Car accidents account for numerous injuries and deaths, most resulting from human errors, which can be avoided by leveraging autonomous driving systems. Advancements in advanced driving assistant systems and automated driving have attracted researchers' attention toward cooperative driving and cooperative adaptive cruise control (CACC). One of the apparent benefits of CACC is the reduction in the inter-vehicle gap, hence improving traffic flow and capacity. However, this raises concerns regarding the safety and performance of connected and automated vehicles (CAVs). Moreover, several maneuvers of vehicles need to be considered, such as lane change, hard braking, and free following. Integrating these behaviors into the controller design can result in optimal behavior of the CAVs. This dissertation proposes a hybrid and stochastic predictive control approach for CACC systems to address those concerns and integrate such behaviors. Although the proposed control structures mainly focus on maintaining the desired velocity and distance among CAVs, in the presence of imperfect communication, it assures safety by considering hard braking. In mixed-autonomy traffic, it also allows human-driving vehicles (HVs) to perform lane-change maneuvers and merge into the platoon's lane when needed. In response to an HV's position in the lane and its probabilistic behavior, the controller may switch the CAV's operating mode to react accordingly. Considering free-following and emergency-braking modes leads to much more efficient and safe autonomous driving. Switching between warning, danger, and lane-change modes and adjusting the steering angle to perform a lane-change maneuver robustifies the platoon's performance against unexpected human-driven vehicle maneuvers. An alternative scenario-based approach is then proposed to further improve the performance and robustness of the developed stochastic controller against uncertainties and stochastic events that may occur during driving. Finally, another concern regarding traditional CACC systems studied here is their inefficient use of communication and computation resources. Hence, it is beneficial to leverage a resource-aware communication and computation mechanism. An event-triggered mechanism is developed in this research that allows vehicles to only transmit information necessary for stabilizing the CACC system, thus striking a balance between system performance and communication. The proposed method is capable of reducing communication usage by up to 70%.