Goal state driven trajectory optimization

Many applications demand a dynamical system to reach a goal state under kinematic and dynamic (i.e., kinodynamic) constraints. Moreover, industrial robots perform such motions over and over again and therefore demand efficiency, i.e., optimal motion. In many applications, the initial state may not be constrained and can be taken as an additional variable for optimization. The semi-stochastic kinodynamic planning (SKIP) algorithm presented in this paper is a novel method for trajectory optimization of a fully actuated dynamic system to reach a goal state under kinodynamic constraints. The basic principle of the algorithm is the parameterization of the motion trajectory to a vector in a high-dimensional space. The kinematic and dynamic constraints are formulated in terms of time and the trajectory parameters vector. That is, the constraints define a time-varying domain in the high dimensional parameters space. We propose a semi stochastic technique that finds a feasible set of parameters satisfying the constraints within the time interval dedicated to task completion. The algorithm chooses the optimal solution based on a given cost function. Statistical analysis shows the probability to find a solution if one exists. For simulations, we found a time-optimal trajectory for a 6R manipulator to hit a disk in a desired state.