Sensors on autonomous vehicles have inherent physical constraints. To address these limitations, several studies have been conducted to enhance sensing capabilities by establishing wireless communication between infrastructure and autonomous vehicles. Various sensors are strategically positioned within the road infrastructure, providing essential sensory data to these vehicles. The primary challenge lies in sensor placement, as it necessitates identifying optimal locations that minimize blind spots while maximizing the sensor’s coverage area. Therefore, to solve this problem, a method for positioning multiple sensor systems in road infrastructure is proposed. By introducing a voxel grid, the problem is formulated as an optimization challenge, and a genetic algorithm is employed to find a solution. Experimental findings using lidar sensors are presented to demonstrate the efficacy of this proposed approach.

End-to-end autonomous driving models often exhibit limited scalability because they rely on expert demonstration data. Imitation learning techniques such as Trajectory-guided Control Prediction (TCP) face adaptability limitations in varied environments, necessitating extensive data collection and retraining for novel driving scenarios, including static obstacle avoidance. To address this issue, we propose a hybrid framework integrating a pre-trained TCP model with a reinforcement learning (RL) module. The RL agent leverages TCP's latent features and trajectory predictions as its state. By interacting with a simulated environment and optimizing a task-specific reward function, the agent acquires an obstacle avoidance policy, eliminating the need for additional expert data. Experiments in the MORAI simulator demonstrate that our approach reduces vehicle collisions by 53.9% and pedestrian collisions by 45.9% compared to the baseline TCP model, while achieving higher route completion. These findings suggest that augmenting TCP with RL enhances system robustness and enables progressive expansion of driving capabilities, particularly for obstacle avoidance, without additional expert data. While this work focuses on static obstacle avoidance, the proposed TCP with RL framework can be adapted to other driving scenarios by modifying the reward and simulation setup without collecting new expert demonstrations.