Loading...

Dynamic Motion Planning and Obstacle Avoidance Simulation for Autonomous Robot-car in Webots

Amiryan, Javad | 2014

1709 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 46197 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Jamzad, Mansour
  7. Abstract:
  8. Motion planning in an autonomous vehicle is responsible for providing smooth, safe and efficient actions. Besides reducing the risk of collision with static and moving obstacles, the ability to make suitable decisionsencountering sudden changes in environment is very important. Many solutions for dealing this problem have been offered, one of which is, Artificial Potential Fields (APF). APF is a simple and computationally low cost method which keeps the robot away from the obstacles in the environment. However, this approach suffers from trapping in local minima’s of potential function and then fails to produce a plan. Furthermore,Oscillation in presence of obstacles or in narrow passages is another disadvantageof the method which makes it unqualified for autonomous driving. In this thesis we aim to resolve these deficiencies by a novel approach which employs a prior path between the origin and the goal configuration of robot.Therefore, it is guaranteed that the planner output leads the robot to goal area while the inherent advantages of potential fields remain. For path planning step, we intendto use randomized sampling methods such as Rapidly-exploring Random Trees (RRT) or its derivatives. We have also designed an adaptation procedure for evolving the motion plans towards optimal solution. Then multi objective optimization is applied to find smoother, safer and shorter plans. Additionally, we apply a simulated vehicle in Webots PRO to test and evaluate the motion planner. Our experiments proves our method to enjoy improving the performance and speed in comparison to already existing approaches
  9. Keywords:
  10. Robot ; Motion Planning ; Artificial Potential Field ; Multiobjective Optimization ; Obstacle Avoidance ; Webots Simulation

 Digital Object List

 Bookmark

...see more