When Pedestrians Hesitate: PPO-Based RL Collision Avoidance in Uncertain Scenarios

Pedestrian collision avoidance at unmarked crosswalks remains a critical challenge for Autonomous Vehicles (AVs), particularly when pedestrians exhibit hesitant or unpredictable behaviors. This work introduces a Reinforcement Learning (RL) framework wherein an AV learns to navigate such a scenario by reasoning under behavioral uncertainty. The environment is modeled as a Markov Decision Process (MDP), and the AV is trained using a Proximal Policy Optimization (PPO) algorithm augmented with a Long Short-Term Memory (LSTM) network. The AV selects among four discrete maneuvers: maintain speed, decelerate, dodge left, or dodge right, based on real-time observations. The pedestrian is modeled as a stochastic, contextaware agent with a tunable hesitation probability parameter (φh), modulating its likelihood to stop, reverse, or proceed depending on proximity to the crossing center. A shaped reward function incentivizes safe, timely, and socially compliant actions. Extensive simulations under varying levels of pedestrian hesitation show that the PPO-LSTM agent achieves a collision rate as low as C_R = 5.84% under φh = 0.1. The AV executes evasive maneuvers in 77.03% of decisions and completes episodes in an average of 3228 steps. These results highlight the agent s capacity to safely and adaptively handle pedestrian indecisiveness without relying on trajectory prediction models or multi-agent RL for AV-pedestrian interaction.