Edge AI · On-device inspection
On-Device Edge Vision Defect Detection on ESP32-S3
A production conveyor inspection camera running a quantized INT8 CNN entirely on an ESP32-S3 — 18 FPS at 0.4 W, no cloud, 6× lower capex per station.
Hardware fails most often at the seams between electronics and mechanics. We design embedded systems and electronics packaging where controllers, power stages, sensor buses, and physical enclosures align on the first revision.

What we do
YantriX provides end-to-end embedded hardware planning and integration for robotics, IoT devices, and industrial machinery. We architect the electronic subsystems — selecting optimal microcontrollers (ESP32-S3, STM32, RP2040) and edge AI compute (NVIDIA Jetson Orin), designing power distribution architectures (DC-DC regulators, battery management, power sequencing), integrating motor drivers (stepper, BLDC, servo), and establishing robust communication buses (CAN bus, RS-485, I2C, SPI, UART). Through tight 3D ECAD-MCAD workflows, we synchronize PCB layouts directly into SolidWorks CAD assemblies to verify connector clearances, component height envelopes, thermal dissipation paths, and fastener placements before fabrication.
Share your technical requirements, 3D CAD files, or operating specs. NDA support is available where required before confidential file exchange.
We adapt the same engineering service to different product contexts depending on the load case, packaging problem, validation target, or deployment environment.
Tailored engineering, mechanical design, and rapid prototyping solutions designed specifically for autonomous mobile robots (amrs) & agvs applications.
Tailored engineering, mechanical design, and rapid prototyping solutions designed specifically for robotic arms & mechatronic actuators applications.
Tailored engineering, mechanical design, and rapid prototyping solutions designed specifically for industrial iot gateways & sealed enclosures applications.
Tailored engineering, mechanical design, and rapid prototyping solutions designed specifically for smart agricultural & environmental monitoring devices applications.
Tailored engineering, mechanical design, and rapid prototyping solutions designed specifically for automated test jigs & production fixtures applications.
See how this engineering capability applies across real project scopes, analysis goals, and physical prototype iterations.
Edge AI · On-device inspection
A production conveyor inspection camera running a quantized INT8 CNN entirely on an ESP32-S3 — 18 FPS at 0.4 W, no cloud, 6× lower capex per station.
Robotics · Autonomous Mobile Robot (AMR)
End-to-end development of an 80 kg payload industrial AMR — custom skid-steer chassis, Nav2 autonomous navigation, LiDAR SLAM, and ESP32 motor controller integration in 16 weeks.
CAD Design · Mechanical & DFM
Complete CAD design and DFM optimization for a multi-part outdoor IoT enclosure in polycarbonate — 1.5° uniform draft, overmolded silicone gasket, and moldflow sink-mark elimination.
Thermal engineering
How CFD-based conjugate heat transfer caught a 14 °C hotspot in a sealed IP66 enclosure before prototype — saved an estimated 2 mold revisions and 7 weeks of rework.
Explore practical engineering guides related to design, manufacturing, simulation, and product development.
Edge AI
The production playbook for deploying YOLOv8 / v11 on Jetson Nano / Orin in Indian factories — quantization, TensorRT, OTA updates, monitoring, and the gotchas you only learn from shipping.
Simulation
How CFD thermal analysis with Conjugate Heat Transfer (CHT) catches hotspots, optimizes heatsink fins, and balances IP67 sealing with heat dissipation in electronics enclosures.
Applied AI
A practical 2026 guide to sourcing AI and ML services in India — what's available, realistic project costs, when to outsource vs hire, and how to evaluate Indian AI vendors.
Common questions teams ask before starting a project.
We use a bidirectional 3D ECAD-MCAD workflow. The board outline, mounting hole locations, keep-out zones, and critical connector positions are established in SolidWorks and exported to the PCB layout environment. Once routed, the populated 3D PCB assembly (STEP/IDF) is re-imported into our master CAD assembly to verify clearance against ribs, walls, and thermal pads.
We regularly architect solutions around ESP32-S3 (Wi-Fi/Bluetooth IoT & edge sensing), STM32 series (hard real-time motor control and safety loops), Raspberry Pi / RP2040 (rapid interface prototyping), and NVIDIA Jetson Orin Nano / NX (on-device AI, computer vision, and ROS 2 robotic perception).
Yes. We size and specify motor controllers (BLDC ESCs, FOC drivers, stepper drivers), magnetic/optical encoders (AS5600, AMT102), IMUs (BNO055, MPU6050), and DC-DC power converters based on peak load current, voltage drop, and thermal operating limits.
For sealed IP65/IP67 enclosures, we design conduction cooling paths that transfer heat from hot components (MOSFETs, voltage regulators, processors) directly to aluminum chassis walls or exterior heatsink fins using silicone thermal pads and gap fillers, backed by CFD thermal analysis.
We begin with functional requirements and power budgeting, select core silicon and connectors, validate critical circuits on breadboard/dev kits, perform 3D mechanical packaging integration, fabricate prototype boards, 3D print custom test enclosures in-house, and perform live firmware bring-up on our test bench.
Share your engineering goals, current design stage, and timeline. Our engineers will review requirements and follow up with a clear project scope.