Jointly Learning Cost and Constraints from Demonstrations for Safe Trajectory Generation

TL;DR

This paper introduces a two-step optimization method for robots to learn both cost functions and unknown constraints from demonstrations, improving safety and adaptability in trajectory generation.

Contribution

It proposes a novel decoupled learning approach that estimates cost and constraints separately, enabling inference of unknown constraints without prior knowledge.

Findings

Successfully inferred unknown constraints like obstacles from demonstrations.

Demonstrated improved safety and accuracy in simulated and real robotic tasks.

Showed the importance of correct cost estimation for constraint learning.

Abstract

Learning from Demonstration allows robots to mimic human actions. However, these methods do not model constraints crucial to ensure safety of the learned skill. Moreover, even when explicitly modelling constraints, they rely on the assumption of a known cost function, which limits their practical usability for task with unknown cost. In this work we propose a two-step optimization process that allow to estimate cost and constraints by decoupling the learning of cost functions from the identification of unknown constraints within the demonstrated trajectories. Initially, we identify the cost function by isolating the effect of constraints on parts of the demonstrations. Subsequently, a constraint leaning method is used to identify the unknown constraints. Our approach is validated both on simulated trajectories and a real robotic manipulation task. Our experiments show the impact that incorrect cost estimation has on the learned constraints and illustrate how the proposed method is able to infer unknown constraints, such as obstacles, from demonstrated trajectories without any initial knowledge of the cost.