A Recurrent Differentiable Engine for Modeling Tensegrity Robots Trainable with Low-Frequency Data
A Recurrent Differentiable Engine for Modeling Tensegrity Robots Trainable with Low-Frequency Data
复制标题
DOI：
10.48550/arxiv.2203.00041
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Kun Wang;Mridul Aanjaneya;Kostas E. Bekris
中科院分区：
文献类型：
--
作者：
Kun Wang;Mridul Aanjaneya;Kostas E. Bekris
张拉整体机器人由刚性杆和柔性索组成，由于存在复杂的动力学和大量自由度，很难精确建模和控制。微分物理引擎最近已被提出作为一种数据驱动的方法，这种复杂的机器人系统的模型识别。这些引擎通常以高频率执行，以实现精确的仿真。然而，由于现实世界传感器的限制，用于训练可微分引擎的地面真实轨迹通常在如此高的频率下不可用。目前的工作重点是这种频率失配，这影响建模精度。我们提出了一种递归结构的可微物理引擎的张拉整体机器人，它可以有效地训练，即使低频轨迹。为了以稳健的方式训练这个新的循环引擎，这项工作相对于先前的工作引入了：（i）一个新的隐式集成方案，（ii）一个渐进式训练管道，以及（iii）一个可微碰撞检查器。MuJoCo上的NASA二十面体SUPERballBot模型被用作地面实况系统来收集训练数据。模拟实验表明，一旦循环微分引擎已经训练给定的低频轨迹从MuJoCo，它能够匹配MuJoCo的系统的行为。成功的标准是使用可微分引擎学习的运动策略是否可以被转移回地面实况系统并导致类似的运动。值得注意的是，训练可微分引擎所需的地面实况数据量，使得策略可转移到地面实况系统，是直接在地面实况系统上训练策略所需数据的1%。
Tensegrity robots, composed of rigid rods and flexible cables, are difficult to accurately model and control given the presence of complex dynamics and high number of DoFs. Differentiable physics engines have been recently proposed as a data-driven approach for model identification of such complex robotic systems. These engines are often executed at a high-frequency to achieve accurate simulation. Ground truth trajectories for training differentiable engines, however, are not typically available at such high frequencies due to limitations of real-world sensors. The present work focuses on this frequency mismatch, which impacts the modeling accuracy. We proposed a recurrent structure for a differentiable physics engine of tensegrity robots, which can be trained effectively even with low-frequency trajectories. To train this new recurrent engine in a robust way, this work introduces relative to prior work: (i) a new implicit integration scheme, (ii) a progressive training pipeline, and (iii) a differentiable collision checker. A model of NASA's icosahedron SUPERballBot on MuJoCo is used as the ground truth system to collect training data. Simulated experiments show that once the recurrent differentiable engine has been trained given the low-frequency trajectories from MuJoCo, it is able to match the behavior of MuJoCo's system. The criterion for success is whether a locomotion strategy learned using the differentiable engine can be transferred back to the ground-truth system and result in a similar motion. Notably, the amount of ground truth data needed to train the differentiable engine, such that the policy is transferable to the ground truth system, is 1% of the data needed to train the policy directly on the ground-truth system.