https://davidnash.dev/write-ups Technical write-ups on robotics, control theory, and physics simulation by David Nash. en-us Tue, 08 Sep 2026 00:00:00 GMT https://davidnash.dev/write-ups/hardening-the-robot-brain https://davidnash.dev/write-ups/hardening-the-robot-brain Tue, 08 Sep 2026 00:00:00 GMT Continuing to improve the Mamba + LNN powered Franka Emika robot arm with parallelized cloud training, improved models, and closing the sim-to-real gap. https://davidnash.dev/write-ups/how-rl-training-works https://davidnash.dev/write-ups/how-rl-training-works Tue, 01 Sep 2026 00:00:00 GMT A systems view of continuous robot reinforcement learning: why control splits across a 20 Hz policy loop and a 500 Hz PD loop, how GAE trades bias for variance, the truncation bug that quietly biases every late-episode advantage, what the PPO clip does and does not constrain, and which metrics to read when a run goes bad. https://davidnash.dev/write-ups/mamba-lnn-robot https://davidnash.dev/write-ups/mamba-lnn-robot Tue, 18 Aug 2026 00:00:00 GMT Designing a multi-rate vision-based pick-and-place policy for a 7-DOF Franka Panda arm from first principles: 10 Hz Mamba-3 SSM Cortex, 50 Hz Liquid CfC Brainstem, SpatialSoftmax, and DLS Inverse Kinematics. https://davidnash.dev/tools/controller-picker https://davidnash.dev/tools/controller-picker Fri, 14 Aug 2026 00:00:00 GMT An interactive decision tree meant to help you find which controller is right for you between PID, LQR, MPC, NMPC, and more. https://davidnash.dev/write-ups/nonlinear-mpc https://davidnash.dev/write-ups/nonlinear-mpc Thu, 13 Aug 2026 00:00:00 GMT Ditch the pre-computation phase, the controller plans it all live, up to 200 times a second, in the browser. Learn how prediction controllers work. https://davidnash.dev/write-ups/bringing-reality-to-sim https://davidnash.dev/write-ups/bringing-reality-to-sim Sat, 08 Aug 2026 00:00:00 GMT The same controller, this time bringing a bit of the real world into the sim. Find out what breaks and how to fix it. https://davidnash.dev/write-ups/inverted-pendulum https://davidnash.dev/write-ups/inverted-pendulum Mon, 03 Aug 2026 00:00:00 GMT One motor against three degrees of freedom. I cover trajectory optimization, LQR, and the handoff between them. Everything running live in the browser.