The aerial manipulator (AM) is a systematic operational robotic platform in high standard on algorithm robustness. Directly deploying the algorithms to the practical system will take numerous trial and error costs and even cause destructive results. In this paper, a new modular simulation platform is designed to evaluate aerial manipulation related algorithms before deploying. In addition, to realize a fully autonomous aerial grasping, a series of algorithm modules consisting a complete workflow are designed and integrated in the simulation platform, including perception, planning and control modules. This framework empowers the AM to autonomously grasp remote targets without colliding with surrounding obstacles relying only on on-board sensors. Benefiting from its modular design, this software architecture can be easily extended with additional algorithms. Finally, several simulations are performed to verify the effectiveness of the proposed system.
翻译:空中操纵器(AM)是一个系统操作的机器人平台,在算法稳健性方面具有很高的标准。 将算法直接部署到实际系统需要大量试验和错误成本,甚至造成破坏性结果。 在本文中,一个新的模块模拟平台的设计是为了在部署之前评价与空中操纵有关的算法。 此外,为了实现完全自主的空中捕捉,设计了一系列包含完整工作流程的算法模块,并纳入模拟平台,包括感知、规划和控制模块。这个框架使AM能够自主掌握远程目标,而不必与仅仅依靠机载传感器的周围障碍相冲突。从模块设计中受益,这一软件结构可以很容易地通过额外的算法扩展。 最后,还进行了若干模拟,以核实拟议系统的有效性。