Dynamic Grasping with a Learned Meta-Controller

TL;DR

This paper introduces a reinforcement learning-based meta-controller that dynamically adjusts parameters in a robotic grasping pipeline, significantly improving success rates and efficiency in cluttered, dynamic environments.

Contribution

It presents a novel meta-controller that learns to adapt look-ahead time and planning time budget during dynamic grasping, outperforming fixed-parameter approaches.

Findings

Up to 28% increase in grasping success rate in cluttered environments.

Reduces grasping time compared to baseline methods.

Generalizes well to unseen obstacles and more complex scenes.

Abstract

Grasping moving objects is a challenging task that requires multiple submodules such as object pose predictor, arm motion planner, etc. Each submodule operates under its own set of meta-parameters. For example, how far the pose predictor should look into the future (i.e., look-ahead time) and the maximum amount of time the motion planner can spend planning a motion (i.e., time budget). Many previous works assign fixed values to these parameters; however, at different moments within a single episode of dynamic grasping, the optimal values should vary depending on the current scene. In this work, we propose a dynamic grasping pipeline with a meta-controller that controls the look-ahead time and time budget dynamically. We learn the meta-controller through reinforcement learning with a sparse reward. Our experiments show the meta-controller improves the grasping success rate (up to 28% in the most cluttered environment) and reduces grasping time, compared to the strongest baseline. Our meta-controller learns to reason about the reachable workspace and maintain the predicted pose within the reachable region. In addition, it assigns a small but sufficient time budget for the motion planner. Our method can handle different objects, trajectories, and obstacles. Despite being trained only with 3-6 random cuboidal obstacles, our meta-controller generalizes well to 7-9 obstacles and more realistic out-of-domain household setups with unseen obstacle shapes.