基于模型的稀疏神经动力学控制

摘要

利用深度神经网络（DNNs）从观测中学习预测模型是许多现实世界规划和控制问题的一种有前途的新方法。然而，常见的DNNs结构过于杂乱，难以有效进行规划，当前的控制方法通常依赖于大量采样或局部梯度下降。在本文中，我们提出了一个新的集成模型学习和预测控制的框架，适用于高效优化算法。具体而言，我们从系统动态的ReLU神经模型开始，通过逐渐稀疏化模型，去除冗余神经元，在最小化预测准确性损失的基础上进行。这种离散稀疏化过程被近似为连续问题，实现了模型架构和权重参数的端到端优化。稀疏化模型随后被混合整数预测控制器使用，该控制器将神经元激活表示为二进制变量，并采用高效的分支定界算法。我们的框架适用于各种DNNs，从简单的多层感知器到复杂的图神经动态。它可以有效处理涉及复杂接触动力学的任务，如推动物体、组合物体排序和可变形物体操纵。数值和硬件实验表明，尽管进行了激进的稀疏化，我们的框架可以提供比现有最先进方法更好的闭环性能。

English

Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current control methods typically rely on extensive sampling or local gradient descent. In this paper, we propose a new framework for integrated model learning and predictive control that is amenable to efficient optimization algorithms. Specifically, we start with a ReLU neural model of the system dynamics and, with minimal losses in prediction accuracy, we gradually sparsify it by removing redundant neurons. This discrete sparsification process is approximated as a continuous problem, enabling an end-to-end optimization of both the model architecture and the weight parameters. The sparsified model is subsequently used by a mixed-integer predictive controller, which represents the neuron activations as binary variables and employs efficient branch-and-bound algorithms. Our framework is applicable to a wide variety of DNNs, from simple multilayer perceptrons to complex graph neural dynamics. It can efficiently handle tasks involving complicated contact dynamics, such as object pushing, compositional object sorting, and manipulation of deformable objects. Numerical and hardware experiments show that, despite the aggressive sparsification, our framework can deliver better closed-loop performance than existing state-of-the-art methods.

基于模型的稀疏神经动力学控制

Model-Based Control with Sparse Neural Dynamics

摘要

Support