arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.01369cs.RO
收藏

通过模拟器调整跨越现实差距

Traversing the Reality Gap via Simulator Tuning

Data61/CSIRO(澳大利亚联邦科学与工业研究组织数据61);Queensland University of Technology (QUT)(昆士兰科技大学);Australian Centre for Robotic Vision (ACRV)(澳大利亚机器人视觉中心);LYRO Robotics Pty Ltd(LYRO机器人私人有限公司)

Jack Collins, Ross Brown, Jurgen Leitner, David Howard

摘要:

对模拟数据的大量需求使得现实差距成为机器人技术前沿的一个问题。我们提出了一种方法来遍历的差距,通过调整可用的模拟参数。通过物理引擎参数的优化,我们表明,我们能够缩小模拟解决方案和现实世界的数据集之间的差距,从而允许更容易地在两者之间转移学习行为。我们随后获得的理解,具体的模拟器参数,这是广泛的兴趣,机器人机器学习社区的重要性。我们发现,即使针对不同的任务进行了优化,不同的物理引擎在某些情况下表现更好,摩擦和最大致动器速度是严格限制的参数,极大地影响了模拟解决方案的转移。

英文摘要:

The large demand for simulated data has made the reality gap a problem on the forefront of robotics. We propose a method to traverse the gap by tuning available simulation parameters. Through the optimisation of physics engine parameters, we show that we are able to narrow the gap between simulated solutions and a real world dataset, and thus allow more ready transfer of leaned behaviours between the two. We subsequently gain understanding as to the importance of specific simulator parameters, which is of broad interest to the robotic machine learning community. We find that even optimised for different tasks that different physics engine perform better in certain scenarios and that friction and maximum actuator velocity are tightly bounded parameters that greatly impact the transference of simulated solutions.

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。

↑