发表机构
The Chinese University of Hong Kong, Shenzhen; DexForce; The Chinese University of Hong Kong; The Hong Kong University of Science and Technology; University of Colorado Anschutz; Mila - Quebec AI Institute; Vector Institute; University of Waterloo; Fudan University; Sun Yat-sen University; Shenzhen Loop Area Institute (SLAI)（香港中文大学（深圳）; 德克斯力公司; 香港中文大学; 香港科技大学; 科罗拉多大学安舒茨医学中心; 米拉-魁北克人工智能研究所; 向量研究所; 滑铁卢大学; 复旦大学; 中山大学; 深圳环区研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RoboSynChallenge竞赛推出统一基准，结合合成数据与真实评估，提供多类基准策略，旨在推动开发泛化性强、数据高效的机器人操作系统，助力通用机器人智能发展。
AI 中文摘要
实现可泛化的机器人操作仍是具身智能领域的核心挑战。尽管模型架构与学习算法发展迅速，但进展常受限于真实世界数据的稀缺性和狭窄多样性。RoboSynChallenge竞赛推出统一基准，用于评估和推进操作策略在一系列任务、环境和难度等级中的泛化能力。为缓解真实数据短缺问题，该竞赛整合大规模合成数据生成与标准化真实世界机器人评估，鼓励参与者利用合成状态-动作试验提升通用策略学习，最终评估仅在未见过的真实世界操作环境中开展。竞赛提供Transformer、Diffusion、视觉-语言-动作（Vision-Language-Action）及世界-动作模型（World-Action-Model）等基准实现，以确保可复现性和可比性。通过将可扩展的基于仿真的训练与严格的真实世界验证相结合，RoboSynChallenge旨在推动开发具备广泛能力、数据高效且适应性强的操作系统，从而为实现真正通用的机器人智能铺平道路。
英文摘要
Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress is often limited by the scarcity and narrow diversity of real-world data. The RoboSynChallenge competition introduces a unified benchmark to evaluate and advance the generalizability of manipulation policies across a spectrum of tasks, environments, and difficulty levels. To alleviate the shortage of realistic data, the challenge integrates large-scale synthetic data generation with standardized real-world robotic evaluation. Participants are encouraged to leverage synthesized state-action trials to improve general-purpose policy learning, while final assessments are conducted exclusively on unseen real-world manipulation environments. Baseline implementations, including Transformer-, Diffusion-, Vision-Language-Action, and World-Action-Model-based policies, are provided to ensure reproducibility and comparability. By coupling scalable simulation-based training with rigorous real-world validation, RoboSynChallenge aims to foster the development of broadly capable, data-efficient, and adaptable manipulation systems, thereby paving the way toward truly general robotic intelligence.
CommentsNeurIPS 2026 Competition Track
