A Hierarchical, Model-Based System for High-Performance Humanoid Soccer
🤖 AI Summary
Addressing the challenges of real-time perception, robust localization, obstacle-aware navigation, tactical decision-making, and high-power kicking in dynamic adversarial environments for RoboCup AdultSize humanoid soccer, this work presents a fully autonomous, high-performance system targeting long-term competitiveness with human athletes. To overcome these interdependent challenges, we introduce three core innovations: (1) a novel lightweight foot mechanism co-optimizing gait stability and kicking torque output; (2) a tightly coupled perception–localization framework integrating stereo vision, YOLO-based object detection, and multi-source landmark filtering via EKF/UKF; and (3) a collision-aware trajectory generation scheme based on model predictive control (MPC), coordinated by a centralized hierarchical state machine for behavior management. The system is implemented using quasi-direct-drive actuation and ROS2 real-time middleware. Deployed on the ARTEMIS robot, it secured the 2024 RoboCup AdultSize World Championship, achieving state-of-the-art performance in high-speed locomotion, precise passing, multi-robot coordination, and reliable shooting.
Application Category
📝 Abstract
The development of athletic humanoid robots has gained significant attention as advances in actuation, sensing, and control enable increasingly dynamic, real-world capabilities. RoboCup, an international competition of fully autonomous humanoid robots, provides a uniquely challenging benchmark for such systems, culminating in the long-term goal of competing against human soccer players by 2050. This paper presents the hardware and software innovations underlying our team's victory in the RoboCup 2024 Adult-Sized Humanoid Soccer Competition. On the hardware side, we introduce an adult-sized humanoid platform built with lightweight structural components, high-torque quasi-direct-drive actuators, and a specialized foot design that enables powerful in-gait kicks while preserving locomotion robustness. On the software side, we develop an integrated perception and localization framework that combines stereo vision, object detection, and landmark-based fusion to provide reliable estimates of the ball, goals, teammates, and opponents. A mid-level navigation stack then generates collision-aware, dynamically feasible trajectories, while a centralized behavior manager coordinates high-level decision making, role selection, and kick execution based on the evolving game state. The seamless integration of these subsystems results in fast, precise, and tactically effective gameplay, enabling robust performance under the dynamic and adversarial conditions of real matches. This paper presents the design principles, system architecture, and experimental results that contributed to ARTEMIS's success as the 2024 Adult-Sized Humanoid Soccer champion.
Problem
Research questions and friction points this paper is trying to address.
Develops a high-performance humanoid robot for autonomous soccer competition
Integrates lightweight hardware and robust software for dynamic gameplay
Enables reliable perception, navigation, and decision-making in adversarial matches
Innovation
Methods, ideas, or system contributions that make the work stand out.
Lightweight structure with high-torque quasi-direct-drive actuators
Stereo vision and landmark fusion for reliable perception and localization
Centralized behavior manager coordinating navigation and kick execution
🔎 Similar Papers
No similar papers found.
