An Event-based Fast Movement Detection Algorithm for a Positioning Robot Using POWERLINK Communication
This work demonstrates incremental integration of event-based vision into industrial systems for robotics, addressing fast movement detection in positioning tasks.
The researchers developed a tracking system using an event-based camera and FPGA-based filtering to enable a robot to accurately follow a ball with fast image recognition, leveraging advantages like size, price, and power efficiency.
This work develops a tracking system based on an event-based camera. A bioinspired filtering algorithm to reduce noise and transmitted data while keeping the main features at the scene is implemented in FPGA which also serves as a network node. POWERLINK IEEE 61158 industrial network is used to communicate the FPGA with a controller connected to a self-developed two axis servo-controlled robot. The FPGA includes the network protocol to integrate the event-based camera as any other existing network node. The inverse kinematics for the robot is included in the controller. In addition, another network node is used to control pneumatic valves blowing the ball at different speed and trajectories. To complete the system and provide a comparison, a traditional frame-based camera is also connected to the controller. The imaging data for the tracking system are obtained either from the event-based or frame-based camera. Results show that the robot can accurately follow the ball using fast image recognition, with the intrinsic advantages of the event-based system (size, price, power). This works shows how the development of new equipment and algorithms can be efficiently integrated in an industrial system, merging commercial industrial equipment with the new devices so that new technologies can rapidly enter into the industrial field.