Dynamic Obstacle Avoidance using Online Trajectory Time-scaling and Local Replanning

In various circumstances, planning at trajectory level is very useful to generate flexible collision-free motions for autonomous robots, especially when the system interacts with humans or human environment. This paper presents a simple and fast obstacle avoidance algorithm that operates at the trajectory level in real-time. The algorithm uses the Velocity Obstacle to obtain the boundary conditions required to avoid a dynamic obstacle, and then adjust the time evolution using the non-linear trajectory time-scaling scheme. A trajectory local replanning method is applied to make a detour when the static obstacles block the advance path of the robot, which leads to failure of implementing time-scaling approach. Cubic polynomial functions are used to describe trajectories, which brings sufficient flexibility in terms of providing higher order smoothness. We applied this algorithm on reaching tasks for a mobile robot. Simulation results demonstrate that the technique can generate collision-free motion in real time.