arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.06169cs.ROcs.CVcs.LG
收藏

基于势函数的扩散运动规划

Potential Based Diffusion Motion Planning

Brown University(布朗大学);MIT(麻省理工学院)

Yunhao Luo, Chen Sun, Joshua B. Tenenbaum, Yilun Du

AI总结:

针对高维空间运动规划易陷局部极小值的问题,提出基于神经网络学习易优化势函数的运动规划方法,性能优于现有方法且具备良好约束泛化能力。

摘要:

高维空间中的有效运动规划是机器人领域长期存在的开放性问题。一类传统运动规划算法属于基于势函数的运动规划方法,其优势在于可组合性——通过叠加对应的势函数即可轻松整合不同的运动约束。但从势函数构建运动路径需要在构型空间势场中求解全局优化问题,往往容易陷入局部极小值。我们提出一种学习式基于势函数的运动规划新方法,训练神经网络来捕捉并学习运动规划轨迹上易于优化的势函数。实验验证了该方法的有效性,其性能显著优于经典方法和近期的学习式运动规划方法,且能避免局部极小值问题。我们还进一步验证了其固有的可组合性,使其能够泛化适配多种不同的运动约束。

英文摘要:

Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability -- different motion constraints can be easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑