Huijuanis our in-house AI simulation engine for autonomous driving, robotics and intelligent hardware development. It covers scene and task orchestration, data generation, quality management and delivery, and it can be adapted to simulation infrastructure a customer already runs.
This page focuses on thesynthetic data generation (SDG) module. The results shown here come from an Unreal Engine 5 implementation, which illustrates the platform's multi-sensor capture, automatic annotation and production-grade data delivery. UE5 is the vehicle for this demonstration, not the only backend the system supports.
Live demo:Huijuan Simulation Platform
What it does
Synthetic data generation walkthrough
Scene construction, sensor configuration, task deployment and result distribution happen inside a single workflow, which is what makes end-to-end data delivery practical rather than a sequence of manual handoffs.
Capabilities
| Area | What you get |
|---|---|
| Sensor coverage | RGB, depth, semantic and instance segmentation, optical flow, edge, thermal infrared, LiDAR and radar, captured in a single pass with consistent timestamps |
| Camera models | Pinhole, fisheye, equirectangular and cube-map projections, so the dataset matches the optics your product actually ships |
| Annotation | 2D and 3D bounding boxes, per-pixel masks and occupancy grids generated as ground truth rather than labelled after the fact |
| Randomisation | Weather, lighting, materials, sensor noise, mounting pose and traffic behaviour, all parameterised and reproducible from a seed |
| Delivery | Versioned datasets with manifest, statistics and quality reports, exported in the schema your training pipeline expects |
Where it fits
Teams use this module when field capture is slow, expensive or impossible to control: rare weather, unsafe manoeuvres, sensor configurations that do not exist yet, or edge cases the fleet has only seen a handful of times. Because every scene is described by parameters, the same condition can be regenerated at any scale once an algorithm weakness is identified.
Deliverables
- A configured scene and sensor rig matching your platform
- A repeatable capture task definition, versioned alongside the data
- The generated dataset with ground truth and quality report
- Integration into your existing training and evaluation pipeline
Talk to us
Tell us your platform type, sensor configuration and the conditions you cannot capture today, and we will scope the data production around them.