基於稀疏神經動力學的模型控制

摘要

利用深度神經網絡（DNNs）從觀察中學習預測模型是許多現實世界規劃和控制問題的一種有前途的新方法。然而，普通的DNNs對於有效的規劃來說過於無結構，當前的控制方法通常依賴於廣泛的採樣或局部梯度下降。在本文中，我們提出了一個新的整合模型學習和預測控制的框架，適合於高效的優化算法。具體而言，我們從系統動態的ReLU神經模型開始，並通過去除多餘的神經元逐漸使其稀疏化，從而在預測準確性上損失最小。這種離散的稀疏化過程被近似為一個連續問題，實現了模型架構和權重參數的端到端優化。稀疏化模型隨後被一個混合整數預測控制器使用，該控制器將神經元激活表示為二進制變量並採用高效的分支定界算法。我們的框架適用於各種DNNs，從簡單的多層感知器到複雜的圖神經動態。它可以有效處理涉及複雜接觸動力學的任務，例如物體推動、組合物體排序和可變形物體的操作。數值和硬體實驗表明，儘管進行了積極的稀疏化，我們的框架可以提供比現有最先進方法更好的閉環性能。

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.

基於稀疏神經動力學的模型控制

Model-Based Control with Sparse Neural Dynamics

摘要

Support