Writing
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 37–48 of 151 posts
Turn lidar angles and ranges into points, find the nearest visible surface with ray casting, and distinguish a missing return from an invalid reading. Inspect occlusion and coordinate frames in an interactive room.
Follow one cup from perception to grasping and recovery. Learn what Moravec’s paradox means, check a grasp’s clearance, and assess a robot demonstration.
Build a small occupancy grid from supplied range readings. Follow free-space and hit updates, calculate log odds, and distinguish unseen cells from conflicting evidence.
Estimate a robot's position with weighted particles. Follow motion prediction, sensor likelihoods, effective sample size, and systematic resampling, then test an initial belief that misses the robot entirely.
Optimize a small planar pose graph with real nonlinear updates. Calculate relative-pose residuals, anchor the world frame, and compare measurement fit with error against a synthetic reference.
Compare direct teleoperation, supervisory control, shared autonomy, and bounded task autonomy. Follow one grasping task, calculate communication delay, and read intervention records.
Choose topics for streams, services for short requests, and actions for goals with progress and results. Follow odometry, a reset, and a navigation cancellation.
Explore sim-to-real transfer by fitting a policy across actuator models. Test unseen gains, compare goal error and effort, and distinguish simulation checks from hardware evidence.
Follow a supplied loop measurement through a small SLAM graph. See how its weight changes the whole route, and why a false revisit can lower cost while increasing error.
Understand SLAM in robotics by solving a small landmark problem. Compare localization, mapping, and joint estimation, then see how anchoring and measurement weights change the answer.
Compare ATE, RPE, alignment, and timing with an interactive trajectory lab and downloadable Python evaluator. Inspect timestamp matches, missing coverage, and a misleading zero-error fit.
Learn how vision-language-action models connect images and instructions to robot actions. Compare token and continuous outputs, then inspect how units, frames, and timing change a synthetic command.