EAGER: Data-Driven Contact Modeling

EAGER：数据驱动的接触建模

• 批准号: 1953008
• 负责人: Karen Liu
• 金额: $ 17.73万
• 依托单位: Stanford University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-06-17 至 2021-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1953008&HistoricalAwards=false
• 关键词: EAGER; Data; Driven; Contact; Modeling

Accurate physics simulation has become an essential component for developing robots that physically interact with the world. A particularly important aspect is simulating contacts between the robots and objects in the environment, which can be useful for both planning and machine learning. However, robots that learn in simulation often perform poorly in the real world due to inaccurate parameters, idealized dynamic and contact models, or other unmodeled factors. This project therefore tackles an important challenge in physics simulation: accurate modeling of contacts. The results will significantly improve contact modeling in physics simulation, which offers a safe space to learn difficult and highly risky motor skills such that the robots can operate more efficiently and robustly even in unseen scenarios in the real world. This capability will have potential impact on robotics in healthcare, search-and-rescue, and space exploration.This proposal introduces a technique that effectively utilizes real-world data to model the complex, poorly understood contact phenomena. Specifically, the new data-driven technique accurately computes contact states (sticking, sliding, or breaking) and contact forces such that the simulated results match the real-world phenomena. Instead of taking the conventional approach of system identification, this proposal leverages empirical evidence and deep learning techniques to enhance the existing contact model, namely, an implicit time-stepping, velocity-based Linear-Complementarity Program (LCP). The key insight is that the contact problem can be broken down into two steps: predicting the next state of each contact point and calculating contact forces based on the prediction and current dynamic state. The first step is solved by learning a classifier from real-world data. By doing so, the second step can be simplified from an LCP to a Linear Program (LP), thus making the calculation of contacts much more efficient.

精确的物理仿真已经成为开发与世界进行物理交互的机器人的重要组成部分。 一个特别重要的方面是模拟机器人与环境中物体之间的接触，这对规划和机器学习都很有用。 然而，在仿真中学习的机器人往往在真实的世界中表现不佳，由于不准确的参数，理想化的动力学和接触模型，或其他未建模的因素。 因此，该项目解决了物理仿真中的一个重要挑战：精确的接触建模。研究结果将显着改善物理仿真中的接触建模，这为学习困难和高风险的运动技能提供了一个安全的空间，即使在真实的世界中看不见的场景中，机器人也可以更有效地运行。这种能力将对医疗保健、搜救和太空探索领域的机器人技术产生潜在影响。该提案引入了一种有效利用真实世界数据来建模复杂且知之甚少的接触现象的技术。具体而言，新的数据驱动技术可以准确计算接触状态（粘附、滑动或断裂）和接触力，从而使模拟结果与现实世界的现象相匹配。该提案没有采用传统的系统识别方法，而是利用经验证据和深度学习技术来增强现有的接触模型，即隐式时间步进，基于速度的线性互补程序（LCP）。 关键的见解是，接触问题可以分为两个步骤：预测每个接触点的下一个状态，并根据预测和当前动态状态计算接触力。第一步是通过从真实世界的数据中学习分类器来解决的。通过这样做，第二步可以从LCP简化为线性规划（LP），从而使接触的计算更加有效。

项目成果

SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning

• DOI: 10.1109/icra48506.2021.9561731
• 发表时间: 2021-01
• 期刊: 2021 IEEE International Conference on Robotics and Automation (ICRA)
• 作者: Yifeng Jiang;Tingnan Zhang;Daniel Ho;Yunfei Bai;C. Liu;S. Levine;Jie Tan

Fast and Feature-Complete Differentiable Physics Engine for Articulated Rigid Bodies with Contact Constraints

用于具有接触约束的铰接刚体的快速且功能完整的可微分物理引擎

• DOI: 10.15607/rss.2021.xvii.034
• 发表时间: 2021
• 期刊: Robotics: Science and Systems
• 作者: Werling, Keenon;Omens, Dalton;Lee, Jeongseok;Exarchos, Ioannis;Liu, C. Karen
• 通讯作者: Liu, C. Karen