One agent. Independent adapters for navigation models and execution backends.
Engineering interface overview: one unchanged Agent connects to independent navigation model and execution backend adapters. LightNav, Go2 and the MuJoCo simulation are built-in implementations. Dashed Custom slots indicate extension points, not connected or validated implementations. The LightNav neural-network symbol represents a learned navigation model, not its actual topology. Lines are structural relationships, not execution order.
Navigation Models
LightNav
Custom +
Agent
Execution Backends
Quadruped
MuJoCo · Sim
Custom +
Runtime workflow overview
Harness supports continuous navigation, timely adjustment and completion checks through in-task memory, monitoring and scheduling.
Harness groups Agent decisions with in-task Memory and skill execution with Monitor. Scheduling coordinates both and receives execution events. Scheduling invokes Agent decisions when needed and allows continuous execution through a shared two-way channel with the execution group. The diagram shows six main connections: goal input, action execution, event feedback and permission to continue, on-demand Agent intervention, completion checking after a stop or completion proposal, and a return for adjustment when the result is not confirmed. Confirmed checks complete the task. Grouping represents local evidence exchange and parallel monitoring without drawing every internal interaction.
Goal & observations
Scheduling
Agent decision
Memory
Skill execution
Monitor
Completion check
Confirmed · complete
Events
On demand
Continue
Stop / finish
Not confirmed
From route execution to autonomous search
Memory
Observations, routes and action history, recalled within a task.
Monitor
A monitor watches for target cues during navigation and triggers a pause for the agent to review.
Scheduling
VLN keeps moving; the agent replans when progress stalls.
From a goal to exploration
Often, we know what we want to find, but not where it is. Nova-HEI lets robots take on that search. Describe your goal in everyday language, and the robot explores its surroundings without needing you to specify a location or guide it at every turn.
The target may be in another room or around a corner, out of sight. The robot keeps your request in mind as it searches, follows clues it discovers along the way, and approaches possible matches to check whether they meet your requirements. You give it a complete search task, without having to issue a new instruction for each move.