MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202631077416 A) filed by Kalinga Institute Of Industrial Technology Kiit Deemed To Be University on June 23, 2026, for Gradient-Based Optimization For Robotic Path Planning.
Inventor includes Samal, Padarbinda.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: A method and system for robotic path planning using gradient-based optimization. The method initializes input parameters including a population size, a maximum number of iterations, and bounds for waypoint positions. An initial population of candidate paths is generated, where each candidate path comprises waypoints representing positions through which a robot passes in a workspace. A as claimed in claim cost function is evaluated for each candidate path, the as claimed in claim cost function comprising a weighted combination of a path length component, a collision penalty component, a smoothness penalty component, and a waypoint spacing penalty component. A gradient search rule updates candidate solutions in the population. A local escaping operator is applied to avoid entrapment in local optima. Boundary and constraint handling ensures candidate solutions remain within valid position bounds. When stopping criteria are met, an optimized path is output representing a trajectory for the robot to navigate while avoiding obstacles. (Fig. 1)
Disclaimer: Curated by HT Syndication.
