Engineering
Custom robotics software and integration, scoped as defined work packages with documented interfaces and test evidence.
Services
We take on engineering work where the result has to run on a physical robot and be maintained after we hand it over.
- Custom robotics software
- Perception, planning, control and task logic written for a specific robot and task, structured so that your team can read, test and extend it.
- ROS 2 integration and middleware
- ROS 2 packages, message and interface design, launch and parameter management, and bridges to existing systems where a project needs them.
- Hardware SDK and API integration
- Wrapping manufacturer SDKs and APIs behind stable interfaces, so that task software does not depend on the details of a single platform.
- Sensor and payload integration
- Driver integration, calibration, time synchronisation and coordinate-frame setup for cameras, depth sensors, LiDAR, inspection payloads and grippers.
- Mission planning and operator applications
- Tools to define routes, inspection points and tasks, and interfaces that let operators monitor progress and take over when needed.
- Teleoperation, telemetry and fleet coordination
- Remote operation with clear latency and safety limits, structured telemetry, and coordination of tasks across more than one robot.
- Edge deployment and infrastructure integration
- Packaging software for onboard computers, managing versions in the field, and connecting robots to the customer’s network, data storage and existing systems.
- Experimental tools and evaluation workflows
- Data recording, labelling and replay tools, scenario definitions and evaluation scripts that make experiments repeatable.
Deliverables
What we hand over is agreed at the start and written into each work package.
Working prototypes
Software running on the agreed platform and demonstrated on the agreed tasks.
Integration software
Drivers, interfaces and packages delivered as maintained source code with build instructions.
Documented interfaces
Interface descriptions covering messages, services, parameters and coordinate frames.
Experimental datasets
Recorded sensor and system data with the conditions under which it was collected.
Test reports
Methods, conditions, results and known limitations, including results that did not meet the target.
Deployment support
Installation, configuration and handover so that your team can operate and maintain the system.
Development and validation
Every project follows the same sequence. Evaluation usually leads back into another round of development, so the sequence is a loop rather than a straight line.
Define the problem
Agree on the task, the operating conditions and what success means, in terms that can be measured.
Establish a baseline
Measure how the task is done today, or how a simple reference method performs, so that improvement can be shown.
Develop and simulate
Build the software and test it in simulation and on recorded data, where failures are cheap.
Integrate hardware
Bring the software onto the physical platform with its sensors, payloads and onboard computing.
Test in representative conditions
Run structured trials in conditions that resemble the intended use, first in the laboratory and then on site where agreed.
Evaluate and refine
Compare results with the baseline, document what did and did not work, and decide what to change next.
Evaluation findings return to development until the agreed criteria are met or the limits are understood.
Examples of evaluation criteria
Criteria are agreed with each partner before testing begins. The examples below describe what a project may measure; they are not results we claim.
| Criterion | What it describes |
|---|---|
| Task completion rate | Share of trials in which the task is completed to the agreed standard. |
| Navigation reliability | Distance or time between navigation failures, and the causes of each failure. |
| Intervention frequency | How often an operator has to step in, and how long each intervention takes. |
| Perception accuracy | Error of detection, localisation or mapping against a measured reference. |
| Response latency | Time from a sensor event or command to the robot’s response. |
| Repeatability across test conditions | How much results vary across repeated trials, lighting, surfaces, objects and operators. |
Laboratory evaluation and field deployment
Laboratory evaluation
Controlled, repeatable conditions. Useful for comparing methods, isolating causes and measuring repeatability. Results show what the system can do under known conditions.
Field deployment
Real sites, real variation and real operators. Useful for finding the failures the laboratory did not anticipate. Results show how the system behaves in use, and are reported separately from laboratory results.
Engineering practice
Versioned software
Every test result is linked to the software version, configuration and model files that produced it.
Documented test conditions
Platform, payload, environment, lighting, surfaces and operator are recorded for each trial.
Careful experiment design
Baselines, repeated trials and defined pass criteria are set before testing, not after.
Traceable findings
Reports state methods and limitations, link to the underlying data and include results that missed the target.
Have an engineering task in mind?
Send us a short description of the robot, the task and the constraints, and we will reply with questions or a first outline of scope.