|
|
|
|
| LEADER |
02648nam a2200553Ia 4500 |
| 001 |
10.1109-TNNLS.2022.3172168 |
| 008 |
220630s2022 CNT 000 0 und d |
| 020 |
|
|
|a 2162237X (ISSN)
|
| 245 |
1 |
0 |
|a Multiagent Soft Actor-Critic Based Hybrid Motion Planner for Mobile Robots
|
| 260 |
|
0 |
|b Institute of Electrical and Electronics Engineers Inc.
|c 2022
|
| 520 |
3 |
|
|a In this article, a novel hybrid multirobot motion planner that can be applied under no explicit communication and local observable conditions is presented. The planner is model-free and can realize the end-to-end mapping of multirobot state and observation information to final smooth and continuous trajectories. The planner is a front-end and back-end separated architecture. The design of the front-end collaborative waypoints searching module is based on the multiagent soft actor-critic (MASAC) algorithm under the centralized training with decentralized execution (CTDE) diagram. The design of the back-end trajectory optimization module is based on the minimal snap method with safety zone constraints. This module can output the final dynamic-feasible and executable trajectories. Finally, multigroup experimental results verify the effectiveness of the proposed motion planner. IEEE
|
| 650 |
0 |
4 |
|a Aerodynamics
|
| 650 |
0 |
4 |
|a Collaboration
|
| 650 |
0 |
4 |
|a Collaboration
|
| 650 |
0 |
4 |
|a Discrete waypoint searching
|
| 650 |
0 |
4 |
|a Discrete waypoints searching
|
| 650 |
0 |
4 |
|a hybrid motion planner
|
| 650 |
0 |
4 |
|a Hybrid motion planner
|
| 650 |
0 |
4 |
|a Industrial robots
|
| 650 |
0 |
4 |
|a Job analysis
|
| 650 |
0 |
4 |
|a Motion planners
|
| 650 |
0 |
4 |
|a Motion planning
|
| 650 |
0 |
4 |
|a Multi agent systems
|
| 650 |
0 |
4 |
|a Multipurpose robots
|
| 650 |
0 |
4 |
|a multirobot motion planning
|
| 650 |
0 |
4 |
|a Multi-robot motion planning
|
| 650 |
0 |
4 |
|a Multi-robot systems
|
| 650 |
0 |
4 |
|a Planning
|
| 650 |
0 |
4 |
|a Reinforcement learning
|
| 650 |
0 |
4 |
|a Reinforcement learning
|
| 650 |
0 |
4 |
|a reinforcement learning (RL)
|
| 650 |
0 |
4 |
|a Robot programming
|
| 650 |
0 |
4 |
|a Robot sensing system
|
| 650 |
0 |
4 |
|a Robot sensing systems
|
| 650 |
0 |
4 |
|a Robots
|
| 650 |
0 |
4 |
|a Task analysis
|
| 650 |
0 |
4 |
|a Task analysis
|
| 650 |
0 |
4 |
|a Trajectories
|
| 650 |
0 |
4 |
|a Trajectory optimization
|
| 650 |
0 |
4 |
|a Trajectory optimization
|
| 650 |
0 |
4 |
|a trajectory optimization.
|
| 650 |
0 |
4 |
|a Trajectory optimization.
|
| 650 |
0 |
4 |
|a Waypoints
|
| 700 |
1 |
0 |
|a Dong, L.
|e author
|
| 700 |
1 |
0 |
|a He, Z.
|e author
|
| 700 |
1 |
0 |
|a Song, C.
|e author
|
| 700 |
1 |
0 |
|a Sun, C.
|e author
|
| 773 |
|
|
|t IEEE Transactions on Neural Networks and Learning Systems
|
| 856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1109/TNNLS.2022.3172168
|
