Learning speeds up distributed control for vehicle path tracking
A Data-Driven Distributed Control Scheme: Learning Multi-Objective Agent-Based MPC for Path-Tracking
Robotics
Summary
Controlling a vehicle with many cooperating parts that have different goals is hard because it takes a lot of computing power. The authors developed a method that breaks the problem into smaller pieces solved by different agents, which work together by exchanging information. They used learning to help the system start with a good guess, making it faster to find the best control actions. Their approach performs just as well as the traditional method but uses much less computation, making it more practical for real-time use.
What this means in practice
- •For autonomous vehicle engineers: Implement efficient multi-agent control schemes that handle conflicting objectives for autonomous driving path-tracking with reduced real-time computation.
- •For robotics control teams: Use learned initialization in distributed multi-agent control to speed up convergence in systems with multiple competing control goals.
Authors
Jiaming Zhong, Reza Valiollahi Mehrizi, Yash Vardhan Pant, Amir Khajepour
Abstract
Agent-based model predictive control (AMPC) has recently been proposed for vehicle systems with various controllers, such as differential braking and torque vectoring, where controllers are regarded as distributed agents contributing to the same objective. However, this scheme is challenging in handling multiple conflicting objectives with coupled agents. A common approach for such tasks is the integrated MPC, where all objectives and agents are stacked together in one optimization. Nevertheless, as more agents and objectives are involved, the integrated MPC will face challenges like computational burdens and maintenance difficulties in practice. To this end, this paper proposes a learning multi-objective AMPC that can improve design flexibility and computing efficiency. First, under the assumption of information exchange, a multi-objective AMPC tailored from the alternating direction method of multipliers (ADMM) is proposed to decouple the system and achieve the same performance as the integrated scheme iteratively. Second, a learning-based method for initializing iterations is proposed to accelerate convergence. In addition, a data management method is proposed for real-time efficiency, and an authentication module is designed for learning reliability. We compare the proposed scheme against the integrated scheme via a combined path-tracking simulation for autonomous vehicles with various controllers. The proposed scheme achieves the same control performance as the integrated one while reducing the computational time by 43.5%. Furthermore, the learning-based method saves 88.6% more computational time than without learning, making it suitable for real-time implementation.