Although automation technology is increasingly replacing human to perform complex tasks such as driving, eliminating human intervention from driving may imply significant safety and trustrelated concerns. To address this issue from a psychological perspective, this study applies layers of anthropomorphic cues to an artificial driving agent to promote positive perceptions of an unmanned driving system. In a between-subjects factorial experiment (N = 89), participants interacted with an artificial driving agent with different levels of anthropomorphism induced by the variations in appearance (human-like vs. gadget-like) and autonomy (high vs. low) of the agent. The results indicated that an agent with human-like appearance and high autonomy were more effective in eliciting positive perceptions of the agent, which in turn the external (i.e., appearance) and internal (i.e., autonomy) anthropomorphic cues can be both strategically manipulated to demonstrate the feasibility of psychologically increasing the safety and trustworthiness of autonomous vehicles. In addition, a mediation analysis revealed that the role of social presence, suggesting that perceiving the driving agent as intelligent, safe, and trustworthy is largely determined by the feelings of social presence experienced during their interaction.