Reactive Trajectory Planning and Tracking for Pedestrian-Aware Autonomous Driving in Urban Environments

In this paper, we address the problem of trajectory planning while simultaneously reacting to the presence of pedestrians for an autonomous car on urban roads. Past work limits jerk, velocities and acceleration for smooth trajectories, without considering reactive behaviors such as responding to pedestrians. Other systems based on collision avoidance, plan paths around obstacles and pedestrians in unstructured environments. In this paper, we present an integrated trajectory generation and tracking system. Our system simultaneously considers both parameter and reactive constraints for smooth trajectory and updates it in real-time. We present a novel online method for planning trajectories to follow a given urban path while honoring traffic regulations such as stop signs at intersections. We update the trajectory to safely avoid pedestrians on the road by slowing down or stopping. Our method has closed form solutions, runs at 20 Hz, and is efficient and reliable for use in online planning. We have confirmed this with a test vehicle and pedestrians with over 100 hours of testing under driverless operation.