Emergent cooperative adaptive cruise control (CACC) strategies being proposed in the literature for platoon formation in the Connected Autonomous Vehicle (CAV) context mostly assume idealized fixed information flow topologies (IFTs) for the platoon, implying guaranteed vehicle-to-vehicle (V2V) communications for the IFT assumed. In reality, V2V communications are unreliable due to failures resulting from communication-related constraints such as interference and information congestion. Since CACC strategies entail continuous information broadcasting, communication failures can occur in congested CAV traffic networks, leading to a platoon's IFT varying dynamically. To explicitly factor IFT dynamics and to leverage it to enhance the performance of CACC strategies, this study proposes the idea of dynamically optimizing the IFT for CACC, labeled the CACC-OIFT strategy. Under CACC-OIFT, the vehicles in the platoon cooperatively determine in real-time which vehicles will dynamically deactivate or activate the "send" functionality of their V2V communication devices to generate IFTs that optimize the platoon performance in terms of string stability under the ambient traffic conditions. The CACC-OIFT consists of an IFT optimization model and an adaptive Proportional-Derivative (PD) controller. Given the adaptive PD controller with a two-predecessor-following scheme, and the ambient traffic conditions and the platoon size just before the start of a time period, the IFT optimization model determines the optimal IFT (in terms of the activated and deactivated status of the "send" functionalities of the vehicles in the platoon) that maximizes the expected string stability. This expectation is because each IFT has specific degeneration scenarios whose probabilities are determined by the communication failure probabilities for that time period based on the ambient traffic conditions. The optimal IFT is deployed for that time period, and the adaptive PD controller continuously determines the car-following behaviors of the vehicles based on the unfolding degeneration scenario for each time instant within that period. The effectiveness of the proposed CACC-OIFT is validated through numerical experiments in NS-3 based on NGSIM field data. The results indicate that the proposed CACC-OIFT can significantly enhance the string stability of platoon control in an unreliable V2V communication context, outperforming CACCs with fixed IFTs or with passive adaptive schemes for IFT dynamics.
Vehicle-to-vehicle communications can be unreliable as interference causes communication failures. Thereby, the information flow topology for a platoon of Connected Autonomous Vehicles (CAVs) can vary dynamically. This limits existing Cooperative Adaptive Cruise Control (CACC) strategies as most of them assume a fixed information flow topology (IFT). To address this problem, we introduce a CACC design that considers a dynamic information flow topology (CACC-DIFT) for CAV platoons. An adaptive Proportional-Derivative (PD) controller under a twopredecessor-following IFT is proposed to reduce the negative effects when communication failures occur. The PD controller parameters are determined to ensure the string stability of the platoon. Further, the designed controller also factors the performance of individual vehicles. Hence, when communication failure occurs, the system will switch to a certain type of CACC instead of degenerating to adaptive cruise control, which improves the control performance considerably. The effectiveness of the proposed CACC-DIFT is validated through numerical experiments based on NGSIM field data. Results indicate that the proposed CACC-DIFT design outperforms a CACC with a predetermined information flow topology. IFT can change dynamically due to communication failures [14][15][16]. The probability of a communication failure is proportional to the number of ongoing V2V communications occurring within the vehicle's communication range.Other factors, such as the dynamic CAV traffic flow density, also impact the number of ongoing communications within the communication range, and further impact communication failure. Hence, the IFT is less likely to be fixed in the realworld. In this context, a CACC based on a predetermined IFT may execute an erroneous control action, which diminishes
Self-driving technology companies and the research community are accelerating the pace of use of machine learning longitudinal motion planning (mMP) for autonomous vehicles (AVs). This paper reviews the current state of the art in mMP, with an exclusive focus on its impact on traffic congestion. The paper identifies the availability of congestion scenarios in current datasets, and summarizes the required features for training mMP. For learning methods, the major methods in both imitation learning and non-imitation learning are surveyed. The emerging technologies adopted by some leading AV companies, such as Tesla, Waymo, and Comma.ai, are also highlighted. It is found that: (i) the AV industry has been mostly focusing on the long tail problem related to safety and has overlooked the impact on traffic congestion, (ii) the current public self-driving datasets have not included enough congestion scenarios, and mostly lack the necessary input features/output labels to train mMP, and (iii) although the reinforcement learning approach can integrate congestion mitigation into the learning goal, the major mMP method adopted by industry is still behavior cloning, whose capability to learn a congestion-mitigating mMP remains to be seen. Based on the review, the study identifies the research gaps in current mMP development. Some suggestions for congestion mitigation for future mMP studies are proposed: (i) enrich data collection to facilitate the congestion learning, (ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and (iii) integrate domain knowledge from the traditional car-following theory to improve the string stability of mMP.
Current factory adaptive cruise control (ACC) systems consist of an upper-level planner that computes the optimal trajectory of the vehicle and a low-level controller in charge of executing it. The literature on the string stability (SS) of ACC systems is mostly concerned with the upper-level planner. In this paper, we show that the low-level controller can have a significant impact on SS. We find that i) a fast controller improves the SS, ii) a slow controller can result from either insufficient control gains or from an undershooting gas/brake system or both, and iii) although the integral gain is helpful for effective control, the integral windup can cause overshooting, and in turn undermines the SS of the ACC. Accordingly, we suggest tuning up the proportional/feedforward gain and ensuring the gas/brake is not to undershoot. Anti-windup design is also needed to improve SS. The results of this paper are validated both numerically and empirically on commercial cars.
Vehicle-to-vehicle communications can be unreliable because of interference and information congestion, which leads to the dynamic information flow topology (IFT) in a platoon of connected and autonomous vehicles. Some existing studies adaptively switch the controller of cooperative adaptive cruise control (CACC) to optimize string stability when IFT varies. However, the difference of transient response between controllers can induce uncomfortable jerks at switching instances, significantly affecting riding comfort and jeopardizing vehicle powertrain. To improve riding comfort while maintaining string stability, the authors introduce a smooth-switching control-based CACC scheme with IFT optimization (CACC-SOIFT) by implementing a bi-layer optimization model and a Kalman predictor. The first optimization layer balances the probability of communication failure and control performance optimally, generating a robust IFT to reduce controller switching. The second optimization layer adjusts the controller parameters to minimize tracking error and the undesired jerk. Further, a Kalman predictor is applied to predict vehicle acceleration if communication failures occur. It is also used to estimate the states of preceding vehicles to suppress the measurement noise and the acceleration disturbance. The effectiveness of the proposed CACC-SOIFT is validated through numerical experiments based on NGSIM field data. Results indicate that the CACC-SOIFT framework can guarantee string stability and riding comfort in the environment of dynamic IFT.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.