Cross-Entropy Optimization of Physically Grounded Task and Motion Plans
物理基础的任务与运动规划的交叉熵优化
机构 * Department of Cognitive Robotics, Delft University of Technology(德鲁夫特理工大学认知机器人学系) ; Faculty of Computer Science, Dalhousie University(达尔豪斯大学计算机科学学院)
AI总结 提出利用GPU并行物理模拟器和交叉熵优化,通过采样控制器参数获得低成本解决方案,以解决传统TAMP算法忽略动力学和接触的问题。
Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L)
Journal ref IEEE Robotics and Automation Letters, 2026