Multivariable control: manage coupling between outputs
Move one output without disturbing another. Compare independent feedback with matrix decoupling, then test model mismatch and large actuator commands.
Writing
Clear accounts of what was tried and learned.
Explanations, tutorials, build notes, and essays grounded in work that can be examined. Explore a concept, try an experiment, and follow the reasoning behind it.
Start with the interactive foundationsShowing 13–24 of 151 posts
Nav2 costmap inflation: turn obstacles into navigation costs
Run a Nav2 costmap on a saved occupancy grid. Compare two inflation radii, inspect raw cell costs, and separate robot size from a preference for distance from obstacles.
Nav2 path planning: request a route and diagnose no path
Run the real Nav2 planner server on a saved map. Request a path between supplied poses, inspect the returned geometry, and diagnose a free goal that the planner cannot reach.
Open-loop vs closed-loop simulation: what replay can test
Run the same robot policy on recorded observations and in an interactive simulation. Compare proposed actions, executed motion, and the claims each test supports.
Pole placement: calculate state-feedback gains
Use pole placement to calculate position and velocity gains for a cart. Verify the closed-loop matrix, compare exact responses, and inspect the force each design requires.
Robot data leakage: split demonstrations by episode
Compare framewise and episodewise evaluation, then inspect downloadable train, validation, and final-test manifests with training-only preprocessing.
Robot foundation models: what transfers across robots?
Examine what robot foundation models transfer across tasks, scenes, and robot bodies. Compare dated RT-X, Octo, and OpenVLA papers, then calculate how evaluation weights change a ranking.
Robot learning generalization: what is actually unseen?
Map the conditions a robot policy saw during training. Compare familiar-value recombinations, unseen axis values, and extrapolation with two fitted policies and an explicit condition grid.
robot_localization in ROS 2: configure an odometry and IMU filter
Run the ROS 2 EKF with supplied wheel odometry and IMU data. Select measurement fields, check frames and covariance, and see how a biased gyro changes the estimated path.
Robot policy evaluation: success, failure, and episode counts
Evaluate robot policies with declared task rules and matched trials. Inspect a downloadable learned policy, shifted dynamics, failures, timeouts, and uncertainty.
Robotics simulation: choose the model for the question
Choose robotics simulation models by the question they can answer. Separate kinematics, force dynamics, numerical error, sensing, and hardware validation with a worked cart example.
ROS 2 bag: record, replay, and check the clock
Record six stamped points, inspect their saved contents, and replay them into a ROS 2 node. Reproduce a clock that stays at zero while messages still arrive.