Intel has helped Chinese robotics company Geek+ develop a robot with depth vision perception to improve obstacle avoidance.

The autonomous mobile robot (AMR), equipped with Intel’s visual navigation modules, is targeting the digital and intelligent transformation of the logistics industry.

It not only possesses depth vision perception enabled by the Intel RealSense camera, but also features deep algorithmic innovations in V-Slam positioning, composite detection networks and robot following. This allows for accurate positioning, navigation and obstacle avoidance, helping enterprises cope with diverse and complex logistics scenarios while enhancing efficiency and accuracy.

The RealSense camera has an all-in-one design that enables all depth calculations to be performed directly within the device, resulting in low power consumption and independence from specific platforms or hardware. The camera provides core support for various vision-based AI options and, when paired with a dedicated visual processor, accelerates the machine-learning process and shortens the automation deployment cycle.

Thanks to the RealSense camera, the robot observes, understands, interacts with and learns from the environment. By obtaining accurate and consistent depth data from the environment, it accurately recognises and interacts with its surroundings.

In addition to the camera, the visual navigation module also includes a robotic vision hub, which contains components such as the Intel Core i7-1270P processor and connection modules. This provides computational support for algorithms running on the robot, including V-Slam positioning, composite detection networks and robot following, while enabling cloud-edge collaboration through high-speed networks.

Geek+ is working with Intel to engage in deep algorithmic innovation related to V-Slam positioning, composite detection networks and robot following:

• V-Slam positioning algorithm: It fuses multi-sensor data and various visual feature elements to generate composite maps, such as point feature, line feature, object and special area maps. It delivers reliable and precise positioning in complex and dynamic environments.
• Composite detection network: With both a traditional object detection network and a validation network, it processes detection data from multiple dimensions, thus enhancing accuracy and reducing the false detection rate.
• Robot following: By integrating modules such as personnel detection, re-identification, and visual target tracking, Geek+ has developed a flexible and efficient visual perception pipeline. Once the relative position between the target personnel and the AMR is determined, the local planning algorithm in Geek+’s self-developed RoboGo, a robotic standalone system, will enable autonomous obstacle avoidance, resulting in smooth AMR following of the target personnel.

Leveraging the depth perception of the visual navigation module and collaborative algorithmic innovation from both sides, the robot ensures high precision and efficiency in environmental perception, positioning and tracking. This helps logistics and warehousing service providers drive the transformation towards smart logistics. The robots are expected to see widespread adoption in areas such as factory and warehouse transportation, helping users build agile, digital and intelligent supply chains.

“The vision-only robot, developed in collaboration with Intel, effectively leverages the depth vision perception of the Intel RealSense camera,” said Solomon Lee, vice president at Geek+ (geekplus.com). “Together with the deep algorithmic innovations from both sides, it results in a boost in business growth and efficiency for customers, driving the digital and intelligent upgrade of smart logistics.”

Mark Yahiro, vice president at Intel (www.intel.com), added: “Highly accurate and consistent depth vision data are critical for AMRs to achieve environmental perception, significantly influencing performance in positioning, navigation and obstacle avoidance. Through collaboration with Geek+, we are driving AMR innovations based on depth vision data, enabling logistics robots to deliver highly stable and accurate transport services in complex environments, thereby empowering agile, digital and intelligent supply chains.”