表征空间中的机器人分层运动规划

由于对机器人的任务要求日趋复杂和多变,如何使机器人具备灵活的配置和运动规划能力,以适应复杂任务的需求,成为了目前运动规划领域所研究的核心问题.传统的基于任务空间和配置空间的建模方法虽然在机器人运动规划领域得到了非常广泛的应用,但在用于解决复杂规划任务时无法对不可行任务进行进一步地处理.本文在表征空间模型的基础上,提出了一种分层的运动规划算法,一方面借助于表征空间维度的扩展,使对运动规划任务的描述更为灵活;另一方面通过任务层与运动层的循环交互,使生成的路径满足更高层次和更丰富的任务要求.在仿人机器人和多机器人系统上的应用结果表明了本文所提算法的有效性.

Robotic hierarchical motion planning in its representation space

In enormous and complicated robotic applications, the key issue in the field of robot motion planning is to endow the robot with the ability of adapting to various tasks. Although traditional task-space and configuration-space-based motion planning methods have been successfully applied to many practical applications, few of them can be used to handle the situation when the planning algorithms fail to find a feasible path, especially with strict and complicated requirements. In this paper, a representation-space-based hierarchical motion planning method is proposed. Taking the advantage in increasing the number of dimensions of the representation space, the motion planning task can be modeled with much more flexibility. On the other hand, through the interaction between the task level and motion level, the iteratively generated trajectory will satisfy higher and richer task requirements. Performance of motion planning tasks on humanoid robots and multi-robot systems prove the effectiveness of the proposed method.