← The Charlot Lab

Research · The Charlot Lab

Space logistics and transportation.

Reaching a destination in space is a velocity budget, and the whole chain, from launch through orbital transfer, rendezvous, capture, servicing, and return, becomes tractable when reusable infrastructure and autonomous in-space transport pay it down. This is the instrument suite: each transport mode running on its real equations, and the autonomy that unites them, so the capabilities can be tested, applied, and deployed toward an open, decentralized space economy.

Technical Report TR-2026-27 · Institute for Physical AI @ JBI

The centerpiece

The autonomy that unites the chain.

One shape repeats across every link: an estimator resolving state, and a controller holding a proven corridor. The clearest case is the hardest, a rendezvous with a body that neither holds still nor helps.

A Kalman filter resolves the tumbling target's pose from noisy returns (the blue covariance shrinks as it converges); the chaser holds the certified corridor, matches the spin, and latches inside the capture envelope. Switch to MPPI to watch a real optimal controller sample hundreds of trajectories and choose its path, or to Learned to fly the approach with a 1,282-parameter policy distilled from that planner and run on-device (released on Hugging Face), or to human-in-loop, where the control lag opens the miss. Illustrative dynamics on a real filter, a real planner, and a real learned policy.

The instrument suite

Twelve instruments, real physics.

Each runs on its governing equations, on the device. Open any one, tune it, and read where the gate is autonomy and control rather than materials.

Δv ARCHITECTURE

Compose the journey

Pick a destination and stack reusable infrastructure and autonomous in-space transport against the velocity budget. The mass-ratio math is the exact rocket equation; a segment a single vehicle could never fly is marked so, and the payload it delivers is read as a real mass fraction.

Open the instrument ↗
ARRIVAL · DESCENT

Precision landing

Arriving at a surface closes the chain. The lander reads the terrain, selects the safest flat site clear of hazards, and flies a closed-form optimal powered descent, ZEM/ZEV guidance, that nulls position and velocity at touchdown under a hard thrust limit. Under-power the engine and it correctly cannot make it soft. Choose where the time-to-go comes from: a flight-time schedule set before ignition, the optimal time-to-go solved from the state every step so the vehicle needs no plan at all, or a released 1,281-parameter net that predicts it on-device in one forward pass.

Open the instrument ↗
AUTONOMY · GNC

On-orbit capture

A chaser estimates a tumbling, non-cooperative target's pose from noisy returns with a Kalman filter, holds a certified approach corridor, matches the spin, and latches. Toggle autonomous against human-in-loop to see why the loop runs on the vehicle.

Open the instrument ↗
PERCEPTION · 6-DOF

Monocular pose

A tumbling, non-cooperative target gives no telemetry. From one camera's noisy keypoints the full six-degree pose is recovered by solving perspective-n-point live, and scored against the truth. This is the SPEED benchmark task, running on the device: rotation error to a degree or two, translation to a few centimetres.

Open the instrument ↗
SERVICING · CONTACT

Servicing & assembly

Past capture, the chain continues: a manipulator inserts a replacement unit into a berthed satellite. Command an exact position and it jams on the rim; command a gentle force and let the chamfer seat it. Compliance, not precision, closes the last millimeter.

Open the instrument ↗
CONSTRUCTION

On-orbit assembly

Structures too large to launch whole are built in orbit. A free-flying assembler plans a valid build order (connected before cantilevered), fetches each module, aligns it to tolerance, and mates the joint, a boom, a solar array, or a ring truss, with no crew.

Open the instrument ↗
IN-SITU RESOURCES

Make propellant on the surface

The tax the whole chain pays is fuel hauled from Earth. An autonomous excavator mines regolith, an electrolysis plant splits out its oxygen, and a tank fills on the surface, throttling itself to the power the sun gives, day and night, so the depot refills without a launch. Lunar or Mars regolith, priced in kWh per kilogram.

Open the instrument ↗
MOBILITY · AUTONAV

Autonomous traverse

Too far for a joystick from Earth, the rover drives itself: it reads the terrain, steers around rocks and steep slopes toward each science target, and drills a sample, hazard-aware navigation planned and executed on the vehicle, target after target.

Open the instrument ↗
MULTI-AGENT · SWARM

Formation flight

No ground controller flies a whole constellation at once. Each satellite holds its slot from its neighbours alone, avoids the others, and, on a new pattern, claims the nearest open slot and transfers without a collision. Distributed coordination with no one in charge: the formation keeps its own shape and reconfigures itself between a ring, a train, an aperture, and a wedge. Toggle the hand-tuned controller against a released 1,474-parameter learned policy flying every agent on-device.

Open the instrument ↗
MOMENTUM TETHER

Skyhook · rotovator

The momentum-exchange tether on real orbital mechanics: catch and release velocities from vis-viva, the payload's true transfer orbit after release, and the tether-to-payload mass from the constant-stress taper equation. Change the material and watch it become buildable.

Open the instrument ↗
EM LAUNCH

Maglev sled

The electromagnetic ground assist: track length grows with the square of exit speed and is capped by the g-load the payload survives. Dial the exit speed and g-limit and read the track length, the peak power, and the coil-switching rate.

Open the instrument ↗
ACTIVE STRUCTURE

Launch loop

An elevated track held up by a fast internal rotor: an unstable equilibrium stabilized span by span. Turn stabilization off, or push the rotor past its control margin, and it buckles. The frame is ordinary steel; the stiffness is the controller.

Open the instrument ↗
The through-line

One stack, every link.

Read across the suite and the same problem recurs: a launch handoff at speed, a momentum-exchange catch, a non-cooperative capture. Each is an estimator and a certified controller running on the vehicle. One autonomy stack, priced in Δv and joules, serves every link in the logistics chain. That is the research this track develops, and the capability the space economy needs to open.

◆ RPO-Bench · the open leaderboard ↗ · a deterministic, reproducible benchmark for capture and pose; run it headless or live and try to beat the baselines.

orbital-logistics on GitHub ↗· capture policy on Hugging Face ↗· formation policy on Hugging Face ↗· landing guidance on Hugging Face ↗· RPO-Bench · open leaderboard ↗ · a headless physics core (MPPI planner, CW/RPO solver, 6-DOF tumble), a distilled on-device capture policy, and a deterministic, reproducible benchmark.

↓ Whitepaper · PDFRead online◆ Living paper

Take the course · PAI-260 →← Back to the labBuild this with us →