AGVs (Automated Guided Vehicles) using vSLAM

The research addressed by the robotics group covers the emerging topic of AGVs (Automated Guided Vehicles) specifically related to industrial sites. The work performed has been carried out within the frame of the MALTA project (Multiple Autonomous forklifts for Loading and Transportation Applications), a joint research project between industry and university, funded by the European Regional Development and Robotdalen, in partnership with the Swedish Knowledge Foundation. The project objective is to create fully autonomous forklift trucks for paper reel handling. The result is expected to be of general benefit for industries that use forklift trucks in their material handling through higher operating efficiency and better flexibility with reduced risk for accidents and handling damages than if only manual forklift trucks are used.
The system can operate regardless of the odometry information from the vehicle since visual odometry is used. As a result, the final system is compact and easy to install and configure.

Malta industrial set-up

Small scale 6D vSLAM

A 6D pose estimation of the stereo camera rig with respect to a generic 3D landmarks configuration is performed holding the camera by hand and moving it freely in all 6 DoFs in front of a test pattern. The pattern is a five LED deformable “non plane” structure that allows us to test the vSLAM without the aid of any homographic information.
Small Scale 6D vSLAM

Small scale 3D vSLAM

Small scale visual SLAM

Large scale 3D vSLAM

Large scale visual SLAM

More to come soon !!

Comments are closed.