Connected cruise control with delayed feedback and disturbance: An adaptive dynamic programming approach

Abstract

This paper studies the connected cruise control problem for a platoon of human-operated and autonomous vehicles. The autonomous vehicles can receive motional data, ie, headway and velocity information from other vehicles by wireless vehicle-to-vehicle communication. The use of wireless communications in information exchange between vehicles inevitably causes input delay in the platooning system. Meanwhile, unpredictable behaviors of the leading vehicle constitute exogenous disturbance for the system. An adaptive optimal control problem with input delay and disturbance is formulated, and a novel data-driven control solution is proposed such that each vehicle in the platoon can achieve safe distance and desired velocity. By adopting an adaptive dynamic programming technique with sampled-data system theory, a data-driven adaptive optimal control approach is proposed for autonomous vehicles by the learning strategies of policy iteration without the accurate knowledge of the dynamics of all human drivers and vehicles. The efficacy of the proposed controller is substantiated by rigorous analysis and validated by simulation results in different scenarios. KEYWORDSadaptive dynamic programming, connected vehicles, time-delayed input INTRODUCTIONTransportation safety and congestion have been the two crucial problems in the major cities around the world for a long time. In the last decade, extensive efforts were devoted to seek innovative solutions for improving transportation efficiency and reducing accidents. Adaptive cruise control (ACC) has been proposed as an advanced driver assistance system to help solve these problems, where a vehicle is equipped with radars or lasers to acquire velocity and distance information from its preceding vehicle to keep a safe space and give the driver more comfort and convenience. 1-3 Nonetheless, the evaluation conducted by Werf et al 4 showed that the impact of ACC to highway systems is limited regarding traffic capacity and smoothness. By the combination of vehicle-to-vehicle (V2V) communication and ACC, cooperative ACC has demonstrated its potential to obtain better performance with a smaller intervehicular gap and improved traffic flow stability, 5 allowing connected vehicles actively exchange information. Several control methods have been investigated for designing cooperative ACC systems, such as model predictive control, 6 robust control, 7 optimal control, 8 and reinforcement learning. 9 356

Fog-Based Distributed Networked Control for Connected Autonomous Vehicles

“…In this subsection, we provide simulations of the connected vehicle system to study the performance of the proposed control scheme. Here, the typical scenario of the three-vehicle platoon is considered [31,43], which can be easily extended to more vehicle scenarios. In particular, each platoon consists of 2 normal human-driven vehicles and a single CAV at the tail.…”

Optimal Current Balance Control of Three-Level Inverter under Grid Voltage Unbalance: An Adaptive Dynamic Programming Approach

“…Currently, there are two algorithms for solving ADP, which are policy iterations (PI) and value iteration (V I) [19][20][21][22]. The main difference between the two methods is that V I is usually implemented offline and PI is usually implemented online [23].…”

“…The VI Algorithm 1 is able to approximate the solution to (19) with assured convergence. Consider P j and K j+1 defined in (22) and (23). Then, for all…”

Editorial for the Special Issue on Learning‐based Adaptive Control: Theory and Applications

“…On the application side, the paper of Huang et al includes new iterative learning‐based algorithms for controlling a platoon of human‐operated and autonomous vehicles. Adaptive dynamic programming theory is used together with sampled‐data systems theory to design a data‐driven iterative learning platooning controller, with robust performances w.r.t.…”