinematics is
failed on V-REP's control methodology in V-REP, control is
distributed and based on an unlimited number of scripts that
are directly associated or attached to scene objects. Finally, in
order to further clarify elements introduced in the first and
second part of this paper, the third party describes via typical
VREP simulation software
METHODLOGY
We have many types of algorithms:
Algorithms is a process or set of rules to be followed in calculations
and other operation by computer.
A* algorithm
D* algorithm
Bug algorithm
Heuristics algorithm
Genetic algorithm
Ant colony algorithm
Djksarta algorithm
Simulate annealing algorithm
PSO algorithm
Bat algorithm
Neural network
Etc..
A* Algorithm
Uses heuristic to guide search
it will compute a path with minimum cost
A* computes the function f(n) = g(n) + h(n)
g(n)= actual cost
h(n)=estimate cost
g(n) = cost from the starting node to reach n
h(n) = estimate of the cost of the cheapest
path from n to the goal node
D* Algorithm
Solution to single source shortest path
problem in graph theory.
Both directed and undirected graphs
Graph must be connected
GENETIC Algorithm
A genetic algorithm (GA) is a method for
solving both constrained and unconstrained
optimization problems based on a natural
selection process that imitate biological
evolution. The algorithm repeatedly modifies a
population of individual solutions.
ANT Colony Algorithm
In computer science and operations research,
the ant colony optimization algorithm (ACO)
is a probabilistic technique for solving
computational problems which can be reduced
to finding good paths through graphs.
Neural network algorithm

Neural networks (also referred to as connectionist systems) are a


computational approach which is based on a large collection of
neural units loosely modeling the way a biological brain solves
problems with large clusters of biological neurons connected by
axons. Each neural unit is connected with many others, and links can
be enforcing or inhibitory in their effect on the activation state of
connected neural units. Each individual neural unit may have a
summation function which combines the values of all its inputs
together. There may be a threshold function or limiting function on
each connection and on the unit itself such that it must surpass it
before it can propagate to other neurons. These systems are self-
learning and trained rather than explicitly programmed and excel in
areas where the solution or feature detection is difficult to express in
a traditional computer program.
RESEARCH GAP STATEMENT
Path planning method such as visibility graph,
grids, etc are not suitable for planning path in
dynamic environment, so we can use genetic algo
method to deal with the path planning problem in
an dynamic environment with movable obstacles
but they have many drawback this algorithm so
we have used hybrid algo for path planning such
as GA/NN used for path planning.
Analysis three major factor
Safety
Accuracy
Efficiency
Time management
Cost estimation
Energy
Software/Tools used
MATLAB
PYTHON
V-RAP
V-REP
V-REP(Virtual Robot Experimentation Platform) is a Robotics
simulator of with a large capacity, features, and APIs (set of
functions and methods to be used by other software).
The V-REP Robot Simulator has an integrated development
environment (IDE) in which each model or object is based on a
distributed control architecture (can be controlled by an own script, a
plugin, a remote client application through its API, etc).This makes
the software an ideal multi-robot environment simulation platform.
The drivers for robots can be written in c and c++ Python, Java,
Lua ,Matlab or Urbi. The following list are just some of the
applications when using V-REP Simulation of automated
manufacturing systems.
RESULT
Future Scope
The implementation of hybrid algorithm for
path planning in dynamic environment with
moving obstacles. The approaches is simpler
and easier to implement, as the method is able
to quickly determine the optimal feasible path.
Heuristic method can use enhance the
efficiency of the hybrid algorithms.
APPLICATION
Space exploration
Medical field
Industrial
Underground
Self driving vehicle
Refernces
PATH PLANNING OF MOBILE ROBOT USING
REINFORCEMENT BASED ARTIFICIAL NEURAL
NETWORK A. D. Dubey, R. B. Mishra and A. K. Jha ,Dept. of
Computer Engineering, Indian Institute of Technology Banaras
Hindu University, Varanasi, India ,Dept. of Mechanical
Engineering, Indian Institute of Technology Banaras Hindu
University, Varanasi, India
An Image Based Path Planning Using A Star Algorithm
Heramb Nandkishor Joshi, Prof J. P. Shinde Dept. Of
Electronics and telecommunications STESs Sinhgad Academy of
Engg, Pune, India
Path Planning Optimization Using Genetic
Algorithm A Literature Review 1,Er. Waghoo
Parvez ,Er. Sonal Dhar, (Department of Mechanical
Engg. , Mumbai University, MHSSCOE , Mumbai,
(Department of Production Engg., Mumbai University,
DJSCOE, Mumbai .
Neural network and genetic algorithm based global
path planning in a static environment, DU Xin
,CHEN Hua-hua, GU Wei-kang (Department of
Information Science and Electronics Engineering,
Zhejiang University, Hangzhou, China),(School of
Communication Engineering, Hangzhou Dianzi
University, Hangzhou, China)
THANK YOU!

Das könnte Ihnen auch gefallen