Reproduce “Robust Adaptive Safe Robotic Grasping with Tactile Sensing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yitaek Kim, Jeeseop Kim, Albert H. Li, Aaron D. Ames, Christoffer Sloth
An integrated framework combines tactile sensing with Control Barrier Functions (CBFs) to provide formal safety guarantees for robust adaptive robotic grasping, preventing object damage and slippage. The Disturbance Observer CBF (DOBCBF) scheme achieved the least conservatism in experiments, reducing it by an average of 83.5% compared to purely robust methods while maintaining strict adherence to safety bounds.
Key insights
- CBF-based safety filters can effectively provide formal safety guarantees for robotic grasping by modifying control inputs to prevent contact force violations and slippage.
- Adaptive and disturbance-observing CBF schemes (RaCBF and DOBCBF) significantly reduce conservatism in safe grasping, enabling more efficient operation closer to safety boundaries than standard or purely robust CBFs.
- Integrating real-time, tactile sensor-based estimation of contact points, forces, and torques is crucial for responsive and practical CBF-based safe grasping in dynamic, uncertain environments.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.