This work proposes a strategy to avoid dynamic and static obstacles for robotic wheelchairs. A laser scanner onboard the vehicle is used to estimate the position and the velocity of the obstacles in a semi-structured environment. Once the model of the movement of the obstacles is estimated, points of wheelchair-obstacle collision are calculated. In the presence of dynamic obstacles, the obstacle avoidance strategy sets the commands of velocity based on such collision points allowing the wheelchair to overtake the most critical obstacle or to wait till being overtaken by it, i.e., increasing or decreasing the linear velocity of the vehicle, respectively. A local mapping is also proposed in order to improve the safety during maneuvers to avoid static obstacles. Real-time simulation results highlight the good performance of the proposed strategy. © 2010 IEEE.