Gaussian Process Constraint Learning for Scalable Chance-Constrained Motion Planning from Demonstrations
This addresses scalable chance-constrained motion planning for robotics, enabling safer trajectory planning with minimal prior information, though it is incremental as it builds on existing constraint learning and GP techniques.
The paper tackles the problem of learning constraints from demonstrations for motion planning by proposing a method that uses Gaussian processes (GPs) and KKT optimality conditions to infer and generalize constraints, achieving accurate results on systems like a 5D car, 12D quadrotor, and 3-link arm while outperforming prior methods that need more prior knowledge.
We propose a method for learning constraints represented as Gaussian processes (GPs) from locally-optimal demonstrations. Our approach uses the Karush-Kuhn-Tucker (KKT) optimality conditions to determine where on the demonstrations the constraint is tight, and a scaling of the constraint gradient at those states. We then train a GP representation of the constraint which is consistent with and which generalizes this information. We further show that the GP uncertainty can be used within a kinodynamic RRT to plan probabilistically-safe trajectories, and that we can exploit the GP structure within the planner to exactly achieve a specified safety probability. We demonstrate our method can learn complex, nonlinear constraints demonstrated on a 5D nonholonomic car, a 12D quadrotor, and a 3-link planar arm, all while requiring minimal prior information on the constraint. Our results suggest the learned GP constraint is accurate, outperforming previous constraint learning methods that require more a priori knowledge.