Orbbec, a company known for robotics and AI vision, has partnered with Robbyant, an AI company, to make LingBot-Depth, a model that helps robots understand their surroundings better. This model uses high-precision depth sensing to improve how robots see and interact with complex environments.
Orbbec provided the necessary depth-sensing hardware and technical support for developing and testing LingBot-Depth. The model was fine-tuned using Orbbec’s Gemini 330 stereo depth camera, resulting in a major improvement in accuracy. The model performs better than other leading models in challenging environments, like indoor scenes and sparse 3D tasks, by lowering errors and improving depth estimation.
LingBot-Depth works by utilizing data from Orbbec’s Gemini 330 camera to fill in missing depth information, helping robots see more clearly and complete tasks more successfully. This is especially helpful in tricky situations where regular cameras face difficulty, like with glass or shiny surfaces, which can cause errors.
The collaboration shows how combining advanced hardware with smart algorithms can make robots more reliable in real-world situations. The new system is optimized without changing the camera hardware, proving that working together on both hardware and software can make a big difference in robot performance.
As per Coherent Market Insights, the Cloud robotics market will grow at a 22.8% compound annual growth rate (CAGR) from 2025 to 2032, from USD 9.27 Bn in 2025 to around USD 39.04 Bn by 2032. Many industrial processes such as painting, machining, material handling, welding, and assembling are now being replaced with automated robots. These robots use electrical, mechanical, and software systems to perform the designated task with higher accuracy, speed, and precision, which exceeds human performance.
“Robbyant’s work in spatial intelligence models and algorithms complements Orbbec’s expertise in 3D vision chips and robotic vision systems,” said Len Zhong, Head of Product Management of Orbbec. “In this collaboration, the chip-level depth data provided by the Gemini 330 delivers a stable, high-fidelity, and physically grounded data foundation for the LingBot-Depth model. This is an exemplary case of close coupling between a robot’s sensing hardware and its perception intelligence.”
Shen Yujun, Chief Technology Officer of Robbyant, noted, “Reliable 3D vision is critical to the advancement of embodied AI. By open-sourcing LingBot-Depth and collaborating with hardware pioneers like Orbbec, we aim to lower the barrier to advanced spatial perception and accelerate the adoption of embodied intelligence across homes, factories, warehouses, and beyond.”
Source:
News: Orbbec