Abstract

Providing mobile robots with autonomous capabilities is advantageous. It allows one to dispense with the intervention of human operators, which may prove beneficial in economic and safety terms. Autonomy requires, in most cases, the use of path planners that enable the robot to deliberate about how to move from its location at one moment to another. Looking for the most appropriate path planning algorithm according to the requirements imposed by users can be challenging, given the overwhelming number of approaches that exist in the literature. Moreover, the past review works analyzed here cover only some of these approaches, missing important ones. For this reason, our paper aims to serve as a starting point for a clear and comprehensive overview of the research to date. It introduces a global classification of path planning algorithms, with a focus on those approaches used along with autonomous ground vehicles, but is also extendable to other robots moving on surfaces, such as autonomous boats. Moreover, the models used to represent the environment, together with the robot mobility and dynamics, are also addressed from the perspective of path planning. Each of the path planning categories presented in the classification is disclosed and analyzed, and a discussion about their applicability is added at the end.

Highlights

  • Surveys on path planning do not offer a comprehensive overview of the majority of existing path planning solutions. This is the main motivation for writing this review paper: it describes in detail different path planning categories and, for each of them, introduces relevant representative references found in the literature, focusing on those algorithms aimed at robots that move on top of surfaces

  • The Dynamic Window Approach (DWA) is an algorithm that searches in the velocity space for a velocity command to follow a collision-free circular trajectory, delimited by admissible speed values and a time window [95]

  • Rapidly Random Tree (RRT), to later apply jt to an optimization process based on Differential Dynamic Programming (DP)

Read more

Summary

Introduction

The path generated by the planner must follow any imposed restrictions These may come from the limitations in the adaptability of the robot to certain terrains. The locomotion of the robot and the characteristics of the existing terrain limit the kind of manoeuvres that can be performed This reduces the number of feasible paths that the path planner can generate. Surveys on path planning do not offer a comprehensive overview of the majority of existing path planning solutions This is the main motivation for writing this review paper: it describes in detail different path planning categories and, for each of them, introduces relevant representative references found in the literature, focusing on those algorithms aimed at robots that move on top of surfaces (ground, water, etc.).

Path Planning Algorithms
General Classification
Path Planning Workspace Modeling
Environment Modeling
Robot–Surface Interaction Modeling
Reactive-Computing-Based Path Planning Algorithms
Reactive Manoeuvre
Local Optimization
Soft-Computing-Based Path Planning Algorithms
Evolutionary Computation
Artificial Intelligence
C-Space-Search-Based Path Planning Algorithms
Graph Search
Sampling-Based
Optimal-Control-Based Path Planning Algorithms
PDE-Solving-Based
Global Optimization
Summary and Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call