Civilisation spent a hundred years building itself around fossil fuel.
Autonomy is how we start building it for something else.
The infrastructure of the modern world, its roads, its supply chains, its industrial operations, was engineered around a driver and an engine. Autonomous systems are the first technology that could change the base assumption. Not a more efficient vehicle, but a different relationship between humanity and the machines that move it.
We bound the world the machine operates in.
Not waiting for Level 5. We start where autonomy already works and pays: yards, ports, farms, fixed routes. Prove it inside a boundary, then widen it. Each domain solved is a piece of infrastructure redesigned for what comes after fossil fuel.
We build on Autoware, auditable and inspectable.
Not a sealed black box. When a regulator, an insurer, or an operator asks how a decision was made, "the model decided" is not an answer. Every layer of our stack can be opened, examined, and replaced.
Teleoperation is a designed layer, not a failure mode.
The machine hands over cleanly at the edge of its domain. A person steps in, the situation is studied, the domain widens. Autonomy earns its place incrementally, and a human is always one step away.
We put Malaysia's first AV on open roads in 2016.
Before most of the region had a serious programme. That head start is not a history lesson, it's the shape of the real problem understood from the inside, on our own roads, in our own conditions.
Widen the domain. Watch the difficulty explode.
Every step from a fenced yard toward "anywhere, any weather, any time" multiplies the rare edge cases a system must handle safely. Drag the slider, the curve is roughly what the long tail does to cost and risk.
// Illustrative. The point isn't the exact numbers, it's the shape: difficulty is not linear in ambition.
The full autonomy stack.
A layered stack, from the sensors bolted to the vehicle up to the operations that watch over a fleet. Each layer is a module we can deploy, tune, or replace independently, so you adopt only what your use case needs.
We build on open standards rather than a black box, which means no vendor lock-in, full auditability for safety cases, and a stack your own engineers can inspect.
Sense, decide, act, every cycle.
The driving loop runs continuously on the vehicle. Each stage feeds the next, then the world is sensed again, dozens of times a second.
Synchronised LiDAR, radar, camera, GNSS/IMU streams, time-stamped on ROS 2.
Objects, lanes and free space from fused sensors.
cm-level pose on the HD map via NDT + GNSS-INS.
Where every nearby agent is likely to go next.
A safe, comfortable trajectory through the scene.
Steering, throttle, brake via drive-by-wire.
Loop repeats continuously; planning ~10 Hz, control ~50–100 Hz depending on platform and ODD.
What we deliver.
From a single autonomy module to a whole vehicle program, plus the systems that operate a fleet.
Perception & fusion
3D object detection, tracking, semantic segmentation and free-space estimation from fused LiDAR, radar and camera.
Localisation & mapping
HD map building, NDT/SLAM localisation and GNSS-INS, holding cm-level pose in tunnels, yards and GPS-poor sites.
Planning & control
Behaviour and motion planning with MPC/PID control, tuned for the region's roads, weather and traffic.
Teleoperation
Low-latency remote monitoring and takeover for the moments a human should step in.
Fleet & operations
Dispatch, health monitoring, OTA updates and ODD enforcement across a fleet.
Simulation & validation
Scenario-based testing across thousands of cases before a wheel turns, then on-road validation.
Where we are. Where we're headed.
This work lives in REKA's Kinetik division: automation, robotics, and human-machine interfaces. Honest timeline assessment matters more than optimism.
Autonomous machines in warehouses, yards, farms and fixed routes, paying for themselves today. Single sites. Single domains. Already running.
Multiple machines running as one operation over secure networks, with teleoperation covering edge cases. The proven domain, now at fleet scale.
As hardware, maps and regulation mature, the proven boundary expands. The organisations inside it first move first. We are getting clients ready.
Autonomy is only trustworthy if it knows where it stops.
The machine operates fully inside its domain. At the boundary, it hands over cleanly. Outside it, it stops and escalates. The domain then widens.
// The boundary is a designed feature. It is what makes the safety case provable.
Specifications at a glance.
// Exact sensor suite, compute and ODD are scoped per platform and use case.
Open standards, real deployments.
As a member of the Autoware Foundation, we tune the open self-driving stack for the region's roads, weather and traffic, and feed improvements back upstream. The same stack powers yard and industrial automation, remote-operated machines, and ADAS components, autonomy applied within a defined ODD, where it pays off fastest.
// Autonomous systems, tested in the physical world
Not a roadmap. A record.
The proof is in the dates. REKA has been building autonomous technology in Malaysia and the region since 2016, before most programmes here existed.
// Full record: reka.re/lab/autonomous-driving/work
Put autonomy to work.
Shuttles, yards, remote operations, or research. Tell us the use case and ODD.