Local planning is an essential module for Autonomous Driving Systems (ADS), in order for a vehicle to safely reach its destination by adapting to rapidly changing road conditions. Although some simple heuristic approaches may satisfy the real-time requirements of the local planning module, they tend to struggle in complex and dynamic scenarios. While a variety of approaches—including reachability-based, optimization-based, sampling-based, and learning-based methods—are capable of handling more complex scenarios in simulation, their practical effectiveness remains uncertain due to long computation time or limited experimental validation. In this paper, we propose an efficient and adaptable sampling-based local trajectory planning method to handle diverse scenarios while ensuring computational efficiency and robust performance in real-world environments. The proposed method leverages the Lateral Recursive Feasible Set (LRFS) to define the control input range based on road boundary constraints, ensuring sampled trajectories within the boundary. To further enhance trajectory sampling efficiency, we introduce a truncated normal distribution for control input sampling, allowing trajectories to remain within safe regions. The effectiveness of our method, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LRFS-MPPI</i>, is demonstrated through comparisons with existing sampling-based methods in terms of execution time, sampling efficiency, the quality of the determined trajectory in simulation, and validation through hardware experiments. The results show that LRFS-MPPI efficiently generates collision-free trajectories suitable for real-time autonomous driving.