MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541134714 A) filed by Pavan P; Guhan S; Lakshan S; and Kevin Kishore S L, Chamarajanagar, Karnataka, on Dec. 31, 2025, for 'hybrid ai-mechanical adaptive gripper with object recognition and force feedback control.'
Inventor(s) include Pavan P; Guhan S; Lakshan S; and Kevin Kishore S L.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to the development of a hybrid AI-mechanical adaptive gripper, developed for robust manipulation in unstructured environments, by effectively incorporating deep learning object recognition with real-time force feedback control. The Hybrid AI Gripper utilizes a compliant mechanical design with pneumatic actuators and shape-adaptive fingers, allowing for versatile gripping of various objects, ranging from delicate electronics to shape-invariant produce. The Hybrid AI Gripper utilizes a CNN to attain 96% object classification and 3D pose estimation accuracy on a multi-modal RGB-D image dataset, automatically switching grip approaches with reinforcement learning policies. Force feedback is implemented using on-board piezoelectric sensors, combined with a PID-extended impedance controller, to maintain optimal gripping forces between 0.5-50 N, while also overcoming the possibility of slipping and damaging the object. Experimental results on a set of 200 objects showcase a 92% success rate, which is 35% more adaptable than rigid grippers. The Hybrid AI Gripper has the potential to revolutionize the field by offering novel uses in precision agriculture for fruit picking, assembly, and assistive robotics."
Disclaimer: Curated by HT Syndication.
