A Review of Deep Reinforcement Learning Algorithms for Mobile Robot Path Planning

Abstract

Path planning is the most fundamental necessity for autonomous mobile robots. Traditionally, the path planning problem was solved using analytical methods, but these methods need perfect localization in the environment, a fully developed map to plan the path, and cannot deal with complex environments and emergencies. Recently, deep neural networks have been applied to solve this complex problem. This review paper discusses path-planning methods that use neural networks, including deep reinforcement learning, and its different types, such as model-free and model-based, Q-value function-based, policy-based, and actor-critic-based methods. Additionally, a dedicated section delves into the nuances and methods of robot interactions with pedestrians, exploring these dynamics in diverse environments such as sidewalks, road crossings, and indoor spaces, underscoring the importance of social compliance in robot navigation. In the end, the common challenges faced by these methods and applied solutions such as reward shaping, transfer learning, parallel simulations, etc. to optimize the solutions are discussed.

Suboptimal Trajectory Planning Technique in Real UAV Scenarios with Partial Knowledge of the Environment

“…For this reason, even though approaches such as the probabilistic ones and those based on machine learning have been spreading more and more because of their promising performances in complex environments, the deterministic counterpart is still the best compromise. In fact, the others are more computational demanding, which makes them impractical for real-time applications [11]. This aspect is even more important when considering where these calculations must take place.…”

Path Planning for Autonomous Mobile Robot Using Intelligent Algorithms

“…The author suggests that the contribution of more than one sensor could improve the learning process, and at the same time, it would benefit the performance of mobile robots in real-world scenarios. Moreover, [17] addressed the potential of deep RL to help deploy robots to navigate uncertain environments.…”