Feature
The combination of AI and robotics is enabling companies to take automation to the next level. Companies are using AI and robotics to quickly and accurately fulfill product orders, conduct warehouse operations more efficiently and prepare to look for signs of life on other planets. Here, we look at some examples of companies applying AI in robotics applications.
1. Zenni Optical
The process of manually fulfilling orders was stifling the workflow for Zenni Optical, an online retailer of prescription glasses. For years, workers manually placed each pair of glasses into clamshell cases and then inserted the cases into a tabletop mechanical bagging machine, which spit them out in a labeled poly bag for shipping. The solution was proving to be too slow and error-prone, according to a case study.
To meet customer demand for quickly fulfilled and correctly shipped orders, the company used an AI-based robotic solution.
Zenni Optical implemented an OSARO robotic picking solution with AI-enhanced computer vision, machine learning (ML) and a custom end-effector to do the actual picking. The robotic picking solution was integrated with existing warehouse management systems, bagging equipment and sensors.
"The integration of AI-powered picking transformed our workflow,” says Simon Goh, director of distribution and facilities, Zenni Optical. “We've reduced errors significantly, enhanced productivity and created a better work environment for our team."
Results
- Decreased mixed-up order (MUO) rate from 20 per 100,000 to 2.5 per 100,000, achieving nearly 99.9% accuracy
- Increased orders processed per hour 50% compared to the manual process
- Reduced order fulfillment steps from five to two
- Automated repetitive tasks, freeing workers for more engaging, technical responsibilities and skill development
2. Farsound Aviation
Farsound Aviation, a supply chain and logistics solutions provider and distributor in the aerospace industry, delivers parts from hundreds of suppliers directly to the production line. Farsound Aviation was facing a variety of challenges, including quality assurance, labor shortages, supply chain disruptions and the need to optimize its warehouse operations, according to a case study.
The warehouse automation company Autrix installed 10 Hikrobot AI-powered autonomous mobile robots (AMRs) that can move up to 2 meters a second with up to a 1,000 kg payload, alongside 650 bespoke racks and 32,000 bins to accommodate the extra capacity created by automation and eight pick-to-light workstations, complete with bespoke software to help automate repetitive tasks.
A combination of AI and ML enables the robots to decide how to navigate through the warehouse aisles, drastically increasing pick rates and precision, while improving safety and eliminating the capacity for human error almost entirely. This means that instead of pickers walking miles around a warehouse each day, the robots take the parts to them.
“AI-driven AMRs have eliminated the inefficiencies that you see in most warehouses,” says James Hooper, head of U.K. operations, Farsound Aviation. “The walking to the rack, the counting and then bringing the goods back to the workstation — this is all handled by robotics.”
Results
- Decreased picking times by 78%
- Consolidated orders 127% more efficiently
- Improved traceability of parts
3. Evergreen
Evergreen, with a location in Clyde, Ohio, is among the nation’s largest recyclers of polyethylene terephthalate (PET) and producers of recycled PET (rPET). The company supplies food and non-food grade rPET pellets and flakes to many top global brands, helping customers increase recycled content in their plastic packaging. Until recently, Evergreen relied on manual sorting, according to a case study.
Although staff could pick as many as 40 bottles per hour, that pace was difficult for humans to maintain for an entire shift.
Evergreen turned to AMP, which provided a team of pick-and-place robotic arms with an AI interface trained for object recognition. The AI can rapidly and accurately distinguish plastic bottles based on the material they are made of.
“The net result is we’re getting more PET bottle picks — about twice as many — from the material stream,” says Mark Passarell, plant superintendent, Evergreen. “We want to recover all we can, and with AMP’s technology, we are.”
Results
- Increased pick rate to 120 bottles picked per minute
- Achieved consistent pick rate throughout day
- Improved material quality and consistency in bottle-to-bottle recycling process
4. Dr. Max
Dr. Max, a pharmacy chain in Europe with 3,000 pharmacies across six countries, wanted to maximize the efficiency of its order picking and stock replenishment. Staff spent a large amount of time walking around the warehouse to retrieve items from storage. Manual picking was also prone to errors, which hurt customer satisfaction, increased costs and complicated inventory and batch tracking, according to a case study.
Dr. Max installed Brightpick Autopicker autonomous mobile robots (AMRs) that use 3D machine vision and AI to identify and pick products with a high level of accuracy. The AMRs navigate narrow warehouse aisles using their vision and do not need QR codes or magnetic tape on the floor, which reduces maintenance costs. Their advanced navigation capability also means the robots don’t require safety fencing.
“The scalability ensures that as we expand our SKU range, we can seamlessly integrate more robots,” says Tomáš Seget, deputy director of logistics, Dr. Max.
Results
- AMRs picked at a 99.99% accuracy rate
- Re-allocated all human pickers to other work, such as quality control
- Increased throughput 60% from the same footprint, from 5,000 to 8,000 picks per day
5. NASA
One of the important elements of NASA's search for signs of life on other plants is the ability to search in caves, according to a case study.
To be ready for such extraterrestrial searches, NASA Jet Propulsion Laboratory’s autonomy and AI system, NeBula, worked in tandem with a team of Boston Dynamics robots to autonomously explore hundreds of meters of Martian-like caves on Earth, with no prior information about the map or features of the environment.
When integrating the space agency's autonomy and AI on a physical robot, it’s critical that the robot supports the requirements of stability over difficult terrain, while being capable of carrying enough scientific instruments with the necessary endurance and speed. Boston Dynamics’ Spot robot can satisfies these requirements simultaneously.
Webinar
Sep
25
CMS Briefing: A Live Look at What’s Next in AI-Driven Platforms
Learn how leading organizations are using AI‑driven tools to publish faster, personalize smarter and stay secure.
Register
Webinar
Oct
16
Agentic AI Playbook: Real-World Customer Service Use Cases You Can Deploy Now
Boost self-service by 30% and slash call volume by 63% with agentic AI.
Register
Webinar
On demand
Ready or Not: How Data-First Organizations Are Unlocking Agentforce Potential
Learn how to cut through the noise, activate Agentforce and build a Salesforce AI strategy that actually delivers.
Watch Now
Webinar
On demand
AI in Customer Service: Faster Resolutions, Happier Customers
Don’t let rising demand burn out your team. See how to build a smarter, more resilient support org.
Watch Now
Webinar
On demand
From Hype to High-Impact CX Strategies That Actually Scale
Turn buzzworthy AI and outsourcing trends into measurable CX wins with fresh 2025 data.
Watch Now
Webinar
On demand
Insights to Action Rethinking the Contact Center for Real Business Impact
Join our exclusive webinar to hear CX executives share their innovative strategies for transforming service delivery.
Watch Now
“What’s so exciting about Spot is how flexible it is and how maneuverable it is,” says Jennifer Blank, lead scientist of Braille Project, NASA Ames. “I can envision scenarios where different Spots have their own assigned roles and their own assigned specialties.”
Results
- Robot explored autonomously
- Robot relayed “interesting” images to scientists at base station
- Subsequent robots can further explore “interesting” elements
