Abstract
Maneuvers of a nonholonomic vehicle in a structured dynamic environment are considered. The paper focuses on motion generation and control methods to autonomously perform lane following/changing, parallel parking and returning to traffic maneuvers. Lane following/changing involves the tracking of a nominal trajectory in the traffic lane, and the generation and tracking of local lane-changing trajectories, for instance, for obstacle avoidance. The key idea of the control approach for the parallel parking and returning to traffic maneuvers is to perform a sequence of controlled motions using sensor data from the car servo-systems and range measurements of the local environment. Appropriate steering and velocity controls are computed in real time and executed to accomplish the planned maneuvers. The methods developed are tested on an automatic electric vehicle.