Learning to Guide: Guidance Law Based on Deep Meta-learning and Model Predictive Path Integral Control

Abstract

In this paper, we present a novel guidance scheme based on model-based deep reinforcement learning (RL) technique. With model-based deep RL method, a deep neural network is trained as a predictive model of guidance dynamics which is incorporated into a model predictive path integral (MPPI) control framework. However the traditional MPPI framework assumes the actual environment similar to the training dataset for the deep neural network which is impractical in practice with different maneuvering of target, other perturbations and actuator failures. To address this problem, our method utilize meta-learning technique to make the deep neural dynamics model adapt to such changes online. With this approach we can alleviate the performance deterioration of standard MPPI control caused by the difference between actual environment and training data. Then, a novel guidance law for a varying velocity interceptor intercepting maneuvering target with desired terminal impact angle under actuator failure is constructed based on aforementioned techniques. Simulation and experiment results under different cases show the effectiveness and robustness of the proposed guidance law in achieving successful interceptions of maneuvering target.

arXiv commentCode available at https://github.com/tccliangchen/deep_meta-learning_guidance_law . in IEEE Access 2019

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Gaussian Processes for Data-Efficient Learning in Robotics and Control
• Control of a Quadrotor with Reinforcement Learning
• Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control
• Adaptive importance sampling for control and inference
• Uncertainty Averse Pushing with Model Predictive Path Integral Control
• Path Integral Networks: End-to-End Differentiable Optimal Control
• Adaptive Guidance with Reinforcement Meta-Learning

Cited by in corpus (3)

• Neural Network-based Flight Control Systems: Present and Future
• Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning
• Online-Learning Deep Neuro-Adaptive Dynamic Inversion Controller for Model Free Control