Mindpool Labs is defining its first research program. The roles below contribute to reference missions, models, papers, and evidence gates that will make the work available for scrutiny and reuse.
Research practices
The work develops specifications, models, and papers as one body of evidence. Publishable results will be released under an open license, with university and scenario partners able to challenge assumptions while the reference missionA bounded, published mission scenario used to test one research claim. It fixes the assumptions, initial conditions, limits, metrics and comparison method so that another team can run the same study. is still defined. Hardware work begins after the analytical result is stable enough to make a test useful.
Roles
Spacecraft thermal engineer
You have modeled the thermal behavior of a spacecraft, a rover, or a high-power payload, and you know where the lumped-parameterA model that treats a vehicle as a handful of connected blocks, each held at a single temperature, instead of solving the full temperature field. At a suitable size and fidelity, it can run fast enough for a planning loop, and it remains an approximation. approximations break. You will own the thermal models and their validation against reference cases, and co-author the survey and the lunar nightAbout fourteen Earth days of unbroken darkness at most lunar sites, with surface temperatures near minus 170 degrees Celsius. Surviving it means storing enough energy and enough heat to last without sunlight. paper.
Autonomy and planning researcher
You have built plannersThe software that decides what a robot or spacecraft does next, and in what order. It is separate from the control loop, which carries out each action once it has been chosen. or controllers that run under real constraints, ideally with mixed-integerAn optimization problem in which some of the decisions are whole numbers or on/off switches rather than continuous quantities. Choosing which heater runs in which time slot is naturally this shape, and it is expensive to solve. or receding-horizonPlanning over a short window ahead, executing the first step, then planning again from the new state. It can respond to changing conditions more often than one long fixed schedule. methods. You will own the planner contract, the fixed-budget baselineThe existing or simpler method against which a new result is compared. Both methods must receive the same hardware assumptions, starting conditions and environment for the comparison to mean anything., and the scheduler for Reference Mission 01 before carrying the method into a servicing transfer case.
Computational physicist
You have an academic background in physics and you write code. You will build the physics-informed surrogatesA fast stand-in for a slow physics solver, usually machine-learned from that solver's own output. Physics-informed means the approximation is held to known physical laws instead of only fitting the data. that replace slow solversThe code that computes the answer to a physics problem, such as a temperature field or a power flow. Distinct from the model, which describes the problem. inside the planning loopThe repeating cycle in which a planner reads the current state, chooses the next actions, then revises as the state changes. For a physics model to sit inside this loop rather than beside it, it has to run fast enough to be consulted on every pass., and co-author the surrogate paper.
AI engineer
You come from software and you have worked with machine learning in earnest. You will begin from the reference model and its agreement tests, then own the learned components and performance work only where the benchmarkA fixed set of scenarios, metrics and baseline methods that anyone can run, so that results from different groups can be compared honestly. shows that a faster path is required.
Research students
You are in aerospace, robotics, or physics, and you want to run a benchmark scenario, extend a model, or co-author a paper through your laboratory.
How to apply
Apply by sending one thing you have built or written that you are proud of, together with a few lines on the initiative or paper you would want to work on. Write to research@mindpoollabs.com. Specific applications receive a reply.