Real-time trajectory generation for omnidirectional vehicles

We discuss a method of generating near-optimal trajectories for a robot with omnidirectional drive capabilities, taking the second-order dynamics of the vehicle into account. The relaxation of optimality results in immense computational savings, critical in dynamic environments. In particular, a decoupling strategy for each of the three degrees of freedom of the vehicle is presented, along with a method for coordinating the degrees of freedom. A nearly optimal trajectory for the vehicle can typically be calculated in less than 1000 floating point operations, which makes it attractive for real-time control in dynamic and uncertain environments.