Online Adaptable Trajectory using artificial Neural Networks for Unknown Environment

Abstract

Walking in unknown environment is complex process. If robots want to move in complex environment, they have to adapt the changes in trajectory due to uncertain circumstances(obstacles and ditches). In this paper, online trajectories are generated for given boundary conditions using neural networks due to it's universal approximation capabilities. Here, NN is used for coefficients calculation which can adapt a change in constraints during tracking. To investigate the idea that suggested trajectory will have continuous velocity and smooth acceleration, the trajectory has been formulated using neural networks for 4, 6, 7 and 9 constraints and compared. A trajectory is trained only in 2.82 seconds for 6 constraints and in 2 minutes 91 seconds for 7 constraints in matlabs on intel Core i5-4200 CPU, 2 Cores, 4 GB RAM laptop. We have tried to find the best trajectory fit in less computation and time. These NN trajectories can adapt the online changes in constraints due to uncertain environment conditions.