The AMR Visual SLAM Solution is a “Solution Ready Platform (SRP)” using the well-validated ADLINK’s RQP-T37 controller and Kudan Visual SLAM (KdVisual), which is compatible with ROS and ROS2. This ensures prompt integration of KdVisual into the customer’s overall architecture with boosted performance, especially in challenging environments of AMR applications such as dynamic objects, scenery changes, and indoor/outdoor mixed applications. This is a perfect platform for the development of industrial use robotic applications such as autonomous mobile robots (AMR) and autonomous mobile industrial robots (AMIR).

The most distinctive benefit of this offering is the ease of integrating Visual SLAM into the AMR system and high-performing AMR navigation. ADLINK offers its Neuron SDK together with ROSCube, which contains various software modules required in AMR development and Kudan Visual SLAM package also offers several supporting software to enable seamless integration, especially for those who use 2D-Lidar SLAM for their localization approach.

3D Visual SLAM is quite different from 2D-Lidar SLAM in terms of mechanism and characteristics. Therefore, many companies cannot see its proper performance before they give up using it. Kudan has very extensive knowledge on how to deploy visual SLAM properly through numerous projects. This Solution Ready Platform includes not only Kudan’s Visual SLAM software but also other supporting documents and modules to accelerate integration and prototyping. We have some examples of developing an initial prototype of AMRs with our visual SLAM package in 2 weeks.

Another challenge robotics OEMs face when they try to adapt visual SLAM is that it’s quite challenging to have reliable performance by building from scratch or based on open-source software. The following points are some of Kudan Visual SLAM’s distinctive advantages, which result in a productivity increase of robots, and application expansion.

• 5x – 10x faster process speed
• 25% – 50% memory usage
• Average <1cm repeatability/ repeatable accuracy
• Better absolute accuracy than 2D-Lidar SLAM
• Robust against 95% scenery changes

Please visit the special web page for this AMR Visual SLAM Solution on our website:
https://www.adlinktech.com/en/kudan-amr-visual-slam

About ADLINK Technology Inc.
ADLINK Technology Inc. (TAIEX:6166) leads edge computing, the catalyst for a world powered by artificial intelligence. ADLINK manufactures edge hardware and develops edge software for embedded, distributed, and intelligent computing – from powering medical PCs in the intensive care unit to building the world’s first high-speed autonomous racecar – more than 1600 customers around the world trust ADLINK for mission-critical success. ADLINK holds top-tier edge partnerships with Intel, NVIDIA, AWS, and SAS, and also participates on the Intel Board of Advisors, ROS 2 Technical Steering Committee, and Autoware Foundation Board. ADLINK contributes to open source, robotics, autonomous, IoT, and 5G standards initiatives within 24+ consortiums. For over 25 years, with 1800+ ADLINKers and 200+ partners, ADLINK enables the technologies of today and tomorrow. Follow ADLINK Technology on LinkedIn, Twitter, Facebook or visit adlinktech.com.

About Kudan Inc.
Kudan is a deep tech research and development company specializing in algorithms for artificial perception (AP). As a complement to artificial intelligence (AI), AP functions allow machines to develop autonomy. Currently, Kudan is using its high-level technical innovation to explore business areas based on its own milestone models established for deep tech which provide wide-ranging impact on several major industrial fields.
For more information, please refer to Kudan’s website at https://www.kudan.io/.

■Company Details
Name: Kudan Inc.
Securities Code: 4425 (TSE Growth)
Representative: CEO Daiu Ko

■For more details, please contact us from here.

The post Kudan and ADLINK launched AMR Visual SLAM Solution combining ROSCube and Kudan SLAM for robotics OEMs first appeared on Kudan global.

KdVisual demonstrates robust and stable tracking/localization on the map throughout the demo video below. Realsense D455 was mounted at the front of the autonomous guided vehicle (AGV) as shown in the image. The data was recorded during operating hours of a factory in Asia thanks to ROSTEK Vietnam. We ran KdVisual on the recorded images and depth data at real-time speed.

Here is the demo video:

Challenges KdVisual can solve for AGVs and AMRs

KdVisual is designed to overcome some of the typical challenges other visual SLAM and positioning approaches may struggle with, while managing to run with a low-power computing platform.

1. Moving objects and workers in front of the robot: SLAM system calculates the robot’s pose and movement based on how objects in the camera’s field of view (FoV) move. When there are moving objects or people occupying a portion of the FoV, these movements can confuse SLAM systems and result in deteriorated accuracy. As you can see, there are many carts and people moving and passing by, and in close proximity to the camera in the demo, it could have easily made the robot trajectory inaccurate but KdVisual can handle this with ease.
2. Scenery changes: When there are some changes in the environment from the time when the map was created, this can usually result in loss in position tracking or inaccurate positioning. However, KdVisual can manage these types of dynamic environments with its unique approach in how it has implemented SLAM, based on years of real-world experience, and focus on accuracy and robustness. As you can see in the video, there are mobile storage carts, and temporary shelves throughout the facility, which can create challenges for SLAM in general.

Repeatable/relative accuracy

Repeatability and repeated accuracy are important factors within factory and warehouse environments. With our own testing, as well as, tests by customers on customer sites, KdVisual consistently achieves positional error rates under 1cm. This enables AGVs and AMRs to stop at designated loading and unloading points accurately to perform pickup/dropoff operations, as well as, charge themselves at a charging station.

There are more features and facts we want to show off, but let’s save them for future posts!

About Kudan Inc.
Kudan (Tokyo Stock Exchange securities code: 4425) is a deep tech research and development company specializing in algorithms for artificial perception (AP). As a complement to artificial intelligence (AI), AP functions allow machines to develop autonomy. Currently, Kudan is using its high-level technical innovation to explore business areas based on its own milestone models established for deep tech which provide wide-ranging impact on several major industrial fields.
For more information, please refer to Kudan’s website at https://www.kudan.io/.

■Company Details
Name: Kudan Inc.
Securities Code: 4425
Representative: CEO Daiu Ko

■For more details, please contact us from here.

The post Kudan Visual SLAM (KdVisual) in action: In an operating factory for autonomous mobile robots first appeared on Kudan global.