用状态转移注意力提升机器人抓取对执行差异的适应能力
CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation
- 引入状态转移注意力机制，显式建模演示中的失败与恢复模式
- 在精密任务上性能超传统注意力两倍以上，仿真中表现最优
- 适合需要历史依赖决策的机器人操控场景，尤其关注鲁棒性
通过监督学习从示范中训练机器人操控策略时，当执行过程中出现训练未覆盖的变化，仍面临挑战。尽管注意力机制可融入历史上下文以增强鲁棒性，但标准方法对所有过去状态一视同仁，未显式建模演示中可能存在的时序结构（如失败与恢复模式）。本文提出跨状态转移注意力变换器（CroSTAta），采用新型状态转移注意力（STA）机制，根据学习到的状态演化模式调节标准注意力权重，使策略能基于执行历史更优地调整行为。该方法结合训练时的时间掩码策略，随机屏蔽近期视觉信息，促进模型从历史中进行时序推理。仿真评估表明，STA持续优于标准注意力及TCN、LSTM等时序建模方法，在精度关键任务上性能提升超过2倍。代码与数据见https://github.com/iit-DLSLab/croSTAta。
原文摘要 · Abstract (English)
Learning robotic manipulation policies through supervised learning from demonstrations remains challenging when policies encounter execution variations not explicitly covered during training. While incorporating historical context through attention mechanisms can improve robustness, standard approaches process all past states in a sequence without explicitly modeling the temporal structure that demonstrations may include, such as failure and recovery patterns. We propose a Cross-State Transition Attention Transformer that employs a novel State Transition Attention (STA) mechanism to modulate standard attention weights based on learned state evolution patterns, enabling policies to better adapt their behavior based on execution history. Our approach combines this structured attention with temporal masking during training, where visual information is randomly removed from recent timesteps to encourage temporal reasoning from historical context. Evaluation in simulation shows that STA consistently outperforms standard attention approach and temporal modeling methods like TCN and LSTM networks, achieving more than 2x improvement over cross-attention on precision-critical tasks. The source code and data can be accessed at https://github.com/iit-DLSLab/croSTAta
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。