A review of motion planning algorithms for intelligent robotics
This review provides a comprehensive understanding of motion planning algorithms for robotics researchers, aiming to clarify their advantages, disadvantages, and relationships.
This paper reviews motion planning algorithms for intelligent robotics, categorizing them into traditional planning, supervised learning, optimal value reinforcement learning, and policy gradient reinforcement learning. It introduces new criteria for evaluating these algorithms, analyzes the convergence speed and stability of reinforcement learning approaches, and discusses future research directions.
We investigate and analyze principles of typical motion planning algorithms. These include traditional planning algorithms, supervised learning, optimal value reinforcement learning, policy gradient reinforcement learning. Traditional planning algorithms we investigated include graph search algorithms, sampling-based algorithms, and interpolating curve algorithms. Supervised learning algorithms include MSVM, LSTM, MCTS and CNN. Optimal value reinforcement learning algorithms include Q learning, DQN, double DQN, dueling DQN. Policy gradient algorithms include policy gradient method, actor-critic algorithm, A3C, A2C, DPG, DDPG, TRPO and PPO. New general criteria are also introduced to evaluate performance and application of motion planning algorithms by analytical comparisons. Convergence speed and stability of optimal value and policy gradient algorithms are specially analyzed. Future directions are presented analytically according to principles and analytical comparisons of motion planning algorithms. This paper provides researchers with a clear and comprehensive understanding about advantages, disadvantages, relationships, and future of motion planning algorithms in robotics, and paves ways for better motion planning algorithms.