Multi‐robot path planning based on a deep reinforcement learning DQN algorithm
Autor: | Peng Lingling, Yang Yang, Li Juntao |
---|---|
Rok vydání: | 2020 |
Předmět: |
0209 industrial biotechnology
multi-robot systems Computer Networks and Communications Computer science 02 engineering and technology scheduling system algorithm improved dqn algorithm converges deep q-network algorithm 020901 industrial engineering & automation mobile robots Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Reinforcement learning q-learning algorithm Motion planning classic deep reinforcement learning algorithm path planning algorithmic process Randomness lcsh:Computer software multirobot path planning volume-based technology robot path-planning problem Artificial neural network path-planning problems unmanned warehouse dispatching system Volume (computing) Process (computing) lcsh:P98-98.5 Mobile robot warehouse picking operation Human-Computer Interaction lcsh:QA76.75-76.765 Robot learning (artificial intelligence) 020201 artificial intelligence & image processing handling robot Computer Vision and Pattern Recognition lcsh:Computational linguistics. Natural language processing Algorithm Information Systems |
Zdroj: | CAAI Transactions on Intelligence Technology (2020) |
ISSN: | 2468-2322 |
Popis: | The unmanned warehouse dispatching system of the ‘goods to people’ model uses a structure mainly based on a handling robot, which saves considerable manpower and improves the efficiency of the warehouse picking operation. However, the optimal performance of the scheduling system algorithm has high requirements. This study uses a deep Q-network (DQN) algorithm in a deep reinforcement learning algorithm, which combines the Q-learning algorithm, an empirical playback mechanism, and the volume-based technology of productive neural networks to generate target Q-values to solve the problem of multi-robot path planning. The aim of the Q-learning algorithm in deep reinforcement learning is to address two shortcomings of the robot path-planning problem: slow convergence and excessive randomness. Preceding the start of the algorithmic process, prior knowledge and prior rules are used to improve the DQN algorithm. Simulation results show that the improved DQN algorithm converges faster than the classic deep reinforcement learning algorithm and can more quickly learn the solutions to path-planning problems. This improves the efficiency of multi-robot path planning. |
Databáze: | OpenAIRE |
Externí odkaz: |