Residual Reinforcement Learning for Waste-Container Lifting Using Large-Scale Cranes with Underactuated Tools

TL;DR

This paper introduces a residual reinforcement learning approach that enhances the precision and robustness of crane-based waste container lifting tasks by combining nominal control with learned residual policies, validated through simulation.

Contribution

It presents a novel residual RL method integrating nominal Cartesian control with learned residuals for large-scale crane operations, improving accuracy and robustness in simulation.

Findings

Enhanced tracking accuracy and stability

Higher success rates in lifting tasks

Robustness to parameter variations

Abstract

This paper studies the container lifting phase of a waste-container recycling task in urban environments, performed by a hydraulic loader crane equipped with an underactuated discharge unit, and proposes a residual reinforcement learning (RRL) approach that combines a nominal Cartesian controller with a learned residual policy. All experiments are conducted in simulation, where the task is characterized by tight geometric tolerances between the discharge-unit hooks and the container rings relative to the overall crane scale, making precise trajectory tracking and swing suppression essential. The nominal controller uses admittance control for trajectory tracking and pendulum-aware swing damping, followed by damped least-squares inverse kinematics with a nullspace posture term to generate joint velocity commands. A PPO-trained residual policy in Isaac Lab compensates for unmodeled dynamics and parameter variations, improving precision and robustness without requiring end-to-end learning from scratch. We further employ randomized episode initialization and domain randomization over payload properties, actuator gains, and passive joint parameters to enhance generalization. Simulation results demonstrate improved tracking accuracy, reduced oscillations, and higher lifting success rates compared to the nominal controller alone.