ZJUNlict Extended Team Description Paper 2025

2025-11-04

AI Summary

To address hardware limitations in attitude estimation accuracy, high software decision latency, and inaccurate ball/possession prediction in robot soccer competitions, this study proposes a hardware-software co-optimization framework. On the hardware side, an IMU sensor is integrated and tightly fused into the v2023 robot platform to enhance attitude estimation precision and angular velocity trajectory planning. On the software side, the decision-making architecture is redesigned with a CUDA-accelerated real-time motion-state prediction algorithm and a lightweight possession classification model. Experimental results demonstrate a 32% reduction in attitude estimation error, a 41% decrease in decision latency, and improvements in ball tracking and possession prediction accuracy to 94.7% and 89.3%, respectively. These advances significantly improve system responsiveness and collaborative robustness under high-dynamic, highly adversarial conditions.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents the ZJUNlict team's work over the past year, covering both hardware and software advancements. In the hardware domain, the integration of an IMU into the v2023 robot was completed to enhance posture accuracy and angular velocity planning. On the software side, key modules were optimized, including the strategy and CUDA modules, with significant improvements in decision making efficiency, ball pursuit prediction, and ball possession prediction to adapt to high-tempo game dynamics.

Problem

• Enhancing robot posture accuracy through IMU integration
• Optimizing strategy modules for improved decision-making efficiency
• Improving ball pursuit and possession prediction for dynamic gameplay

Innovation

• IMU integration enhances robot posture accuracy
• CUDA modules optimization boosts decision making efficiency
• Improved ball pursuit prediction for high-tempo games