Robust Time-Delay Feedback Control of Vehicular CACC Systems with Uncertain Dynamics

Song, Xiulan; Chen, Li; Wang, Ke; He, Defeng

doi:10.3390/s20061775

“…In order to improve the limitations of vehicle following models, DRL has been a steady area of research in the AV community, with many authors contributing works to DRL applied to CACC [8,9,22,23] . In a study by Lin et al, a DRL framework is designed to control a CACC AV platoon [22] .…”

Section: Deep Reinforcement Learning Applied To Av Platooningmentioning

confidence: 99%

“…The state space formula (6) can be discretized using the forward euler method giving the system equation below (8) where 𝑥 𝑖,𝑘 = [𝑒 𝑝𝑖,𝑘 , 𝑒 𝑣𝑖,𝑘 , 𝑎 𝑖,𝑘 , 𝑎 𝑖−1,𝑘 ] is the observation state for the MDP problem that includes the position error 𝑒 𝑝𝑖,𝑘 , velocity error 𝑒 𝑣𝑖,𝑘 , acceleration 𝑎 𝑖,𝑘 , and the acceleration of the predecessor vehicle 𝑎 𝑖−1,𝑘 at time step 𝑘. Moreover, 𝐴 𝐷𝑖 , 𝐵 𝐷𝑖 , and 𝐶 𝐷𝑖 are given as…”

Section: State Spacementioning

confidence: 99%

“…Vehicle following models are based on following a vehicle on a single lane road with respect to a leading vehicle' s actions [7] . CACC is a multivehicle control strategy where vehicles follow one another in a line known as a platoon, while simultaneously transmitting vehicle data amongst each other [8] . CACC platoons have been proven to improve traffic flow stability, throughput and safety for occupants [8,9] .…”

Section: Introductionmentioning

confidence: 99%

“…CACC is a multivehicle control strategy where vehicles follow one another in a line known as a platoon, while simultaneously transmitting vehicle data amongst each other [8] . CACC platoons have been proven to improve traffic flow stability, throughput and safety for occupants [8,9] . Traditionally controlled vehicle following models have limited accuracy, poor generalization from a lack of data, and a lack of adaptive updating [7] .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AVDDPG – Federated reinforcement learning applied to autonomous platoon control

Boin¹,

Lei²,

Yang³

2022

View full text Add to dashboard Cite

Since 2016 federated learning (FL) has been an evolving topic of discussion in the artificial intelligence (AI) research community. Applications of FL led to the development and study of federated reinforcement learning (FRL). Few works exist on the topic of FRL applied to autonomous vehicle (AV) platoons. In addition, most FRL works choose a single aggregation method (usually weight or gradient aggregation). We explore FRL's effectiveness as a means to improve AV platooning by designing and implementing an FRL framework atop a custom AV platoon environment. The application of FRL in AV platooning is studied under two scenarios: (1) Inter-platoon FRL (Inter-FRL) where FRL is applied to AVs across different platoons; (2) Intra-platoon FRL (Intra-FRL) where FRL is applied to AVs within a single platoon. Both Inter-FRL and Intra-FRL are applied to a custom AV platooning environment using both gradient and weight aggregation to observe the performance effects FRL can have on AV platoons relative to an AV platooning environment trained without FRL. It is concluded that Intra-FRL using weight aggregation (Intra-FRLWA) provides the best performance for controlling an AV platoon. In addition, we found that weight aggregation in FRL for AV platooning provides increases in performance relative to gradient aggregation. Finally, a performance analysis is conducted for Intra-FRLWA versus a platooning environment without FRL for platoons of length 3, 4 and 5 vehicles. It is concluded that Intra-FRLWA largely out-performs the platooning environment that is trained without FRL.

show abstract

“…Vehicle following models are based on following a vehicle on a single lane road with respect to a leading vehicle's actions [7]. CACC is a multi-vehicle control strategy where vehicles follow one another in a line known as a platoon, while simultaneously transmitting vehicle data amongst each other [8]. CACC platoons have been proven to improve traffic flow stability, throughput and safety for occupants [8], [9].…”

Section: Introductionmentioning

confidence: 99%

AVDDPG: Federated reinforcement learning applied to autonomous platoon control

Boin,

Lei,

Yang

2022

Preprint

0

View full text Add to dashboard Cite

Since 2016 federated learning (FL) has been an evolving topic of discussion in the artificial intelligence (AI) research community. Applications of FL led to the development and study of federated reinforcement learning (FRL). Few works exist on the topic of FRL applied to autonomous vehicle (AV) platoons. In addition, most FRL works choose a single aggregation method (usually weight or gradient aggregation). We explore FRL's effectiveness as a means to improve AV platooning by designing and implementing an FRL framework atop a custom AV platoon environment. The application of FRL in AV platooning is studied under two scenarios: (1) Inter-platoon FRL (Inter-FRL) where FRL is applied to AVs across different platoons; (2) Intra-platoon FRL (Intra-FRL) where FRL is applied to AVs within a single platoon. Both Inter-FRL and Intra-FRL are applied to a custom AV platooning environment using both gradient and weight aggregation to observe the performance effects FRL can have on AV platoons relative to an AV platooning environment trained without FRL. It is concluded that Intra-FRL using weight aggregation (Intra-FRLWA) provides the best performance for controlling an AV platoon. In addition, we found that weight aggregation in FRL for AV platooning provides increases in performance relative to gradient aggregation. Finally, a performance analysis is conducted for Intra-FRLWA versus a platooning environment without FRL for platoons of length 3, 4 and 5 vehicles. It is concluded that Intra-FRLWA largely out-performs the platooning environment that is trained without FRL.

show abstract

Bidirectional asymmetric delay feedback for cooperative adaptive cruise control of vehicle platoons with unreliable communication

Song

¹

,

Wei

²

,

Chen

³

et al. 2021

Asian Journal of Control

Self Cite

View full text Add to dashboard Cite

This paper considers the cooperative adaptive cruise control (CACC) problem of vehicle platoons under unreliable vehicle-to-everything (V2X) communication network. A bidirectional asymmetric delay feedback CACC method is presented to cope with the time delay and packet dropout induced by the unreliable network. The concept of equivalent delays is used to compensate the packet dropout of the network with the bidirectional communication topology. Using the asymmetric PD structure and the longitudinal models with varying time delay, the CACC controller of the platoon in a centralized mode is computed by solving linear matrix inequalities. To guarantee string stability of the platoon with the controller under the unreliable network, some sufficient conditions on the parameters of the controller and the time delay and packet dropout are derived. Furthermore, the upper bound of the time delay is estimated to satisfy string stability of the platoon. Finally, the presented method is verified by some comparative experiments of a sevencar platoon with representative traffic scenarios and communication topologies.

show abstract

Robust Time-Delay Feedback Control of Vehicular CACC Systems with Uncertain Dynamics

Cited by 15 publications

References 33 publications

AVDDPG – Federated reinforcement learning applied to autonomous platoon control

AVDDPG – Federated reinforcement learning applied to autonomous platoon control

AVDDPG: Federated reinforcement learning applied to autonomous platoon control

Bidirectional asymmetric delay feedback for cooperative adaptive cruise control of vehicle platoons with unreliable communication

Contact Info

Product

Resources

About