Taking into account the effects of parameter uncertainties in the robot model is crucial to the robustness of motion generation. One approach to address this issue is to compute ‘uncertainty tubes’ enveloping the robot state for any combination of parameters within a given range, and to use these tubes to robustly check for collisions within a motion planning algorithm. However, computing these tubes for complex dynamical systems can be too computationally expensive due to the need to solve and integrate potentially numerous nonlinear ordinary differential equations (ODEs) associated with robot dynamics. To overcome this limitation, we propose a GRU-based architecture that provides fast and accurate estimation of these uncertainty tubes. We demonstrate that GRUs achieve the best compromise between prediction accuracy, prediction time, and network size compared to basic RNNs and LSTMs, justifying our choice. Finally, we showcase the efficiency of the learning process within a motion planning framework for an aerial vehicle.

Closed-loop state sensitivity [1], [2] is a recently introduced notion that can be used to quantify deviations of the closed-loop trajectory of a robot/controller pair against variations of uncertain parameters in the robot model. While local optimization techniques are used in [1], [2] to generate reference trajectories minimizing a sensitivity-based cost, no global planning algorithm considering this metric to compute collision-free motions robust to parametric uncertainties has yet been proposed. The contribution of this paper is to propose a global control-aware motion planner for optimizing a state sensitivity metric and producing collision-free reference motions that are robust against parametric uncertainties for a large class of complex dynamical systems. Given the prohibitively high computational cost of directly minimizing the state sensitivity using asymptotically optimal sampling-based tree planners, the proposed RRT*-based SAMP planner uses an appropriate steering method to first compute a (near) time-optimal and kinodynamically feasible trajectory that is then locally deformed to improve robustness and decrease its sensitivity to uncertainties. The evaluation performed on planar/full-3D quadrotor UAV models shows that the SAMP method produces low sensitivity robust solutions with a much higher performance than a planner directly optimizing the sensitivity.