Meet Techie: on-demand autonomous delivery robot built with reComputer J2012 powered by NVIDIA Jetson Xavier NX 

Many businesses have started to rectify their last-mile delivery operations. Their current operational process is to hire third-party courier companies, and it is very inefficient as it requires an astonishing amount of effort and time, for example, a delivery driver can take up to 5 minutes to deliver 1 small package. 

Furthermore, as e-commerce continues to thrive, it will cause an upsurge in parcel deliveries and other issues, especially in densely populated cities. Examples are congested roads due to the rise in courier fleets, items damaged during deliveries, and stolen parcels. 

Meet Techie, your neighborhood-friendly delivery robot

Techie is a smart navigation delivery robot built by Azimorph, seeking to eliminate the need for door-to-door deliveries. The robot would navigate its way toward the consumer’s house according to the time selected by the consumer beforehand. Upon Techie’s arrival, the consumer would then scan a QR code to authenticate and retrieve the parcel. Afterwhich, Techie will return to the centralized bay to charge or load up more parcels. Techie comes with a safety feature that stops it when danger or unforeseen circumstances are detected, for example, a human in its path, construction zones, or roadblocks. With Azimorph’s Techie, there is no need to worry about your parcel!

Hardware Architecture

A reComputer J2012 is used in Techie as it is compact enough to fit in. It functions as a mini computer with a CPU and GPU that is able to process image feed from a real sense camera and USB camera array. A Teensy board is also used as a low-level controller to receive input from GPS and IMU and output controls the motors.

The reComputer J2012 is a hand-size edge AI box built with Jetson Xavier NX 16GB module, rich set of IOs, aluminum case, cooling fan, and pre-installed JetPack System, ready for your next AI application development and deployment. More details can be found on Seeed’s online store!

Navigation system

• Drivable area detection
• Uses a realsense D435i to detect drivable areas through image segmentation and point cloud.

• Outdoor localization
• Utilize the sensor data from IMU, GPS, and odometry to estimate the robot’s position.

• Point-to-Point Navigation
• Based on the data provided by the drivable area detection and outdoor localization, the algorithm will plan a safe route from its current location to its destination for the robot to follow.

• Real-Time Remote Assistance
• A remote operator will take control of the robot if it detects any failures or is unable to continue navigating.

Smart delivery robot accelerates the last-mile delivery to the end consumer.

• Reduces manpower cost (courier)
• Provide flexibility and consistent solution to a growing logistic market
• Capable of navigating in a robust environment in case of unforeseen circumstance
• Reduces cars on the road
• Reduces vehicle pollution

About Azimorph

Founded in 2021, Azimorph is a group of passionate engineers based in Singapore who aim to make robotics’ delivery the new normal. 

Join Seeed as Edge AI Partner, Deliver Real-World AI Together  

Seeed’s Edge AI platform provides devices, carrier boards, peripherals, software tools, and ML solutions. Seeed is NVIDIA’s official reseller and ecosystem hardware partner. By consolidating our best-in-class hardware and cutting-edge technology from our software partners and the community, we aim at helping both developers and enterprises deploy ML in the real world across industries. Contact us at [email protected]

We are looking forward to working with AI experts, software enterprises, and system integrators: 

• Integrating your unique technology, resell or co-brand licensed solution with us. 
• Building next-gen AI product powered by the NVIDIA Jetson module, one-stop bring your product to the market with Seeed’s manufacturing, fulfillment, and distribution.  
• Working with Seeed Amazing Ecosystem Partners together, unlocking more AI possibilities. 

About Author