Software stack & tools
Hardware without software is furniture. A serious learner — or a team that bought robots from SVRC — needs a repeatable software story: drivers, middleware, simulation, training, evaluation, and deployment.
Learning outcomes
- Order the stack from drivers through deployment and name one risk per layer.
- Explain why logging format should precede policy training on new hardware.
- Contrast simulation success with field metrics that matter for pilots.
Learn
Drivers → middleware → sim → data/learning → eval → deployment.
Practice
Draw your project’s stack; circle where time sync and logging live.
Challenge
Write a one-page “definition of done” for a policy update; share on the Forum.
Facilitation: Assign teams different layers — have them present failure modes upward/downward in the stack.
Self-check
I bought hardware — where do I start?
Vendor baseline, joint harness, then logging before ML — see Ownership.
What is one deployment metric that isn’t accuracy?
MTTR, pick cycle time, or regression rate on a fixed eval set.
STEM alignment: abstraction & modularity, computational thinking, testing & debugging.
Layers (build familiarity top to bottom)
- Drivers & real-time paths: motor controllers, CAN/EtherCAT, safe command paths — pairs with Communication & architecture.
- Middleware: ROS 2 graphs, recording, time sync — see Tools hub for frameworks.
- Simulation: MuJoCo, Isaac, MJX — reduce hardware wear while learning; align sim assets with real URDFs.
- Data & learning: episode formats, LeRobot-style pipelines, fine-tuning VLAs — Getting Started, Datasets, Models.
- Evaluation: success metrics, failure mining, regression tests before policy updates.
- Deployment: OTA configs, logging in the field, fleet hygiene — ties to Data Platform thinking.
How does SVRC help?
Data Services for collection, Data Platform for evaluation loops, and Contact for integration questions tied to gear you source from us.
Account & platform: Use the same SVRC account for store purchases, Forum posts, and points. Fearless Data Platform access is provisioned per organization at a stable URL — start from Data Platform and Contact for your deployment.