Differentiable physics enables efficient gradient-based optimizations of neural network (NN) controllers. However, existing work typically only delivers NN controllers with limited capability and generalizability. We present a practical learning framework that outputs unified NN controllers capable of tasks with significantly improved complexity and diversity. To systematically improve training robustness and efficiency, we investigated a suite of improvements over the baseline approach, including periodic activation functions, and tailored loss functions. In addition, we find our adoption of batching and an Adam optimizer effective in training complex locomotion tasks. We evaluate our framework on differentiable mass-spring and material point method (MPM) simulations, with challenging locomotion tasks and multiple robot designs. Experiments show that our learning framework, based on differentiable physics, delivers better results than reinforcement learning and converges much faster. We demonstrate that users can interactively control soft robot locomotion and switch among multiple goals with specified velocity, height, and direction instructions using a unified NN controller trained in our system. Code is available at https://github.com/erizmr/Complex-locomotion-skill-learning-via-differentiable-physics.

翻译：可微分物理能够实现神经网络控制器的高效梯度优化。然而，现有工作通常仅能提供能力有限且泛化性不足的神经网络控制器。我们提出了一种实用的学习框架，能够输出统一的神经网络控制器，显著提升任务复杂度与多样性。为系统性地提升训练鲁棒性和效率，我们在基线方法基础上研究了一系列改进措施，包括周期性激活函数和定制化损失函数。此外，我们发现批处理和Adam优化器的结合使用在复杂运动任务训练中效果显著。我们在可微分质量-弹簧系统与物质点法（MPM）模拟上评估了该框架，涉及具有挑战性的运动任务与多种机器人设计。实验表明，基于可微分物理的学习框架相比强化学习能取得更优结果，且收敛速度更快。我们证明，用户可通过该系统训练的统一神经网络控制器，根据指定的速度、高度和方向指令，实现软体机器人的交互式运动控制并在多个目标间切换。代码开源地址：https://github.com/erizmr/Complex-locomotion-skill-learning-via-differentiable-physics