从物理角度设计攻击方法，让机器人抓不住物体
AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective
- 通过变形物体形状增加重力扭矩，降低抓取稳定性
- 在多个场景中使抓取成功率下降超过40%
- 适合研究机器人抓取鲁棒性与安全性的学者
针对机器人抓取的对抗攻击为评估和提升系统鲁棒性提供了重要视角。与仅关注神经网络预测而忽视抓取物理原理的研究不同，本文提出从物理视角出发的对抗攻击框架AdvGrasp。该框架聚焦两个核心方面：抗重力提升能力（lift capability）和抗扰动稳定性（grasp stability）。通过改变物体形状以增大重力力矩并减小力矩空间（wrench space）中的稳定裕度，系统性地削弱这两项关键抓取指标，生成能破坏抓取性能的对抗物体。大量实验验证了AdvGrasp的有效性，真实世界测试进一步证明其鲁棒性与实用性。
原文摘要 · Abstract (English)
Adversarial attacks on robotic grasping provide valuable insights into evaluating and improving the robustness of these systems. Unlike studies that focus solely on neural network predictions while overlooking the physical principles of grasping, this paper introduces AdvGrasp, a framework for adversarial attacks on robotic grasping from a physical perspective. Specifically, AdvGrasp targets two core aspects: lift capability, which evaluates the ability to lift objects against gravity, and grasp stability, which assesses resistance to external disturbances. By deforming the object's shape to increase gravitational torque and reduce stability margin in the wrench space, our method systematically degrades these two key grasping metrics, generating adversarial objects that compromise grasp performance. Extensive experiments across diverse scenarios validate the effectiveness of AdvGrasp, while real-world validations demonstrate its robustness and practical applicability
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。