Sense
Match modality to trace, with live sensor footprints and optional overlays.
The SLO programme
SLO ROBO Simulator
Wildlife Forensic Mission
Training for system-level operators who govern intelligent machines rather than drive them — learning shared autonomy by running it, in a scene where every decision has evidential consequences.
01The programme
Operating the partnership, not the platform.
Human-machine interaction has moved from discrete manual teleoperation toward multi-agent shared autonomy. The System-Level Operator presides over that architecture as a cognitive arbiter: setting intent, judging machine confidence against physical reality, and owning the decisions that carry legal and ethical weight.
Authority in these systems is not held or handed over wholesale. It is distributed along a continuum of joint action, and the operating point moves constantly with task complexity, algorithmic confidence, operator load and environmental uncertainty. Reading that continuum — and moving deliberately along it — is the core competence this programme develops.
Direct manual controlShared assistanceDynamic arbitrationSupervisory autonomy
02The simulator
Learning through simulation.
A continuous 3D wildlife crime scene where a mixed fleet operates under your direction. You choose the platforms, the sensing modality and where authority sits, then live with the result: a trace detected in time, reached without contamination and preserved through custody — or lost.
Arbitrate
Shift authority as confidence and workload change, one platform or the full fleet.
Preserve
Approach cleanly and hold the chain of custody through to the debrief.
03Learning objectives
What a system-level operator is trained to do.
Competence here is judged by the quality of governance, not the smoothness of the driving.
Operate at system level
Govern mission intent and arbitration rather than kinematics, and recognise when a task must be pulled back down to direct execution.
Read the spectrum continuously
Judge task complexity, environmental uncertainty, cognitive load and algorithmic confidence, and move the operating point before conditions force the move.
Calibrate trust to evidence
Interpret confidence and uncertainty signals critically, and resist both automation bias and needless override.
Preserve agency and integrity
Keep the operator's authorship legible, and keep every recovered trace defensible from detection through chain of custody.
04Background
Read the theory behind the mission.
The Learn section carries the conceptual programme: the operator's role and abstraction hierarchy, the Spectrum of Shared Control, trust calibration and explainability, and a glossary of every term in use.
- 01The System-Level OperatorThe role, the abstraction hierarchy it governs, and why observability and transparency decide whether the partnership holds.9 min
- 02The Spectrum of Shared ControlThe Human-AI Partnership Model as a continuum of joint action, and the human factors that make a position on it sustainable.12 min
- 03Trust, explanation and failureAutomation bias, anchoring, machine uncertainty, and the safeguards that keep an interpretable interface from becoming a persuasive one.11 min
- 04GlossaryEvery term used across the programme, the simulator interface and the mission debrief.4 min
Open access to the essentials. Register for the depth.
The overview, the introductory theory and a trial mission are open to everyone. A free account opens the full analysis in each Learn part, every scenario in the simulator, the paced modules and your saved mission record.
- Full theory: arbitration formalism, agency safeguards, XAI practice
- Every scenario and the full platform fleet
- Saved reflections and a persistent mission record