The new real-time robot guidance system enables flexible and low-cost bin picking for unstructured environments, achieving 95% success rates and sub-1-second pick cycles in live automotive production.

DETROIT: Inbolt, a leader in real-time vision-guidance systems for robots, today announced the launch of its next-generation bin picking solution designed to bring human-like adaptability to industrial robotics. Built for fully unstructured environments, this breakthrough enables robots to identify, grasp, and place parts with unmatched flexibility and accuracy, even when objects are randomly positioned or partially hidden.

A new standard for industrial bin picking

Traditional bin picking systems rely on fixed overhead high-end and long-range 3D cameras, complex calibration, and pre-calculated grasp points. These systems are expensive, rigid, and easily disrupted when bins move, parts aren’t detected, or pre-defined pick points aren’t accessible. Inbolt’s approach turns this model on its head.

Using a 3D camera mounted directly on the robot arm, powered by Inbolt’s proprietary AI, the robot continuously perceives, understands, and adapts in real time. The AI delivers an infinite number of grasp strategies, removing the need for a perfect grasp. This provides 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.

How the solution operates

Inbolt’s bin picking solution uses a process inspired by human behavior:

• Pick like a human - The robot identifies any pickable side, just like a human.
• See in hand - Once the object is gripped, the robot analyzes and locates it.
• Adjust to place - During motion, the AI continuously refines the robot’s trajectory for accurate placement, a capability known as in-hand localization.

This closed-loop process allows the robot to adapt instantly to part variability and bin movement, achieving a level of robustness never before seen in traditional bin picking systems.

Flexible, fast, and cost-effective

Inbolt’s on-arm camera architecture eliminates the need for multiple fixed cameras and expensive high-resolution setups. Manufacturers can deploy the same robot across different bins and configurations, significantly lowering hardware costs and setup time.

This flexibility and robustness are what make Inbolt’s solution unique in the market. “Traditional bin picking systems are too rigid for real factory conditions,” said Albane Dersy, COO of Inbolt. “We designed our solution to adapt in real time, able to see, grasp, and adjust the way a human would. That level of flexibility is what manufacturers need to reach truly autonomous production.”

Key benefits include:

• Flexibility: Works with bins of any size or position, even if they move during operation.
• Speed: Average processing time per pick under 1 second.
• Reliability: Up to 95% successful pick rates in production environments.
• Affordability: One camera per robot, not per bin, and no need for complex overhead installations.
• Scalability: Fast integration across multiple stations or factories.

Production-proven across plants

Inbolt’s unstructured bin picking solution is already running across more than 5 different factories. Across these sites, Inbolt’s technology has consistently delivered high uptime and throughput, proving its robustness in real-world industrial conditions.

Powered by AI and real-time 3D vision

The system runs on NVIDIA’s hardware platform and leverages Inbolt’s proprietary AI robot guidance models, which enable real-time pose estimation and continuous trajectory correction. This unique architecture minimizes computational load while maximizing robustness, ensuring consistent performance across different use cases and part geometries. Watch the Inbolt bin picking announcement video here.

Availability

Manufacturers looking to modernize their bin picking stations can request a live demo or pilot deployment at www.inbolt.com/contact

Inbolt gives robots the ability to see, think, and adapt in real time. Its generalist AI model enables any robot to master any process, part, or station, helping manufacturers deploy faster, cut costs, and keep production moving. Trusted by Stellantis, Toyota, Beko, and Volkswagen, Inbolt combines real-time 3D vision and proprietary models to deliver precise part localization and robot trajectory control, even in unstructured environments. Trained on CAD models in minutes and compatible with FANUC, ABB, KUKA, Yaskawa, and Universal Robots, Inbolt powers over 70 factories worldwide with flexible, scalable automation.

For more information, visit https://www.inbolt.com/

Fonte: Business Wire