Learning Dynamic Pick-and-Place for a Legged Manipulator

TL;DR

This paper introduces a hierarchical reinforcement learning framework enabling a quadruped robot with a robotic arm to perform dynamic pick-and-place tasks, effectively handling heavier payloads and larger workspaces through adaptive whole-body control.

Contribution

The work presents a novel RL-based approach with explicit mass estimation for agile, continuous pick-and-place operations in quadruped robots, surpassing prior lightweight, slow-motion methods.

Findings

Achieved 86.05% success rate in simulation with payloads up to 2.3 kg.

Demonstrated 73.3% success rate in real-world scenarios with payloads up to 1.3 kg.

System executes pick-and-place within an average of 4.06 seconds across various tasks.

Abstract

Legged manipulators extend robotic capabilities beyond static manipulation by integrating agile locomotion with versatile arm control. However, achieving precise manipulation while maintaining coordinated locomotion remains a major challenge. This work presents a hierarchical reinforcement learning framework for dynamic pick-and-place tasks using a quadruped equipped with a 6-DOF robotic arm. The framework incorporates an explicit mass estimation module enabling adaptive whole-body control for objects with varying weights. In simulation, the system achieves an 86.05% success rate with payloads up to 2.3 kg. The approach is further validated through real-world experiments across six representative scenarios with controlled variations in object physical properties (size and mass) and task heights. Specifically, within a wide vertical workspace ranging from ground level to 1.1~m-high tabletops, the system demonstrates an average success rate of 73.3% for payloads up to 1.3 kg, with an average execution time of 4.06 s. Unlike prior works that handle lightweight objects and execute pick-and-place motions with slow, piecewise motions, the proposed framework exploits concurrent locomotion and manipulation for dynamic, continuous execution. These results demonstrate the potential of quadrupedal mobile manipulators for adaptive, whole-body pick-and-place with heavier payloads and extended workspaces.