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Dojo，一种用于机器人的可微物理引擎，其优先考虑稳定仿真、精确接触物理，以及与状态、动作和系统参数相关的可微性。Dojo通过采用变分积分器，在低采样率下实现稳定仿真，并守恒能量和动量。一种带有二阶锥的非线性互补问题用于摩擦模型硬接触，并通过定制的主-对偶内点法可靠求解。利用隐式微分法利用内点法的特殊性质，高效计算平滑梯度，从而在接触事件中提供有用信息。我们通过规划、策略优化和系统辨识等多个示例展示Dojo，这些示例证明了该引擎在提供平滑解析梯度的同时模拟硬接触的独特能力。