Design of a 3-DOF Hopping Robot with an Optimized Gearbox: An Intermediate Platform Toward Bipedal Robots

2025-05-18

AI Summary

There is a need for an intermediate platform to accelerate bipedal robot development. Method: This paper proposes a three-degree-of-freedom anthropomorphic legged jumping robot designed for dynamic, repeatable jumping. It introduces a novel compact 3K compound planetary gearbox, whose gear geometry is optimized via mixed-integer nonlinear programming (MINLP); integrates custom brushless joint actuators, embedded control, and communication modules; and implements a reinforcement learning–based real-time jumping controller, validated through hardware-in-the-loop experiments. Results/Contribution: The robot (mass: 12.45 kg; maximum extended height: 840 mm) achieves stable, command-responsive repetitive jumping, confirming its viability as a foundational platform for bipedal robotics. Key contributions include: (1) a MINLP-optimized high-performance planetary gearbox; (2) a highly integrated mechatronic architecture; and (3) a reinforcement learning control framework explicitly tailored to jumping dynamics.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

This paper presents a 3-DOF hopping robot with a human-like lower-limb joint configuration and a flat foot, capable of performing dynamic and repetitive jumping motions. To achieve both high torque output and a large hollow shaft diameter for efficient cable routing, a compact 3K compound planetary gearbox was designed using mixed-integer nonlinear programming for gear tooth optimization. To meet performance requirements within the constrained joint geometry, all major components-including the actuator, motor driver, and communication interface-were custom-designed. The robot weighs 12.45 kg, including a dummy mass, and measures 840 mm in length when the knee joint is fully extended. A reinforcement learning-based controller was employed, and robot's performance was validated through hardware experiments, demonstrating stable and repetitive hopping motions in response to user inputs. These experimental results indicate that the platform serves as a solid foundation for future bipedal robot development.

Problem

• Designing a 3-DOF hopping robot with human-like joints
• Optimizing gearbox for high torque and cable routing
• Validating stable hopping using reinforcement learning control

Innovation

• Compact 3K compound planetary gearbox design
• Custom-designed actuator and motor components
• Reinforcement learning-based hopping controller