1 On Complete Coverage Path Planning Algorithms for Non-holonomic Mobile Robots: Survey and Challenges Amna Khan 1 , Iram Noreen 2 , Zulfiqar Habib 3 Department of Computer Science, COMSATS Institute of Information Technology, Lahore 1 amna.cs@gmail.com, 2 iramnoreen@gmail.com, 3 drzhabib@ciitlahore.edu.pk Abstract The problem of determining a collision free path within a region is an important area of research in robotics. One significant aspect of this problem is coverage path planning, which is a process to find a path that passes through each reachable position in the desired area. This task is fundamental to many robotic applications such as cleaning, painting, underwater operations, mine sweeping, lawn mowing, agriculture, monitoring, searching, and rescue operations. The total coverage time is significantly influenced by total number of turns, optimization of backtracking sequence, and smoothness in the complete coverage path. There is no comprehensive literature review on backtracking optimization and path smoothing techniques used in complete coverage path planning. Although the problem of coverage path planning has been addressed by many researchers. However, existing state of the art needs to be significantly improved, particularly in terms of accuracy, efficiency, robustness, and optimization. This paper aims to present the latest developments, challenges regarding backtracking sequence optimization, smoothness techniques, limitations of existing approaches, and future research directions. Keywords: Complete coverage path, non-holonomic, mobile robots, backtracking optimization, path smoothness. 1. Introduction Complete Coverage Path Planning (CCPP) is the problem of finding a path that passes through all the points in the workspace from a starting point to a final point while avoiding obstacles. CCPP is a fundamental problem in robotics with numerous applications in real world such as demining [1] , agriculture and farming [2], cleaning [3, 4], inspection of complex structures [5], seabed mining [6], and underwater operations to name a few. Coverage efficiency of a CCPP algorithm is determined by total coverage ratio, total time required for complete coverage, total path length and energy consumption required to cover the path [3, 7]. Generally, the coverage algorithms are categorized as offline and online algorithms [8]. Offline coverage algorithms use fixed information and environment is known in advance. Complete coverage planned by genetic algorithms, neural networks, cellular decomposition, spanning trees, spiral filling paths and ant colony method falls in this category [4]. Whereas, online coverage algorithms use real time measurements and decisions to sweep the entire target area. In online approaches complete environment map can only be generated by the robot’s exploration such as executing an action and observing the consequences of these actions. Sensor based approaches are popular candidate for this category. In CCPP, two standard basic motions are followed to perform coverage, 1) the square spiral motions, and 2) the boustrophedon (back-and-forth) motion (see Fig. 1). The main advantage of these basic motions is that they can cover region of any shape and can be used as a base for more complex movements particularly in an environment full of obstacles. A CCPP algorithm is complete if the robot sweeps the workplace such that union of all the sub-trajectories completely covers the workplace in finite time. A CCPP algorithm is robust if it is complete and at least one active robot performs the coverage task. A CCPP algorithm is non- overlapping if the robot does not cover the already covered area [9].