How to Better Train VLAs: Lessons Learned From the REAL-I Challenge at ICRA 2026

2026-09-11

AI Summary

研究通过REAL-I挑战探讨如何更有效地从固定演示预算中学习机器人策略，比较了不同团队的方法，强调了适应环境、数据管理和抑制错误的重要性。

Abstract

How can robot policies learn more effectively from a fixed demonstration budget? The first Real-world Embodied AI Learning (REAL-I) Challenge at ICRA 2026 examined this question through simulation, real-robot evaluation, and an on-site final on a shared dual-arm humanoid platform. We describe the challenge tasks, data and deployment interfaces, and competition results, then compare the approaches contributed by NUS-CLEAR, RCL-Lab, and Deeptouch.ai. Their systems combined pretrained vision-language-action models and task-specific imitation policies with different strategies for data curation, staged adaptation, checkpoint selection, and action-space design. The team reports highlight the importance of adapting to the deployment environment while retaining prior capabilities, treating demonstration quality at an appropriate temporal scale, and suppressing errors in inactive robot components. They also expose the limitations of offline action-prediction metrics for forecasting closed-loop success. These observations motivate a view of fixed-data robot learning that integrates data, adaptation, evaluation, and deployment.

Problem

• fixed demonstration budget
• robot policies
• effective learning
• embodied AI
• real-robot evaluation

Innovation

• pretrained vision-language-action models
• staged adaptation
• data curation