Probabilistic Collision Constraint for Motion Planning in Dynamic Environments

Online generation of collision free trajectories is prime importance for autonomous navigation. Dynamic environments, robot motion and sensing uncertainties adds further challenges to avoidance systems. This paper presents an approach in dynamic incorporating obstacle state uncertainties. We derive a tight upper bound probability between formulate it as planning constraint which solvable real time. The proposed tested simulation considering mobile robots well quadrotors demonstrate that successful achieved time application. also provide comparison our with several state-of-the-art methods.