Bringing A Robot Simulator to the SCAMP Vision System
This provides a platform for researchers and developers to prototype vision-based robotic algorithms more efficiently, though it is incremental as it combines existing tools.
The work integrated the SCAMP-5d vision system into the CoppeliaSim robot simulator to create a semi-simulated environment, enabling rapid prototyping of SCAMP algorithms for robotics, as demonstrated with a car localization and tracking task using CNN inference on SCAMP to control robot motion.
This work develops and demonstrates the integration of the SCAMP-5d vision system into the CoppeliaSim robot simulator, creating a semi-simulated environment. By configuring a camera in the simulator and setting up communication with the SCAMP python host through remote API, sensor images from the simulator can be transferred to the SCAMP vision sensor, where on-sensor image processing such as CNN inference can be performed. SCAMP output is then fed back into CoppeliaSim. This proposed platform integration enables rapid prototyping validations of SCAMP algorithms for robotic systems. We demonstrate a car localisation and tracking task using this proposed semi-simulated platform, with a CNN inference on SCAMP to command the motion of a robot. We made this platform available online.