Fast and Bounded Probabilistic Collision Detection for High-DOF Robots in Dynamic Environments

We present a novel approach to performing probabilistic collision detection between a high-DOF robot and imperfect obstacle representations in dynamic, uncertain environments. These uncertainties are modeled using Gaussian distributions. We present an efficient algorithm for bounded collision probability approximation. We use our probabilistic collision algorithm for trajectory optimization in dynamic scenes for 7DOF robots. We highlight its performance in challenging simulated and real-world environments with robot arms operating next to dynamically moving human obstacles.