MPC-based Controller with Terrain Insight for Dynamic Legged Locomotion
MPC-based Controller with Terrain Insight for Dynamic Legged Locomotion
复制标题
基于 MPC 的控制器，具有地形洞察力，可实现动态腿部运动
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
C. Semini
中科院分区：
文献类型：
--
作者：
Octavio Antonio Villarreal;Victor Barasuol;Patrick M. Wensing;C. Semini
提出了一种新的复杂场景下的动态腿部运动控制策略，该策略在只有车载地图和计算可用的情况下，考虑了环境中地形的形态信息。该策略建立在两个主要元素之上：第一个是基于卷积神经网络的接触序列任务，它提供安全的落脚点位置，以执行快速和连续的地形评估，以寻找安全的落脚点位置；第二个是模型预测控制器，它考虑接触序列任务给出的落脚点位置，以优化目标地面反作用力。我们通过对液压驱动的四足机器人HyQReal在真实的车载感知和计算条件下穿越崎岖地形的仿真来评估我们的策略的性能。
We present a novel control strategy for dynamic legged locomotion in complex scenarios that considers information about the morphology of the terrain in contexts when only on-board mapping and computation are available. The strategy is built on top of two main elements: first a contact sequence task that provides safe foothold locations based on a convolutional neural network to perform fast and continuous evaluation of the terrain in search of safe foothold locations; then a model predictive controller that considers the foothold locations given by the contact sequence task to optimize target ground reaction forces. We assess the performance of our strategy through simulations of the hydraulically actuated quadruped robot HyQReal traversing rough terrain under realistic on-board sensing and computing conditions.
使用学习质心动力学预测进行高效的人形接触规划
DOI：
10.1109/icra.2019.8794032
发表时间：
2019
期刊：
2019 IEEE International Conference on Robotics and Automation (ICRA
影响因子：
--
作者：
Lin, Yu-Chi;Ponton, Brahayam;Righetti, Ludovic;Berenson, Dmitry
通讯作者：
Berenson, Dmitry