An Overview of Nature-Inspired, Conventional, and Hybrid Methods of Autonomous Vehicle Path Planning

Table 3

Summary of strengths and challenges of hybrid mobile robot path planning and obstacle avoidance methods.

Approach	Major Implementation	Strengths	Challenges
Neuro Fuzzy	Simulation and real Experiment	Takes advantage of the strengths of NN and Fuzzy logic while reducing the drawbacks of both methods. Example: NN can help tune the rule base of fuzzy logic which is difficult using fuzzy logic alone [145, 232]	Unsatisfactory control performance and difficulty of reducing the effect of uncertainty and oscillation of T1FNN [101]
Others (Kalman Filter and Fuzzy logic, Visual Based and APF, Wall following and Fuzzy Logic, Fuzzy logic and Q-Learning, GA and NN, APF and SA, APF and Visual Servoing, APF and Ant Colony, Fuzzy and A, Reinforcement and computer graphics and computer vision, PSO and Gravitational search, etc)	Simulation and real Experiments	The drawbacks of each approach in the combination is reduced. Example: Improves noise resistance ability, deal better with oscillation and data uncertainties [131, 271–273] and controlling local minima problem associated with APF [36]	Noise from sensor and cameras and the hardware constraints including the limitation of motor speed, imbalance mass of the robot, power supply to the motors and many others affects the practical performance of these approaches.