SLOT-V: Supervised Learning of Observer Models for Legible Robot Motion Planning in Manipulation

TL;DR

SLOT-V is a supervised learning framework that effectively learns observer models for legible robot motion planning, improving trajectory transparency and human-robot interaction in manipulation tasks.

Contribution

It introduces a supervised learning approach to derive observer models from data, encompassing existing handcrafted models and demonstrating strong generalization and sample efficiency.

Findings

SLOT-V accurately predicts various handcrafted observer models.

It generalizes well to unseen goal configurations and counts.

It learns better models with less data compared to IRL methods.

Abstract

We present SLOT-V, a novel supervised learning framework that learns observer models (human preferences) from robot motion trajectories in a legibility context. Legibility measures how easily a (human) observer can infer the robot's goal from a robot motion trajectory. When generating such trajectories, existing planners often rely on an observer model that estimates the quality of trajectory candidates. These observer models are frequently hand-crafted or, occasionally, learned from demonstrations. Here, we propose to learn them in a supervised manner using the same data format that is frequently used during the evaluation of aforementioned approaches. We then demonstrate the generality of SLOT-V using a Franka Emika in a simulated manipulation environment. For this, we show that it can learn to closely predict various hand-crafted observer models, i.e., that SLOT-V's hypothesis space encompasses existing handcrafted models. Next, we showcase SLOT-V's ability to generalize by showing that a trained model continues to perform well in environments with unseen goal configurations and/or goal counts. Finally, we benchmark SLOT-V's sample efficiency (and performance) against an existing IRL approach and show that SLOT-V learns better observer models with less data. Combined, these results suggest that SLOT-V can learn viable observer models. Better observer models imply more legible trajectories, which may - in turn - lead to better and more transparent human-robot interaction.