On July 7, 2026, Lingbo Technology, a subsidiary under the umbrella of Ant Group, proudly announced the launch of its cutting-edge spatial perception model, LingBot-Depth 2.0. This model has been meticulously trained on an extensive dataset comprising 150 million samples, undergoing thorough enhancements in several key areas. These improvements include sharper edge definition, more precise small object recognition, accurate long-distance depth estimation, and heightened robustness in intricate and challenging scenarios. Moreover, the introduction of the visual foundation model, LingBot-Vision, marks a significant milestone. It establishes a comprehensive capability chain, enabling robots to evolve from merely 'seeing clearly' to 'seeing with pinpoint accuracy,' thereby tackling the fundamental challenges in robot vision technology.
