i2LQR: Iterative LQR for Iterative Tasks in Dynamic Environments

arxiv link , official code link , paper link

Abstract

This work introduces a novel control strategy called Iterative Linear Quadratic Regulator for Iterative Tasks (i2LQR), which aims to improve closed-loop performance with local trajectory optimization for iterative tasks in a dynamic environment. The proposed algorithm is reference-free and utilizes historical data from previous iterations to enhance the performance of the autonomous system. Unlike existing algorithms, the i2LQR computes the optimal solution in an iterative manner at each timestamp, rendering it well-suited for iterative tasks with changing constraints at different iterations. To evaluate the performance of the proposed algorithm, we conduct numerical simulations for an iterative task aimed at minimizing completion time. The results show that i2LQR achieves an optimized performance with respect to learningbased MPC (LMPC) as the benchmark in static environments, and outperforms LMPC in dynamic environments with both static and dynamics obstacles.

Iterative Nearest Points Selection

LMPC With Dynamic Obstacles	i2LQR With Dynamic Obstacles

The animation above could give a taste of our work. Actually tests in both static and dynamic environments are run in this work, and the results show that in static environment, the performance of i2LQR aligns with LMPC, but in dynamic environment i2LQR can outperform LMPC.