Autonomous Machinery System
Applying robotics, AI, and edge computing to make traditional heavy machinery more intelligent, safer, and more productive.
Jason Ye · Baidu project, started 2018 · Engineering interview discussion
From lab research to real industrial autonomy deployment.
About me
- Zhixian Ye, or Jason
- UCSD ECE robotics track
- Baidu robotics, Sensing World AI/product, GM perception
Why it mattered
- Labor shortage in harsh industrial sites
- Improve safety without replacing people
- Jiangsu waste-factory excavator ran 24/7
Engineering goal
- Parse high-level customer tasks into common autonomy commands
- Share perception, planning, control, and safety modules
- Reuse simulation and replay across machine types
A hierarchical stack turned operator intent into coordinated base and arm execution.
Human-Robot Interface
Operator dispatches high-level work: move, dig, trench, supervise.
Task Resolver
Parses commands into segments, work cycles, and executable robot behaviors.
Base Loop
- Encoders, cameras, LiDAR, RTK localization
- Global route, local mapping, path following
- Obstacle avoidance while repositioning the machine
Arm & Digging Loop
- Inclination sensors and hydraulic valve readings
- Camera/LiDAR material-height and pile-shape sensing
- Dig, move, dig cycle with calibrated MPC/PID-style controls
Modularity made the system testable, portable, and safer to evolve.
Hardware boundary
Normalize sensors, drive-by-wire signals, hydraulics, and machine health behind explicit adapters.
Autonomy contracts
Keep perception, planning, control, and safety services loosely coupled through versioned interfaces.
Safety envelope
Use state machines and monitors so autonomy can degrade gracefully instead of failing silently.
Sim/replay loop
Turn field failures into deterministic tests before changing robot behavior in production.
The outcome was both technical credibility and business leverage.
The system generated publishable robotics work and reusable technical narratives.
Architecture, safety, perception, or control innovations became protectable assets.
Autonomy moved from prototype value to customer-facing machinery capability.
The modular stack reduced reinvention across machines, sites, and follow-on products.