Mobile Robots Get More Autonomous with Visual SLAM

The new T702 from ABB is a tug-style autonomous mobile robot (AMR) that uses Visual SLAM (simultaneous localization and mapping) navigation to create a 360-degree point cloud of data to navigate in changing environments. 

ABB explains that Visual SLAM is a navigation technology that combines artificial intelligence and 3D vision using off-the-shelf cameras. It allows AMRs to make intelligent decisions based on their surroundings and provides higher accuracy—even in challenging environments. Used with ABB’s new AMR Studio software, users can achieve faster commissioning and ensure superior performance in dynamic and unstructured installations, the company says.

Joshua Alphonse, head of U.S. mobile robotics at ABB said, “With traditional SLAM, which uses lasers to navigate and map the environment, the robot’s internal map of the factory is disrupted if you change the environment, causing the AMRs to get lost. With this Visual SLAM technology, you can change the environment [without affecting the AMR’s performance]. So, for manufacturers looking to dynamically change their processes, which can result in a lot of changes within their facility, Visual SLAM makes the T702 very robust and flexible because it's literally looking at features on the ceiling, it's looking at the [support] posts and it’s looking at the floor. So, there's a lot more data points [it’s considering] rather than just looking at hard objects right out in front of it.”

See Joshua Alphonse in the video below captured at Automate 2024 explaining the T702 and Visual SLAM technology.