Learning to Shift Attention for Motion Generation

TL;DR

This paper introduces a novel motion generation model that captures multiple demonstration modes using local latent representations and real-valued non-volume preserving transformations, while also enabling the robot to shift attention between local frames for better extrapolation, demonstrated on complex docking tasks.

Contribution

The paper proposes a new model combining local latent representations with attention shifting to improve motion generation from limited demonstrations and handle multiple modes.

Findings

Outperforms previous methods on complex docking tasks

Demonstrates effective extrapolation in real robot experiments

Successfully captures multiple demonstration modes

Abstract

One challenge of motion generation using robot learning from demonstration techniques is that human demonstrations follow a distribution with multiple modes for one task query. Previous approaches fail to capture all modes or tend to average modes of the demonstrations and thus generate invalid trajectories. The other difficulty is the small number of demonstrations that cannot cover the entire working space. To overcome this problem, a motion generation model with extrapolation ability is needed. Previous works restrict task queries as local frames and learn representations in local frames. We propose a model to solve both problems. For multiple modes, we suggest to learn local latent representations of motion trajectories with a density estimation method based on real-valued non-volume preserving (RealNVP) transformations that provides a set of powerful, stably invertible, and learnable transformations. To improve the extrapolation ability, we propose to shift the attention of the robot from one local frame to another during the task execution. In experiments, we consider the docking problem used also in previous works where a trajectory has to be generated to connect two dockers without collision. We increase complexity of the task and show that the proposed method outperforms other approaches. In addition, we evaluate the approach in real robot experiments.