knaxuslearn · build · ship

Roadmaps / Robotics / Who this is for

Read first

Who this is for

Hours by path. A Senior who skims Week 1 and skips Week 6 saves about 12 hours (about 116 hours of core work). A Staff reader doing Weeks 3, 4, 8 and 12 to 16 needs 8 weeks, 64 hours: 22 weeks at 3 hours a week. The work version is a separate effort of about 30 hours in work time. A Principal does Phase 4 (32 hours) plus the work version, about 62 hours in all.

You areStart atSkipYour assignmentsYour milestone scopeAim for
Fresher (under a year of work; Python, Linux shell, Git)Week 0, then Week 1Nothing. Do all the weeks, and plan 20Practice projects 1 and 2 in each phase, and checkpoints 1 to 4Core scope: one empty world, 20 goals, a 2-hour soak, no hardware2 Sound on every dimension
Senior (5 to 8 years, owns services, new to robots)Week 1 (skim it), then Week 2Week 6 if you know Kalman filtersAll practice projects, checkpoints 1 to 4Adds a cluttered world, a moving obstacle and the fault-injection suite3 Proven on every dimension
Staff (10+ years, sets direction)Weeks 3, 4 and 8, then Weeks 12 to 16Weeks 1, 2, 5 to 7, 9 and 10Checkpoints 1, 3 and 4, and the work version (Checkpoint W below)Adds a safety case, a failure taxonomy and a fleet-readiness memo3 on all, 4 on two
Principal (15+ years, sets strategy)The milestone section, Phase 4, then Interview topicsThe weekly tables of Phases 1 to 3The work version on a real robot or stack, plus a reusable checklistAdds a platform and safety decision memo with a measured outcome4 on at least two

Prerequisites for a fresher. If one is missing, do Week 0 first.

  • You can write Python: functions, classes, modules, reading a stack trace.
  • You can use a Linux shell: files, grep, environment variables, running a program.
  • You use Git: commit, branch, diff.
  • You know high-school geometry: angles, vectors, a coordinate frame.
  • You can multiply two small matrices by hand (Week 0 covers this).

Career change (for example a backend or embedded engineer moving into robots): start at Week 1 and skim what you know. The new ideas are coordinate frames, sensor noise and time, because a robot acts on data that is late, noisy and sometimes wrong.