利用归纳偏置迈向安全的机器人基础模型
Towards Safe Robot Foundation Models Using Inductive Biases
AI总结：
针对机器人基础模型缺乏形式化安全保证且依赖大量安全演示的问题，本文提出在基础策略后接入 ATACOM 安全层，以几何归纳偏置强制动作约束，在操作和机器人空气曲棍球任务中验证了安全性与性能。
摘要：
安全性是机器人系统在真实世界中部署的一项关键要求。遗憾的是，尽管当前的机器人基础模型在多种多样的任务上展现出颇具前景的泛化能力，但它们未能解决安全性这一确保长期运行的重要方面。当前的机器人基础模型假设，通过从足够大规模的演示数据集中学习，安全行为应当会自然涌现。然而，这种方法存在两个明显的主要缺陷。首先，对于使用监督学习训练的行为克隆策略，并不存在形式化的安全保证。其次，在没有任何安全约束的显式知识的情况下，该策略可能需要数量多到不合理的额外演示，才能甚至只是近似期望的受约束行为。为了解决这些关键问题，我们展示了如何转而利用 ATACOM 将机器人基础模型与几何归纳偏置相结合；ATACOM 是一个置于基础策略之后的安全层，通过强制执行动作约束来确保安全的状态转移。借助这种方法，我们能够为通用策略确保形式化的安全保证，而无需提供大量安全行为演示，也无需任何针对安全性的特定微调。我们的实验表明，该方法既有利于经典操作任务（在此类任务中我们避免了与无关物体发生不必要的碰撞），也有利于动态任务，例如机器人空气曲棍球环境；在该环境中，我们能够生成既快速又遵守复杂任务和关节空间约束的轨迹。
英文摘要：
Safety is a critical requirement for the real-world deployment of robotic systems. Unfortunately, while current robot foundation models show promising generalization capabilities across a wide variety of tasks, they fail to address safety, an important aspect for ensuring long-term operation. Current robot foundation models assume that safe behavior should emerge by learning from a sufficiently large dataset of demonstrations. However, this approach has two clear major drawbacks. Firstly, there are no formal safety guarantees for a behavior cloning policy trained using supervised learning. Secondly, without explicit knowledge of any safety constraints, the policy may require an unreasonable number of additional demonstrations to even approximate the desired constrained behavior. To solve these key issues, we show how we can instead combine robot foundation models with geometric inductive biases using ATACOM, a safety layer placed after the foundation policy that ensures safe state transitions by enforcing action constraints. With this approach, we can ensure formal safety guarantees for generalist policies without providing extensive demonstrations of safe behavior, and without requiring any specific fine-tuning for safety. Our experiments show that our approach can be beneficial both for classical manipulation tasks, where we avoid unwanted collisions with irrelevant objects, and for dynamic tasks, such as the robot air hockey environment, where we can generate fast trajectories respecting complex tasks and joint space constraints.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
