Sim2Real2Sim: Bridging the Gap Between Simulation and Real-World in Flexible Object Manipulation
Sim2Real2Sim: Bridging the Gap Between Simulation and Real-World in Flexible Object Manipulation
复制标题
DOI：
10.1109/irc.2020.00015
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Peng Chang;T. Padır
中科院分区：
文献类型：
--
作者：
Peng Chang;T. Padır
本文提出了一种名为“模拟到真实到模拟”(Sim2Real2Sim) 的新策略，以弥合模拟与现实世界之间的差距，并自动执行灵活的对象操作任务。该策略包括三个步骤：（1）利用粗糙环境和估计模型来开发完成模拟中操纵任务的方法； (2) 将仿真方法应用到现实世界并比较其性能； (3)根据现实世界与模拟的差异更新模拟中的模型和方法。选择 2015 年 DARPA 机器人挑战赛决赛中的 Plug Task 来评估我们的 Sim2Real2Sim 策略。一种从现实世界到模拟建立线性柔性物体模型的新识别方法。仿真和现实世界中 DRC 插件任务的自动化证明了 Sim2Real2Sim 策略的成功。进行数值实验来验证模拟模型。
This paper addresses a new strategy called Simulation-to-Real-to-Simulation (Sim2Real2Sim) to bridge the gap between simulation and real-world, and automate a flexible object manipulation task. This strategy consists of three steps: (1) using the rough environment with the estimated models to develop the methods to complete the manipulation task in the simulation; (2) applying the methods from simulation to realworld and comparing their performance; (3) updating the models and methods in simulation based on the differences between the real world and the simulation. The Plug Task from the 2015 DARPA Robotics Challenge Finals is chosen to evaluate our Sim2Real2Sim strategy. A new identification approach for building the model of the linear flexible objects is derived from real-world to simulation. The automation of the DRC plug task in both simulation and real-world proves the success of the Sim2Real2Sim strategy. Numerical experiments are implemented to validate the simulated model.