arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01728cs.ROcs.LG
收藏

BayesSim:通过机器人模拟器的概率推理的自适应域随机化

BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators

NVIDIA(英伟达);University of Sydney(悉尼大学);University of Washington(华盛顿大学)

Fabio Ramos, Rafael Carvalhaes Possas, Dieter Fox

摘要:

我们介绍BayesSim,机器人模拟的框架,允许一个完整的贝叶斯处理模拟器的参数。随着模拟器变得越来越复杂,能够更准确地表示动态,机器人技术中的基本问题,如运动规划和感知,可以在模拟和解决方案转移到物理机器人解决。然而,即使是最复杂的模拟器也可能仍然无法在所有细节中表示现实,这可能是由于动态模型中不准确的参数化或过于简单的假设。BayesSim提供了一个原则性的框架来推理模拟参数的不确定性。给定一个黑箱模拟器(或生成模型),输出的状态和动作对的轨迹从未知的仿真参数,其次是与物理机器人获得的轨迹,我们开发了一种无似然推理方法,计算后验分布的仿真参数。这个后验可以用于Sim2Real关键的问题,例如策略搜索。我们比较性能的BayesSim在获得准确的后验在一些经典的控制和机器人问题。结果表明,从BayesSim计算的后验可以用于域随机化优于基于均匀先验随机化的替代方法。

英文摘要:

We introduce BayesSim, a framework for robotics simulations allowing a full Bayesian treatment for the parameters of the simulator. As simulators become more sophisticated and able to represent the dynamics more accurately, fundamental problems in robotics such as motion planning and perception can be solved in simulation and solutions transferred to the physical robot. However, even the most complex simulator might still not be able to represent reality in all its details either due to inaccurate parametrization or simplistic assumptions in the dynamic models. BayesSim provides a principled framework to reason about the uncertainty of simulation parameters. Given a black box simulator (or generative model) that outputs trajectories of state and action pairs from unknown simulation parameters, followed by trajectories obtained with a physical robot, we develop a likelihood-free inference method that computes the posterior distribution of simulation parameters. This posterior can then be used in problems where Sim2Real is critical, for example in policy search. We compare the performance of BayesSim in obtaining accurate posteriors in a number of classical control and robotics problems. Results show that the posterior computed from BayesSim can be used for domain randomization outperforming alternative methods that randomize based on uniform priors.

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。

↑