用神经网络逼近无限时域价值函数，提升模型预测控制的稳定性与实时性。
Infinite-Horizon Value Function Approximation for Model Predictive Control
- 通过值迭代与轨迹优化训练神经网络，逼近约束最优控制的无限时域价值函数。
- 在玩具问题和工业机械臂避障场景中，实现全局稳定，且支持在线避障。
- 适合需要高稳定性与实时性的机器人运动规划任务，尤其有障碍物动态环境。
模型预测控制（MPC）已成为机器人生成复杂动作的常用工具。然而，实时性要求限制了硬约束和大预览时域的使用，而这些对保证安全性和稳定性至关重要。实践中，需精心设计成本函数以模拟无限时域形式，过程繁琐且常陷入局部最优。本文研究如何利用值迭代与轨迹优化，通过神经网络逼近约束最优控制问题的无限时域价值函数。实验表明，将该价值函数近似作为终端代价，可为MPC控制器提供全局稳定性。方法在两个玩具问题及一个真实世界场景中验证，包括工业机械臂在线避障，其中价值函数条件依赖于目标和障碍物。
原文摘要 · Abstract (English)
Model Predictive Control has emerged as a popular tool for robots to generate complex motions. However, the real-time requirement has limited the use of hard constraints and large preview horizons, which are necessary to ensure safety and stability. In practice, practitioners have to carefully design cost functions that can imitate an infinite horizon formulation, which is tedious and often results in local minima. In this work, we study how to approximate the infinite horizon value function of constrained optimal control problems with neural networks using value iteration and trajectory optimization. Furthermore, we experimentally demonstrate how using this value function approximation as a terminal cost provides global stability to the model predictive controller. The approach is validated on two toy problems and a real-world scenario with online obstacle avoidance on an industrial manipulator where the value function is conditioned to the goal and obstacle.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。