PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 2, 20250 citationsOpen Access

AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective

View Full Paper
XWXiaofei WangMHMingliang HanTHTianyu Hao

Key Points

  • Adversarial attacks systematically degrade key metrics like lift capability and grasp stability through targeted modifications.
  • The framework successfully identifies vulnerabilities in robotic grasping by manipulating object shape to increase gravitational torque.
  • Extensive experiments demonstrate the effectiveness of AdvGrasp in various scenarios, confirming its real-world applicability.
  • Insights gained from this approach may enable the development of more robust grasping systems in robotics.

Abstract

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

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/68de5da783cbc991d0a20c83https://doi.org/10.48550/arxiv.2507.09857
Ask AI
Helpful
Bookmark
Share
View Full Paper