Hierarchical Policy Blending as Inference for Reactive Robot Control

TL;DR

This paper introduces a hierarchical motion generation method for reactive robot control that combines reactive policies with planning via probabilistic inference, improving safety and efficiency in complex environments.

Contribution

It proposes a novel hierarchical framework using probabilistic inference and stochastic optimization to blend reactive and planning-based policies for robot motion generation.

Findings

Outperforms reactive controllers in cluttered environments

Achieves higher safety and efficiency in experiments

Effective in planar navigation and 6DoF manipulation

Abstract

Motion generation in cluttered, dense, and dynamic environments is a central topic in robotics, rendered as a multi-objective decision-making problem. Current approaches trade-off between safety and performance. On the one hand, reactive policies guarantee fast response to environmental changes at the risk of suboptimal behavior. On the other hand, planning-based motion generation provides feasible trajectories, but the high computational cost may limit the control frequency and thus safety. To combine the benefits of reactive policies and planning, we propose a hierarchical motion generation method. Moreover, we adopt probabilistic inference methods to formalize the hierarchical model and stochastic optimization. We realize this approach as a weighted product of stochastic, reactive expert policies, where planning is used to adaptively compute the optimal weights over the task horizon. This stochastic optimization avoids local optima and proposes feasible reactive plans that find paths in cluttered and dense environments. Our extensive experimental study in planar navigation and 6DoF manipulation shows that our proposed hierarchical motion generation method outperforms both myopic reactive controllers and online re-planning methods.