Active Constraint Learning in High Dimensions from Demonstrations
This work addresses the challenge of efficiently inferring constraints from sparse demonstrations for robotics or autonomous systems, representing an incremental improvement over existing methods.
The paper tackles the problem of learning unknown constraints from demonstrations in high-dimensional environments by proposing an iterative active constraint learning algorithm that uses Gaussian processes to query informative demonstrations, resulting in outperforming a random-sampling baseline in simulation and hardware experiments.
We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the demonstrator's environment. Our approach iteratively trains a Gaussian process (GP) on the available demonstration dataset to represent the unknown constraints, uses the resulting GP posterior to query start/goal states, and generates informative demonstrations which are added to the dataset. Across simulation and hardware experiments using high-dimensional nonlinear dynamics and unknown nonlinear constraints, our method outperforms a baseline, random-sampling based method at accurately performing constraint inference from an iteratively generated set of sparse but informative demonstrations.