We present Dojo, a differentiable physics engine for robotics that prioritizes stable simulation, accurate contact physics, and differentiability with respect to states, actions, and system parameters. Dojo achieves stable simulation at low sample rates and conserves energy and momentum by employing a variational integrator. A nonlinear complementarity problem with second-order cones for friction models hard contact, and is reliably solved using a custom primal-dual interior-point method. Special properties of the interior-point method are exploited using implicit differentiation to efficiently compute smooth gradients that provide useful information through contact events. We demonstrate Dojo with a number of examples including: planning, policy optimization, and system identification, that demonstrate the engine's unique ability to simulate hard contact while providing smooth, analytic gradients.
翻译:我们提出了Dojo,这是一个专注于稳定模拟、精确接触力学和对状态、动作和系统参数可微分的机器人物理引擎。Dojo实现了在低采样率下稳定模拟,并通过采用变分积分器保持能量和动量的规律性。使用以二阶锥体为基础的非线性互补问题来模拟硬性接触,并使用自定义原始-对偶内点法可靠地解决该问题。通过隐式微分来利用内点法的特殊属性,以便通过接触事件高效地计算平滑的梯度。我们使用许多示例来演示Dojo,包括:规划、策略优化和系统识别,这些示例演示了该引擎在模拟硬性接触的同时提供平滑、解析梯度的独特能力。