In this thesis, four robots will be used to implement a collision-free trajectory planning/replanning algorithm. The existence of a chained form transformation so that the robot's model can be control in canonical form will be analyzed and proved. A trajectory generation for obstacles avoidance will be derived, simulated, and implemented. A specific PC based control algorithm will be developed. Chapter two describes two wheels differential drive robot modeling and existence of controllable canonical chained form. Chapter 3 describes criterion for avoiding dynamic objects, a feasible collision-free trajectory parameterization, and solution to steering velocity. Chapter 4 describes robot implementation, pc wireless interface, and strategy to send and receive information wirelessly. The main robot will be moving in a dynamically changing environment using canonical chained form. The other three robots will be used as moving obstacles that will move with known piecewise constant velocities, and therefore, with known trajectories. Their initial positions are assumed to be known as well. The main robot will receive the command from the computer such as how fast to move and to turn in order to avoid collision. The robot will autonomously travel to the desired destination collision-free.