Active Learning of Abstract Plan Feasibility

TL;DR

This paper introduces an active learning method for efficiently predicting abstract plan feasibility in robotic manipulation, enabling real robot learning with minimal interactions and improving task planning reliability.

Contribution

It presents a novel active learning approach that uses curiosity-driven exploration and plan pruning to learn an APF predictor with less data in robotic tasks.

Findings

Learned APF model in 400 interactions on real robot

Model effectively predicts plan feasibility in stacking tasks

System improves downstream task planning performance

Abstract

Long horizon sequential manipulation tasks are effectively addressed hierarchically: at a high level of abstraction the planner searches over abstract action sequences, and when a plan is found, lower level motion plans are generated. Such a strategy hinges on the ability to reliably predict that a feasible low level plan will be found which satisfies the abstract plan. However, computing Abstract Plan Feasibility (APF) is difficult because the outcome of a plan depends on real-world phenomena that are difficult to model, such as noise in estimation and execution. In this work, we present an active learning approach to efficiently acquire an APF predictor through task-independent, curious exploration on a robot. The robot identifies plans whose outcomes would be informative about APF, executes those plans, and learns from their successes or failures. Critically, we leverage an infeasible subsequence property to prune candidate plans in the active learning strategy, allowing our system to learn from less data. We evaluate our strategy in simulation and on a real Franka Emika Panda robot with integrated perception, experimentation, planning, and execution. In a stacking domain where objects have non-uniform mass distributions, we show that our system permits real robot learning of an APF model in four hundred self-supervised interactions, and that our learned model can be used effectively in multiple downstream tasks.