Train a Manipulation Policy for Bin Picking with Imitation Learning
Overview
What this challenge is about.
You receive a dataset of 500 teleop trajectories on the in-distribution part plus a held-out simulation environment with a never-seen part. Train an imitation-learning policy (Diffusion Policy recommended; ACT acceptable) conditioned on RGB-D images and proprioception. Evaluate over 100 sim rollouts per condition: (a) in-distribution part, (b) novel part, (c) bin shifted by 5 cm. Report success rate, mean cycle time, and a failure-mode taxonomy. The memo recommends whether the team can move to a 50-pick real-robot pilot.
The Brief
What you'll do, and what you'll demonstrate.
Train an imitation-learning bin-picking policy that hits 85% success in simulation and degrades gracefully on novel parts.
Earning criteria — what you'll demonstrate
- Apply modern imitation-learning algorithms (Diffusion Policy / ACT) to manipulation
- Set up reproducible simulation evaluation for a manipulation policy
- Characterize policy generalization with structured rollout protocols
- Translate sim results into a defensible real-robot pilot recommendation
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career paths this builds toward
Canonical rolesMachine Learning Engineer
Training a manipulation policy end-to-end and shipping a pilot-readiness memo is exactly the senior-IC MLE workflow at robotics companies.
This challenge sharpens
- imitation-learning
- diffusion-policy
- pytorch
ML Researcher
Structured generalization evaluation on novel parts mirrors the rigor robotics ML researchers apply to their own results.
This challenge sharpens
- imitation-learning
- evaluation
- manipulation