A practical approach to learning robot skills, often termed sim2real, is to train control policies in simulation and then deploy them on a real robot. Popular techniques to improve the sim2real transfer build on domain randomization (DR) -- training the policy on a diverse set of randomly generated domains with the hope of better generalization to the real world. Due to the large number of hyper-parameters in both the policy learning and DR algorithms, one often ends up with a large number of trained policies, where choosing the best policy among them demands costly evaluation on the real robot. In this work we ask - can we rank the policies without running them in the real world? Our main idea is that a predefined set of real world data can be used to evaluate all policies, using out-of-distribution detection (OOD) techniques. In a sense, this approach can be seen as a `unit test' to evaluate policies before any real world execution. However, we find that by itself, the OOD score can be inaccurate and very sensitive to the particular OOD method. Our main contribution is a simple-yet-effective policy score that combines OOD with an evaluation in simulation. We show that our score - VSDR - can significantly improve the accuracy of policy ranking without requiring additional real world data. We evaluate the effectiveness of VSDR on sim2real transfer in a robotic grasping task with image inputs. We extensively evaluate different DR parameters and OOD methods, and show that VSDR improves policy selection across the board. More importantly, our method achieves significantly better ranking, and uses significantly less data compared to baselines. Project website is available at https://sites.google.com/view/vsdr/home.
Object Detection Using Sim2Real Domain Randomization for Robotic Applications
Eötvös Loránd Research Network（厄特沃什·罗兰研究网络）；Institute for Computer Science and Control（计算机科学与控制研究所）；Eötvös Loránd University（厄特沃什·罗兰大学）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Pavol Jozef Šafárik University（帕沃尔·约瑟夫·沙法里克大学）
在非结构化环境中工作的机器人必须能够感知和解释周围环境。机器人领域基于深度学习的模型的主要障碍之一是缺乏针对不同工业应用的特定领域标记数据。在这篇文章中，我们提出了一种基于域随机化的sim 2 real迁移学习方法用于目标检测，可以自动生成任意大小和对象类型的标记合成数据集。随后，训练最先进的卷积神经网络YOLOv 4来检测不同类型的工业对象。使用所提出的域随机化方法，我们可以将现实差距缩小到令人满意的水平，在zero-shot和one-shot传输的情况下，在包含190张真实图像的手动注释数据集上，分别实现86.32%和97.38%的mAP 50分数。我们的解决方案适合工业应用，因为在GeForce RTX 2080 Ti GPU上，每张图像的数据生成过程不到0.5秒，训练仅持续约12小时。此外，它可以通过仅访问一个真实图像进行训练来可靠地区分类似的对象类别。据我们所知，这是迄今为止唯一满足这些限制的工作。
Politecnico di Torino（都灵理工大学）；Technische Universität Darmstadt（达姆施塔特工业大学）；Hessian Center for Artificial Intelligence (Hessian.AI)（黑森人工智能中心）；German Research Center for AI (DFKI)（德国人工智能研究中心）；University of Würzburg（维尔茨堡大学）
RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting
Center for Artificial Intelligence and Robotics, Shenzhen International Graduate School, Tsinghua University（人工智能与机器人中心，深圳国际研究生院，清华大学）；Shanghai AI Laboratory（上海人工智能实验室）；Northwestern Polytechnical University（西北工业大学）；Shanghai Jiao Tong University（上海交通大学）
Memorize, Adapt, Ignore: Diagnosing Robot Learning Mechanisms under Training Data Variation
PRIME Robotics Lab, Department of Mechanical Engineering, The University of British Columbia（不列颠哥伦比亚大学机械工程系PRIME机器人实验室）；Department of Computer Science, University of British Columbia（不列颠哥伦比亚大学计算机科学系）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
