Shanghai, January 27, 2025 — Orbbec, a leading provider of robotics and AI vision, today announced a strategic partnership with Robbyant, an embodied AI company within Ant Group, to advance spatial intelligence for robotics through the launch of LingBot-Depth, a high-precision open-source spatial perception model.
Orbbec provided critical depth sensing hardware and technical support throughout LingBot-Depth’s development and testing phases. The model was jointly optimized on Orbbec’s platforms, with resulting performance validated and certified by Orbbec’s Depth Vision Laboratory. This collaboration demonstrates the power of coupling high-fidelity sensing hardware with advanced perception algorithms to enable robots to operate reliably in visually complex real-world environments.
Breakthrough Performance in Challenging Scenarios
In benchmark evaluations on NYUv2 and ETH3D, LingBot-Depth achieves state-of-the-art depth estimation accuracy across diverse and challenging scenarios, outperforming leading models such as PromptDA and PriorDA. Co-optimized with Orbbec’s Gemini 330 stereo depth camera, LingBot-Depth achieves a relative error (REL) reduction of over 70% in indoor scenes and reducing RMSE by approximately 47% on the challenging sparse Structure-from-Motion (SfM) task.
Using chip-level depth data directly from Gemini 330 cameras, LingBot-Depth intelligently reconstructs missing depth information, significantly improving robots’ perception robustness and task success rates in complex optical environments. The Gemini 330 was used throughout data collection, training, and validation, with LingBot-Depth optimized using high-quality depth data output directly by Orbbec’s depth processing engine.
Orbbec’s Hardware Foundation: Gemini 330 and MX6800 Chip
Traditional RGB-D cameras often struggle to capture reliable depth data from materials like glass, mirrors, and polished metal due to inherent limitations of optical sensing methods. These surfaces frequently result in missing depth information or severe noise, causing robots to miss objects or miscalculate distances—potentially leading to operational failures or safety risks.
Orbbec’s Gemini 330 stereo 3D camera integrates the company’s proprietary MX6800 depth engine chip, specifically developed for robotics applications. By fusing active and passive imaging technologies, the Gemini 330 delivers reliable 3D data across extreme lighting conditions—from complete darkness to direct sunlight. On-device depth computation and precise sensor synchronization reduce system latency and host compute requirements, enabling seamless real-world deployment.
Robbyant developed Masked Depth Modeling (MDM) to address the industry-wide challenge of depth perception in complex environments. When depth inputs from a sensor are incomplete or corrupted, LingBot-Depth analyzes RGB image features—including texture, object contours, and scene context—to infer and reconstruct missing regions, producing denser, more accurate, and sharper 3D depth maps.
The results highlight the value of combining high-quality, chip-level depth data with algorithms designed for real-world conditions. These performance improvements are achieved without modifications to existing sensor form factors, demonstrating that hardware-software co-optimization can significantly enhance robot perception capabilities in challenging scenarios.
Industry-Leading Training Data
This performance is powered by extensive real-world training data. Robbyant collected approximately 10 million raw samples and curated a high-quality dataset of 2 million depth-RGB pairs, specifically optimized for extreme and ambiguous conditions. Robbyant plans to open-source this dataset in the near future to accelerate community-driven innovations in complex-scenario spatial perception.
Strategic Partnership and Future Outlook
“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.”
The two companies have signed a strategic agreement to develop next-generation depth cameras based on the LingBot-Depth model. Through continued technical collaboration and ecosystem development, Orbbec and Robbyant aim to provide robust technological support for real-world robot deployment.
Since entering the robotics sector in 2015, Orbbec has been a leading provider of robotics and AI vision, serving over 3,000 customers globally. The company currently holds over 70% market share in both China’s service robotics and South Korea’s mobile robotics 3D vision markets. Moving forward, Orbbec and Robbyant will continue to explore and deepen collaboration around “embodied perception × spatial intelligence,” driving stable deployment and scaled application of spatial intelligence technology in complex environments—accelerating robots’ evolution from “seeing the world” to “understanding and acting in the real world.”
To learn more about LingBot-Depth, please visit: https://github.com/robbyant/lingbot-depth
About Orbbec
Founded in 2013, Orbbec is a leading provider of robotics and AI Vision. The company delivers full-stack 3D vision solutions spanning structured light, stereo vision, ToF, and LiDAR technologies, serving over 3,000 customers across nearly 100 countries and regions. The company continues to sharpen its focus on robotic “eye” core technology in the AI era, advancing “hand-eye-brain” integration and multi-sensor fusion perception to empower the robotics industry toward more intelligent, versatile horizons.
About Robbyant
Robbyant is an embodied intelligence company within Ant Group, dedicated to advancing embodied intelligence through cutting-edge software and hardware technologies. Robbyant independently develops foundational large models for embodied AI and actively explores next-generation intelligent devices, aiming to create robotic companions and caregivers that truly understand and enhance people’s everyday lives and deliver reliable intelligent services across key use cases, such as elderly care, medical assistance, and household tasks.
To learn more about Robbyant, please visit: www.robbyant.com
