Trajectory optimization and obstacle avoidance of autonomous robot using Robust and Efficient Rapidly Exploring...

Area of Science:

• Robotics
• Artificial Intelligence
• Autonomous Systems

Background:

• Motion planning is a critical challenge in robotics, particularly for autonomous vehicles.
• Existing sampling-based algorithms have limitations like slow convergence and high computational complexity.
• These limitations hinder efficient navigation in complex environments.

Purpose of the Study:

• To address the limitations of current sampling-based motion planning algorithms.
• To propose a novel algorithm, RE-RRT*, for robust and efficient path-finding.
• To improve trajectory planning and obstacle avoidance for autonomous vehicles.

Main Methods:

• Developed the Robust and Efficient RRT* (RE-RRT*) algorithm, a novel sampling-based path-finding approach.
• Implemented sampling along the displacement from initial to goal points to constrain the sample space.
• Utilized Choose Parent and Rewire processes for continuous path optimization.

Main Results:

• RE-RRT* demonstrates faster convergence to shorter paths with fewer iterations.
• The algorithm significantly reduces redundant searches and improves sampling space efficiency.
• Experimental results show superior performance over existing methods in computational time, speed, and stability.

Conclusions:

• The RE-RRT* algorithm effectively overcomes the limitations of traditional sampling-based methods.
• This approach offers a more efficient and stable solution for autonomous vehicle motion planning.
• The proposed method enhances navigation capabilities in complex, obstacle-ridden environments.