A bin-picking solution designed to bring “human-like adaptability to industrial robotics” has been developed by Inbolt, a maker of real-time vision-guidance systems for robots.
Designed for fully unstructured environments, this solution reportedly enables robots to accurately identify, grasp and place parts — even when objects are randomly positioned or partially hidden.
Source: Inbolt
The new system replaces expensive, rigid bin-picking setups that rely on fixed 3D cameras and pre-calculated grasp points with a more flexible approach that instead uses a 3D camera mounted directly on the robot arm.
According to its developers, the system is powered by Inbolt’s proprietary artificial intelligence (AI) to perceive, understand and adapt in real time. The AI also delivers an endless number of grasp strategies, thus removing the need for a perfect grasp while providing a faster, cheaper and more flexible solution that achieves less than 1 second per pick and up to 95% success rates in live manufacturing production.
For more on the system, visit the Inbolt website.
